{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20096,
  "eval_steps": 500,
  "global_step": 157,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00128,
      "grad_norm": 2.8870697066158506,
      "learning_rate": 0.0,
      "loss": 0.8422,
      "step": 1
    },
    {
      "epoch": 0.00256,
      "grad_norm": 2.88484389829891,
      "learning_rate": 6.329113924050633e-07,
      "loss": 0.8541,
      "step": 2
    },
    {
      "epoch": 0.00384,
      "grad_norm": 2.858151965789657,
      "learning_rate": 1.2658227848101265e-06,
      "loss": 0.8376,
      "step": 3
    },
    {
      "epoch": 0.00512,
      "grad_norm": 2.759628117182127,
      "learning_rate": 1.8987341772151901e-06,
      "loss": 0.8334,
      "step": 4
    },
    {
      "epoch": 0.0064,
      "grad_norm": 2.796990062811218,
      "learning_rate": 2.531645569620253e-06,
      "loss": 0.8256,
      "step": 5
    },
    {
      "epoch": 0.00768,
      "grad_norm": 2.5779298795445023,
      "learning_rate": 3.1645569620253167e-06,
      "loss": 0.8301,
      "step": 6
    },
    {
      "epoch": 0.00896,
      "grad_norm": 2.182261607936066,
      "learning_rate": 3.7974683544303802e-06,
      "loss": 0.8156,
      "step": 7
    },
    {
      "epoch": 0.01024,
      "grad_norm": 1.9615896152651355,
      "learning_rate": 4.430379746835443e-06,
      "loss": 0.7982,
      "step": 8
    },
    {
      "epoch": 0.01152,
      "grad_norm": 1.452541644948315,
      "learning_rate": 5.063291139240506e-06,
      "loss": 0.7819,
      "step": 9
    },
    {
      "epoch": 0.0128,
      "grad_norm": 1.4723286808630864,
      "learning_rate": 5.69620253164557e-06,
      "loss": 0.7906,
      "step": 10
    },
    {
      "epoch": 0.01408,
      "grad_norm": 1.3529636617858944,
      "learning_rate": 6.329113924050633e-06,
      "loss": 0.7724,
      "step": 11
    },
    {
      "epoch": 0.01536,
      "grad_norm": 1.960737179905222,
      "learning_rate": 6.9620253164556965e-06,
      "loss": 0.7495,
      "step": 12
    },
    {
      "epoch": 0.01664,
      "grad_norm": 2.2349101055406337,
      "learning_rate": 7.5949367088607605e-06,
      "loss": 0.7581,
      "step": 13
    },
    {
      "epoch": 0.01792,
      "grad_norm": 2.0897577150322477,
      "learning_rate": 8.227848101265822e-06,
      "loss": 0.7404,
      "step": 14
    },
    {
      "epoch": 0.0192,
      "grad_norm": 1.8227218322635887,
      "learning_rate": 8.860759493670886e-06,
      "loss": 0.7382,
      "step": 15
    },
    {
      "epoch": 0.02048,
      "grad_norm": 1.2099951464458898,
      "learning_rate": 9.49367088607595e-06,
      "loss": 0.7231,
      "step": 16
    },
    {
      "epoch": 0.02176,
      "grad_norm": 1.2177037129914572,
      "learning_rate": 1.0126582278481012e-05,
      "loss": 0.7259,
      "step": 17
    },
    {
      "epoch": 0.02304,
      "grad_norm": 1.1031346132830708,
      "learning_rate": 1.0759493670886076e-05,
      "loss": 0.7059,
      "step": 18
    },
    {
      "epoch": 0.02432,
      "grad_norm": 0.9194779600801882,
      "learning_rate": 1.139240506329114e-05,
      "loss": 0.7137,
      "step": 19
    },
    {
      "epoch": 0.0256,
      "grad_norm": 0.8679468005972053,
      "learning_rate": 1.2025316455696203e-05,
      "loss": 0.7036,
      "step": 20
    },
    {
      "epoch": 0.02688,
      "grad_norm": 0.7227287276969042,
      "learning_rate": 1.2658227848101267e-05,
      "loss": 0.696,
      "step": 21
    },
    {
      "epoch": 0.02816,
      "grad_norm": 0.7425882516811844,
      "learning_rate": 1.3291139240506329e-05,
      "loss": 0.6888,
      "step": 22
    },
    {
