{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1380738695201933,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034518467380048324,
      "grad_norm": 164.25050354003906,
      "learning_rate": 0.0,
      "loss": 1.9257,
      "step": 1
    },
    {
      "epoch": 0.0006903693476009665,
      "grad_norm": 116.43001556396484,
      "learning_rate": 2e-05,
      "loss": 1.8201,
      "step": 2
    },
    {
      "epoch": 0.0010355540214014498,
      "grad_norm": 111.98278045654297,
      "learning_rate": 2e-05,
      "loss": 1.9652,
      "step": 3
    },
    {
      "epoch": 0.001380738695201933,
      "grad_norm": 312.7107238769531,
      "learning_rate": 2e-05,
      "loss": 1.6971,
      "step": 4
    },
    {
      "epoch": 0.0017259233690024164,
      "grad_norm": 124.51359558105469,
      "learning_rate": 2e-05,
      "loss": 1.7228,
      "step": 5
    },
    {
      "epoch": 0.0020711080428028996,
      "grad_norm": 117.87893676757812,
      "learning_rate": 2e-05,
      "loss": 1.7254,
      "step": 6
    },
    {
      "epoch": 0.002416292716603383,
      "grad_norm": 59.12928771972656,
      "learning_rate": 2e-05,
      "loss": 1.473,
      "step": 7
    },
    {
      "epoch": 0.002761477390403866,
      "grad_norm": 24.38951873779297,
      "learning_rate": 2e-05,
      "loss": 1.5216,
      "step": 8
    },
    {
      "epoch": 0.0031066620642043494,
      "grad_norm": 57.787757873535156,
      "learning_rate": 2e-05,
      "loss": 1.5563,
      "step": 9
    },
    {
      "epoch": 0.0034518467380048328,
      "grad_norm": 21.435535430908203,
      "learning_rate": 2e-05,
      "loss": 1.4052,
      "step": 10
    },
    {
      "epoch": 0.0037970314118053157,
      "grad_norm": 25.76114273071289,
      "learning_rate": 2e-05,
      "loss": 1.4289,
      "step": 11
    },
    {
      "epoch": 0.004142216085605799,
      "grad_norm": 16.697547912597656,
      "learning_rate": 2e-05,
      "loss": 1.5014,
      "step": 12
    },
    {
      "epoch": 0.0044874007594062825,
      "grad_norm": 10.946109771728516,
      "learning_rate": 2e-05,
      "loss": 1.4236,
      "step": 13
    },
    {
      "epoch": 0.004832585433206766,
      "grad_norm": 9.638275146484375,
      "learning_rate": 2e-05,
      "loss": 1.4098,
      "step": 14
    },
    {
      "epoch": 0.0051777701070072485,
      "grad_norm": 17.02400016784668,
      "learning_rate": 2e-05,
      "loss": 1.4035,
      "step": 15
    },
    {
      "epoch": 0.005522954780807732,
      "grad_norm": 7.689630508422852,
      "learning_rate": 2e-05,
      "loss": 1.3273,
      "step": 16
    },
    {
      "epoch": 0.005868139454608215,
      "grad_norm": 7.028171539306641,
      "learning_rate": 2e-05,
      "loss": 1.3675,
      "step": 17
    },
    {
      "epoch": 0.006213324128408699,
      "grad_norm": 8.425003051757812,
      "learning_rate": 2e-05,
      "loss": 1.3065,
      "step": 18
    },
    {
      "epoch": 0.006558508802209182,
      "grad_norm": 7.860549449920654,
      "learning_rate": 2e-05,
      "loss": 1.2914,
      "step": 19
    },
    {
      "epoch": 0.0069036934760096655,
      "grad_norm": 5.793131351470947,
      "learning_rate": 2e-05,
      "loss": 1.2639,
      "step": 20
    },
    {
      "epoch": 0.007248878149810148,
      "grad_norm": 6.066828727722168,
      "learning_rate": 2e-05,
      "loss": 1.2845,
      "step": 21
    },
    {
      "epoch": 0.0075940628236106315,
      "grad_norm": 6.9683074951171875,
      "learning_rate": 2e-05,
      "loss": 1.2839,
      "step": 22
    },
    {
      "epoch": 0.007939247497411116,
      "grad_norm": 7.026453018188477,
      "learning_rate": 2e-05,
      "loss": 1.3129,
      "step": 23
    },
    {
      "epoch": 0.008284432171211598,
      "grad_norm": 6.011166095733643,
      "learning_rate": 2e-05,
      "loss": 1.2021,
      "step": 24
    },
    {
      "epoch": 0.00862961684501208,