      "epoch": 0.02944,
      "grad_norm": 0.7093793012252196,
      "learning_rate": 1.3924050632911393e-05,
      "loss": 0.6791,
      "step": 23
    },
    {
      "epoch": 0.03072,
      "grad_norm": 0.6018215463147907,
      "learning_rate": 1.4556962025316457e-05,
      "loss": 0.6783,
      "step": 24
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.5846346732378257,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 0.6811,
      "step": 25
    },
    {
      "epoch": 0.03328,
      "grad_norm": 0.5855419788452784,
      "learning_rate": 1.5822784810126583e-05,
      "loss": 0.683,
      "step": 26
    },
    {
      "epoch": 0.03456,
      "grad_norm": 0.5096689891724868,
      "learning_rate": 1.6455696202531644e-05,
      "loss": 0.6589,
      "step": 27
    },
    {
      "epoch": 0.03584,
      "grad_norm": 0.4871170504081146,
      "learning_rate": 1.7088607594936708e-05,
      "loss": 0.6582,
      "step": 28
    },
    {
      "epoch": 0.03712,
      "grad_norm": 0.4949600697144217,
      "learning_rate": 1.7721518987341772e-05,
      "loss": 0.669,
      "step": 29
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.5082926031630941,
      "learning_rate": 1.8354430379746836e-05,
      "loss": 0.666,
      "step": 30
    },
    {
      "epoch": 0.03968,
      "grad_norm": 0.49381475380567175,
      "learning_rate": 1.89873417721519e-05,
      "loss": 0.6556,
      "step": 31
    },
    {
      "epoch": 0.04096,
      "grad_norm": 0.4265624784331274,
      "learning_rate": 1.962025316455696e-05,
      "loss": 0.646,
      "step": 32
    },
    {
      "epoch": 0.04224,
      "grad_norm": 0.39190416547723717,
      "learning_rate": 2.0253164556962025e-05,
      "loss": 0.6473,
      "step": 33
    },
    {
      "epoch": 0.04352,
      "grad_norm": 0.4631353399929371,
      "learning_rate": 2.088607594936709e-05,
      "loss": 0.6441,
      "step": 34
    },
    {
      "epoch": 0.0448,
      "grad_norm": 0.3928335126997034,
      "learning_rate": 2.1518987341772153e-05,
      "loss": 0.6352,
      "step": 35
    },
    {
      "epoch": 0.04608,
      "grad_norm": 0.36295027582313966,
      "learning_rate": 2.2151898734177217e-05,
      "loss": 0.6333,
      "step": 36
    },
    {
      "epoch": 0.04736,
      "grad_norm": 0.35026852064181846,
      "learning_rate": 2.278481012658228e-05,
      "loss": 0.6399,
      "step": 37
    },
    {
      "epoch": 0.04864,
      "grad_norm": 0.39778614916835536,
      "learning_rate": 2.341772151898734e-05,
      "loss": 0.6298,
      "step": 38
    },
    {
      "epoch": 0.04992,
      "grad_norm": 0.33278348666417684,
      "learning_rate": 2.4050632911392405e-05,
      "loss": 0.6301,
      "step": 39
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.31444068712551376,
      "learning_rate": 2.468354430379747e-05,
      "loss": 0.6263,
      "step": 40
    },
    {
      "epoch": 0.05248,
      "grad_norm": 0.36059728676958264,
      "learning_rate": 2.5316455696202533e-05,
      "loss": 0.6458,
      "step": 41
    },
    {
      "epoch": 0.05376,
      "grad_norm": 0.3916144552301749,
      "learning_rate": 2.5949367088607597e-05,
      "loss": 0.6331,
      "step": 42
    },
    {
      "epoch": 0.05504,
      "grad_norm": 0.32338566356420756,
      "learning_rate": 2.6582278481012658e-05,
      "loss": 0.6332,
      "step": 43
    },
    {
      "epoch": 0.05632,
      "grad_norm": 0.33704233729853356,
      "learning_rate": 2.7215189873417722e-05,
      "loss": 0.6348,
      "step": 44
    },
    {
      "epoch": 0.0576,
      "grad_norm": 0.36015399213900634,
      "learning_rate": 2.7848101265822786e-05,
      "loss": 0.6392,
      "step": 45
    },
    {
      "epoch": 0.05888,
      "grad_norm": 0.31471331803021757,
      "learning_rate": 2.848101265822785e-05,
      "loss": 0.6272,
      "step": 46
    },
    {
      "epoch": 0.06016,
      "grad_norm": 0.3225170654156012,
      "learning_rate": 2.9113924050632914e-05,
      "loss": 0.635,
      "step": 47
    },
    {
      "epoch": 0.06144,
      "grad_norm": 0.3064473735810606,
      "learning_rate": 2.9746835443037974e-05,
      "loss": 0.6284,
      "step": 48
    },
    {
      "epoch": 0.06272,
      "grad_norm": 0.3038289969291092,
      "learning_rate": 3.0379746835443042e-05,
      "loss": 0.6149,
      "step": 49
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.3226803690164346,
      "learning_rate": 3.10126582278481e-05,
      "loss": 0.626,
      "step": 50
    },
    {
      "epoch": 0.06528,
      "grad_norm": 0.3096398144524693,
      "learning_rate": 3.1645569620253167e-05,
      "loss": 0.621,
      "step": 51
    },
    {
      "epoch": 0.06656,
      "grad_norm": 0.2754757429130796,
      "learning_rate": 3.227848101265823e-05,
      "loss": 0.6185,
      "step": 52
    },
    {
      "epoch": 0.06784,
      "grad_norm": 0.3262507218160328,
      "learning_rate": 3.291139240506329e-05,
      "loss": 0.6171,
      "step": 53
    },
    {
      "epoch": 0.06912,
      "grad_norm": 0.34971068352090656,
      "learning_rate": 3.354430379746836e-05,
      "loss": 0.616,
      "step": 54
    },
    {
      "epoch": 0.0704,
      "grad_norm": 0.2841621281043231,
      "learning_rate": 3.4177215189873416e-05,
      "loss": 0.5995,
      "step": 55
    },
    {
      "epoch": 0.07168,
      "grad_norm": 0.4003223636484448,
      "learning_rate": 3.4810126582278487e-05,
      "loss": 0.6169,
      "step": 56
    },
    {
      "epoch": 0.07296,
      "grad_norm": 0.31868860231705426,
      "learning_rate": 3.5443037974683544e-05,
      "loss": 0.6077,
      "step": 57
    },
    {
      "epoch": 0.07424,
      "grad_norm": 0.3960425782005289,
      "learning_rate": 3.607594936708861e-05,
      "loss": 0.6164,
      "step": 58
    },
    {
      "epoch": 0.07552,
      "grad_norm": 0.363865574596696,
      "learning_rate": 3.670886075949367e-05,
      "loss": 0.6118,
      "step": 59
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.33961478774466697,
      "learning_rate": 3.7341772151898736e-05,
      "loss": 0.6137,
      "step": 60
    },
    {
      "epoch": 0.07808,
      "grad_norm": 0.4212164741206082,
      "learning_rate": 3.79746835443038e-05,
      "loss": 0.6275,
      "step": 61
    },
    {
      "epoch": 0.07936,
      "grad_norm": 0.29878729710395663,
      "learning_rate": 3.8607594936708864e-05,
      "loss": 0.6084,
      "step": 62
    },
    {
      "epoch": 0.08064,
      "grad_norm": 0.36745026817379894,
      "learning_rate": 3.924050632911392e-05,
      "loss": 0.607,
      "step": 63
    },
    {
      "epoch": 0.08192,
      "grad_norm": 0.38983571508393644,
      "learning_rate": 3.987341772151899e-05,
      "loss": 0.6176,
      "step": 64
    },
    {
      "epoch": 0.0832,
      "grad_norm": 0.37337392917475115,
      "learning_rate": 4.050632911392405e-05,
      "loss": 0.6184,
      "step": 65
    },
    {
      "epoch": 0.08448,
      "grad_norm": 0.3668068115925863,
      "learning_rate": 4.113924050632912e-05,
      "loss": 0.6194,
      "step": 66
    },
    {
      "epoch": 0.08576,
      "grad_norm": 0.36138503055306903,
      "learning_rate": 4.177215189873418e-05,
      "loss": 0.6077,
      "step": 67
    },
    {
      "epoch": 0.08704,
      "grad_norm": 0.43361127462043814,
      "learning_rate": 4.240506329113924e-05,
      "loss": 0.6147,
      "step": 68
    },
    {
      "epoch": 0.08832,
      "grad_norm": 0.33520423726109644,
      "learning_rate": 4.3037974683544305e-05,
      "loss": 0.6118,
      "step": 69
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.4381154362148859,
      "learning_rate": 4.367088607594937e-05,
      "loss": 0.6031,
      "step": 70
    },
    {
      "epoch": 0.09088,
      "grad_norm": 0.3717345864324632,
      "learning_rate": 4.430379746835443e-05,
      "loss": 0.6031,
      "step": 71
    },
    {
      "epoch": 0.09216,
      "grad_norm": 0.4861728465398392,
      "learning_rate": 4.49367088607595e-05,
      "loss": 0.6006,
      "step": 72
    },
    {
      "epoch": 0.09344,
      "grad_norm": 0.3264992939190504,
      "learning_rate": 4.556962025316456e-05,
      "loss": 0.6151,
      "step": 73
    },
    {
      "epoch": 0.09472,
      "grad_norm": 0.4319794925001871,
      "learning_rate": 4.6202531645569625e-05,
      "loss": 0.6058,
      "step": 74
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.4616345840492333,
      "learning_rate": 4.683544303797468e-05,
      "loss": 0.5967,
      "step": 75
    },
    {
      "epoch": 0.09728,
      "grad_norm": 0.4405721152587957,
      "learning_rate": 4.7468354430379746e-05,
      "loss": 0.6002,
      "step": 76
    },
    {
      "epoch": 0.09856,
      "grad_norm": 0.5122605377853799,
      "learning_rate": 4.810126582278481e-05,
      "loss": 0.6076,
      "step": 77
    },
    {
      "epoch": 0.09984,
      "grad_norm": 0.45313870340097556,
      "learning_rate": 4.8734177215189874e-05,
      "loss": 0.6074,
      "step": 78
    },
    {
      "epoch": 0.10112,
      "grad_norm": 0.4340044755876676,
      "learning_rate": 4.936708860759494e-05,
      "loss": 0.606,
      "step": 79
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.4987172862476422,
      "learning_rate": 5e-05,
      "loss": 0.6158,
      "step": 80
    },
    {
      "epoch": 0.10368,
      "grad_norm": 0.6226880208665108,
      "learning_rate": 4.999974965737065e-05,
      "loss": 0.621,
      "step": 81
    },
    {
      "epoch": 0.10496,
      "grad_norm": 0.5448293131914782,
      "learning_rate": 4.999899863449631e-05,
      "loss": 0.6014,
      "step": 82
    },
    {
      "epoch": 0.10624,
      "grad_norm": 0.3427022601926917,
      "learning_rate": 4.999774694641803e-05,
      "loss": 0.6198,
      "step": 83
    },
    {
      "epoch": 0.10752,
      "grad_norm": 0.5005152113593655,
      "learning_rate": 4.999599461820387e-05,
      "loss": 0.6054,
      "step": 84
    },
    {
      "epoch": 0.1088,
      "grad_norm": 0.5702968806820528,
      "learning_rate": 4.999374168494844e-05,
      "loss": 0.6069,
      "step": 85
    },
    {
      "epoch": 0.11008,
      "grad_norm": 0.4671310661706222,
      "learning_rate": 4.999098819177214e-05,
      "loss": 0.6017,
      "step": 86
    },
    {
      "epoch": 0.11136,
      "grad_norm": 0.46081768174689064,
      "learning_rate": 4.9987734193820324e-05,
      "loss": 0.5988,
      "step": 87
    },
    {
      "epoch": 0.11264,
      "grad_norm": 0.5448729856183013,
      "learning_rate": 4.9983979756262136e-05,
      "loss": 0.6181,
      "step": 88
    },
    {
      "epoch": 0.11392,
      "grad_norm": 0.5095775592779056,
      "learning_rate": 4.9979724954289244e-05,
      "loss": 0.608,
      "step": 89
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.41119162739543413,
      "learning_rate": 4.997496987311431e-05,
      "loss": 0.5979,
      "step": 90
    },
    {
      "epoch": 0.11648,
      "grad_norm": 0.45501958535738946,
      "learning_rate": 4.996971460796929e-05,
      "loss": 0.6019,
      "step": 91
    },
    {
      "epoch": 0.11776,
      "grad_norm": 0.4287172104360816,
      "learning_rate": 4.9963959264103544e-05,
      "loss": 0.5955,
      "step": 92
    },
    {
      "epoch": 0.11904,
      "grad_norm": 0.409872269342458,
      "learning_rate": 4.995770395678171e-05,
      "loss": 0.5927,
      "step": 93
    },
    {
      "epoch": 0.12032,
      "grad_norm": 0.4304173966206036,
      "learning_rate": 4.995094881128138e-05,
      "loss": 0.5967,
      "step": 94
    },
    {
      "epoch": 0.1216,
      "grad_norm": 0.4229799776298517,
      "learning_rate": 4.994369396289063e-05,
      "loss": 0.6084,
      "step": 95
    },
    {
      "epoch": 0.12288,
      "grad_norm": 0.4509596954971553,
      "learning_rate": 4.9935939556905295e-05,
      "loss": 0.6134,
      "step": 96
    },
    {
      "epoch": 0.12416,
      "grad_norm": 0.467661146414229,
      "learning_rate": 4.992768574862603e-05,
      "loss": 0.5986,
      "step": 97
    },
    {
      "epoch": 0.12544,
      "grad_norm": 0.42432875998240194,
      "learning_rate": 4.9918932703355256e-05,
      "loss": 0.6028,
      "step": 98
    },
    {
      "epoch": 0.12672,
      "grad_norm": 0.43479377184835605,
      "learning_rate": 4.990968059639379e-05,
      "loss": 0.5942,
      "step": 99
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.3680676685801686,
      "learning_rate": 4.989992961303738e-05,
      "loss": 0.5994,
      "step": 100
    },
    {
      "epoch": 0.12928,
      "grad_norm": 0.3956815409903461,
      "learning_rate": 4.9889679948572974e-05,
      "loss": 0.5871,
      "step": 101
    },
    {
      "epoch": 0.13056,
      "grad_norm": 0.34354949934586104,
      "learning_rate": 4.98789318082748e-05,
      "loss": 0.5873,
      "step": 102
    },
    {
      "epoch": 0.13184,
      "grad_norm": 0.3608260963951222,
      "learning_rate": 4.986768540740028e-05,
      "loss": 0.5883,
      "step": 103
    },
    {
      "epoch": 0.13312,
      "grad_norm": 0.3937004101078116,
      "learning_rate": 4.98559409711857e-05,
      "loss": 0.6029,
      "step": 104
    },
    {
      "epoch": 0.1344,
      "grad_norm": 0.3401718481532899,
      "learning_rate": 4.9843698734841705e-05,
      "loss": 0.5983,
      "step": 105
    },
    {
      "epoch": 0.13568,
      "grad_norm": 0.4371868869288284,
      "learning_rate": 4.983095894354858e-05,
      "loss": 0.5866,
      "step": 106
    },
    {
      "epoch": 0.13696,
      "grad_norm": 0.3722813571279646,
      "learning_rate": 4.981772185245135e-05,
      "loss": 0.5954,
      "step": 107
    },
    {
      "epoch": 0.13824,
      "grad_norm": 0.36493596395606354,
      "learning_rate": 4.980398772665468e-05,
      "loss": 0.5806,
      "step": 108
    },
    {
      "epoch": 0.13952,
      "grad_norm": 0.43678937522389644,
      "learning_rate": 4.9789756841217546e-05,
      "loss": 0.595,
      "step": 109
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.34968596729530604,
      "learning_rate": 4.977502948114772e-05,
      "loss": 0.5999,
      "step": 110
    },
    {
      "epoch": 0.14208,
      "grad_norm": 0.4035249077012057,
      "learning_rate": 4.9759805941396075e-05,
      "loss": 0.582,
      "step": 111
    },
    {
      "epoch": 0.14336,
      "grad_norm": 0.3396387531525401,
      "learning_rate": 4.974408652685072e-05,
      "loss": 0.5912,
      "step": 112
    },
    {
      "epoch": 0.14464,
      "grad_norm": 0.3888124435581031,
      "learning_rate": 4.9727871552330794e-05,
      "loss": 0.5994,
      "step": 113
    },
    {
      "epoch": 0.14592,
      "grad_norm": 0.3487289265208422,
      "learning_rate": 4.971116134258025e-05,
      "loss": 0.598,
      "step": 114
    },
    {
      "epoch": 0.1472,
      "grad_norm": 0.34084258932596606,
      "learning_rate": 4.969395623226133e-05,
      "loss": 0.5965,
      "step": 115
    },
    {
      "epoch": 0.14848,
      "grad_norm": 0.33211872605390524,
      "learning_rate": 4.967625656594782e-05,
      "loss": 0.5984,
      "step": 116
    },
    {
      "epoch": 0.14976,
      "grad_norm": 0.31055192632357626,
      "learning_rate": 4.9658062698118213e-05,
      "loss": 0.593,
      "step": 117
    },
    {
      "epoch": 0.15104,
      "grad_norm": 0.35790400007793166,
      "learning_rate": 4.963937499314857e-05,
      "loss": 0.6035,
      "step": 118
    },
    {
      "epoch": 0.15232,
      "grad_norm": 0.31118450185510343,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.5811,
      "step": 119
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.3326176465041298,
      "learning_rate": 4.960051957873725e-05,
      "loss": 0.581,
      "step": 120
    },
    {
      "epoch": 0.15488,
      "grad_norm": 0.30210249377153575,
      "learning_rate": 4.958035264746893e-05,
      "loss": 0.5837,
      "step": 121
    },
    {
      "epoch": 0.15616,
      "grad_norm": 0.3480385124671555,
      "learning_rate": 4.955969343539162e-05,
      "loss": 0.5768,
      "step": 122
    },
    {
      "epoch": 0.15744,
      "grad_norm": 0.3003392569743352,
      "learning_rate": 4.9538542356255866e-05,
      "loss": 0.5938,
      "step": 123
    },
    {
      "epoch": 0.15872,
      "grad_norm": 0.32082565179488104,
      "learning_rate": 4.9516899833663e-05,
      "loss": 0.5948,
      "step": 124
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.3564349708048278,
      "learning_rate": 4.949476630105669e-05,
      "loss": 0.595,
      "step": 125
    },
    {
      "epoch": 0.16128,
      "grad_norm": 0.32049541972124757,
      "learning_rate": 4.94721422017143e-05,
      "loss": 0.5838,
      "step": 126
    },
    {
      "epoch": 0.16256,
      "grad_norm": 0.3317680882353993,
      "learning_rate": 4.944902798873794e-05,
      "loss": 0.5952,
      "step": 127
    },
    {
      "epoch": 0.16384,
      "grad_norm": 0.3381465061198974,
      "learning_rate": 4.942542412504543e-05,
      "loss": 0.6004,
      "step": 128
    },
    {
      "epoch": 0.16512,
      "grad_norm": 0.38351657127693595,
      "learning_rate": 4.940133108336105e-05,
      "loss": 0.6014,
      "step": 129
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.3276142738951724,
      "learning_rate": 4.9376749346206006e-05,
      "loss": 0.5853,
      "step": 130
    },
    {
      "epoch": 0.16768,
      "grad_norm": 0.37146400882939534,
      "learning_rate": 4.935167940588887e-05,
      "loss": 0.5995,
      "step": 131
    },
    {
      "epoch": 0.16896,
      "grad_norm": 0.32804274509201087,
      "learning_rate": 4.9326121764495596e-05,
      "loss": 0.5955,
      "step": 132
    },
    {
      "epoch": 0.17024,
      "grad_norm": 0.3344845806030499,
      "learning_rate": 4.9300076933879574e-05,
      "loss": 0.5818,
      "step": 133
    },
    {
      "epoch": 0.17152,
      "grad_norm": 0.3479572078392269,
      "learning_rate": 4.92735454356513e-05,
      "loss": 0.5941,
      "step": 134
    },
    {
      "epoch": 0.1728,
      "grad_norm": 0.34868252062960353,
      "learning_rate": 4.924652780116799e-05,
      "loss": 0.5898,
      "step": 135
    },
    {
      "epoch": 0.17408,
      "grad_norm": 0.35674279058993497,
      "learning_rate": 4.921902457152289e-05,
      "loss": 0.5899,
      "step": 136
    },
    {
      "epoch": 0.17536,
      "grad_norm": 0.3672614416380493,
      "learning_rate": 4.9191036297534454e-05,
      "loss": 0.585,
      "step": 137
    },
    {
      "epoch": 0.17664,
      "grad_norm": 0.4039478601084677,
      "learning_rate": 4.916256353973535e-05,
      "loss": 0.5994,
      "step": 138
    },
    {
      "epoch": 0.17792,
      "grad_norm": 0.3428958061155067,
      "learning_rate": 4.913360686836117e-05,
      "loss": 0.575,
      "step": 139
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.4024960602256603,
      "learning_rate": 4.910416686333906e-05,
      "loss": 0.5913,
      "step": 140
    },
    {
      "epoch": 0.18048,
      "grad_norm": 0.31040065034832104,
      "learning_rate": 4.907424411427608e-05,
      "loss": 0.5761,
      "step": 141
    },
    {
      "epoch": 0.18176,
      "grad_norm": 0.359237099401051,
      "learning_rate": 4.90438392204474e-05,
      "loss": 0.5885,
      "step": 142
    },
    {
      "epoch": 0.18304,
      "grad_norm": 0.3357545415879296,
      "learning_rate": 4.901295279078431e-05,
      "loss": 0.5907,
      "step": 143
    },
    {
      "epoch": 0.18432,
      "grad_norm": 0.2846403022642179,
      "learning_rate": 4.898158544386201e-05,
      "loss": 0.5886,
      "step": 144
    },
    {
      "epoch": 0.1856,
      "grad_norm": 0.3636245125193307,
      "learning_rate": 4.894973780788722e-05,
      "loss": 0.5816,
      "step": 145
    },
    {
      "epoch": 0.18688,
      "grad_norm": 0.25440894793562924,
      "learning_rate": 4.8917410520685635e-05,
      "loss": 0.576,
      "step": 146
    },
    {
      "epoch": 0.18816,
      "grad_norm": 0.3380189678855273,
      "learning_rate": 4.888460422968908e-05,
      "loss": 0.5931,
      "step": 147
    },
    {
      "epoch": 0.18944,
      "grad_norm": 0.3096794617975588,
      "learning_rate": 4.885131959192262e-05,
      "loss": 0.5829,
      "step": 148
    },
    {
      "epoch": 0.19072,
      "grad_norm": 0.280174710159943,
      "learning_rate": 4.881755727399134e-05,
      "loss": 0.5794,
      "step": 149
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.31769340776297994,
      "learning_rate": 4.878331795206705e-05,
      "loss": 0.5729,
      "step": 150
    },
    {
      "epoch": 0.19328,
      "grad_norm": 0.31671973855902796,
      "learning_rate": 4.8748602311874694e-05,
      "loss": 0.5905,
      "step": 151
    },
    {
      "epoch": 0.19456,
      "grad_norm": 0.32614211009906474,
      "learning_rate": 4.8713411048678635e-05,
      "loss": 0.5855,
      "step": 152
    },
    {
      "epoch": 0.19584,
      "grad_norm": 0.29921149443441614,
      "learning_rate": 4.8677744867268764e-05,
      "loss": 0.5779,
      "step": 153
    },
    {
      "epoch": 0.19712,
      "grad_norm": 0.3558339409344647,
      "learning_rate": 4.8641604481946314e-05,
      "loss": 0.5892,
      "step": 154
    },
    {
      "epoch": 0.1984,
      "grad_norm": 0.285079025062,
      "learning_rate": 4.8604990616509616e-05,
      "loss": 0.5912,
      "step": 155
    },
    {
      "epoch": 0.19968,
      "grad_norm": 0.32189736402098207,
      "learning_rate": 4.856790400423958e-05,
      "loss": 0.5881,
      "step": 156
    },
    {
      "epoch": 0.20096,
      "grad_norm": 0.3293153125716864,
      "learning_rate": 4.8530345387885004e-05,
      "loss": 0.5679,
      "step": 157
    }
  ],
  "logging_steps": 1,
  "max_steps": 781,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 157,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 194598775488512.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}