      "grad_norm": 6.688496112823486,
      "learning_rate": 2e-05,
      "loss": 1.2988,
      "step": 25
    },
    {
      "epoch": 0.008974801518812565,
      "grad_norm": 5.536924839019775,
      "learning_rate": 2e-05,
      "loss": 1.2529,
      "step": 26
    },
    {
      "epoch": 0.009319986192613048,
      "grad_norm": 6.189913749694824,
      "learning_rate": 2e-05,
      "loss": 1.2541,
      "step": 27
    },
    {
      "epoch": 0.009665170866413532,
      "grad_norm": 5.186566352844238,
      "learning_rate": 2e-05,
      "loss": 1.1685,
      "step": 28
    },
    {
      "epoch": 0.010010355540214014,
      "grad_norm": 5.111907482147217,
      "learning_rate": 2e-05,
      "loss": 1.1647,
      "step": 29
    },
    {
      "epoch": 0.010355540214014497,
      "grad_norm": 7.816215515136719,
      "learning_rate": 2e-05,
      "loss": 1.1613,
      "step": 30
    },
    {
      "epoch": 0.010700724887814981,
      "grad_norm": 6.994287014007568,
      "learning_rate": 2e-05,
      "loss": 1.1798,
      "step": 31
    },
    {
      "epoch": 0.011045909561615464,
      "grad_norm": 6.679455280303955,
      "learning_rate": 2e-05,
      "loss": 1.1356,
      "step": 32
    },
    {
      "epoch": 0.011391094235415948,
      "grad_norm": 5.451405048370361,
      "learning_rate": 2e-05,
      "loss": 1.1679,
      "step": 33
    },
    {
      "epoch": 0.01173627890921643,
      "grad_norm": 5.443926811218262,
      "learning_rate": 2e-05,
      "loss": 1.1729,
      "step": 34
    },
    {
      "epoch": 0.012081463583016915,
      "grad_norm": 5.605351448059082,
      "learning_rate": 2e-05,
      "loss": 1.1808,
      "step": 35
    },
    {
      "epoch": 0.012426648256817397,
      "grad_norm": 5.121994972229004,
      "learning_rate": 2e-05,
      "loss": 1.1379,
      "step": 36
    },
    {
      "epoch": 0.01277183293061788,
      "grad_norm": 4.825695037841797,
      "learning_rate": 2e-05,
      "loss": 1.1291,
      "step": 37
    },
    {
      "epoch": 0.013117017604418364,
      "grad_norm": 4.905743598937988,
      "learning_rate": 2e-05,
      "loss": 1.1687,
      "step": 38
    },
    {
      "epoch": 0.013462202278218847,
      "grad_norm": 5.373997688293457,
      "learning_rate": 2e-05,
      "loss": 1.2164,
      "step": 39
    },
    {
      "epoch": 0.013807386952019331,
      "grad_norm": 4.702381134033203,
      "learning_rate": 2e-05,
      "loss": 1.1769,
      "step": 40
    },
    {
      "epoch": 0.014152571625819814,
      "grad_norm": 5.017072677612305,
      "learning_rate": 2e-05,
      "loss": 1.1081,
      "step": 41
    },
    {
      "epoch": 0.014497756299620296,
      "grad_norm": 4.598694801330566,
      "learning_rate": 2e-05,
      "loss": 1.0872,
      "step": 42
    },
    {
      "epoch": 0.01484294097342078,
      "grad_norm": 4.88613224029541,
      "learning_rate": 2e-05,
      "loss": 1.166,
      "step": 43
    },
    {
      "epoch": 0.015188125647221263,
      "grad_norm": 4.172844886779785,
      "learning_rate": 2e-05,
      "loss": 1.1078,
      "step": 44
    },
    {
      "epoch": 0.015533310321021747,
      "grad_norm": 4.9598612785339355,
      "learning_rate": 2e-05,
      "loss": 1.1068,
      "step": 45
    },
    {
      "epoch": 0.01587849499482223,
      "grad_norm": 4.003320693969727,
      "learning_rate": 2e-05,
      "loss": 1.0951,
      "step": 46
    },
    {
      "epoch": 0.016223679668622714,
      "grad_norm": 4.30601692199707,
      "learning_rate": 2e-05,
      "loss": 1.1088,
      "step": 47
    },
    {
      "epoch": 0.016568864342423197,
      "grad_norm": 4.957517623901367,
      "learning_rate": 2e-05,
      "loss": 1.1152,
      "step": 48
    },
    {
      "epoch": 0.01691404901622368,
      "grad_norm": 5.051650047302246,
      "learning_rate": 2e-05,
      "loss": 1.0514,
      "step": 49
    },
    {
      "epoch": 0.01725923369002416,
      "grad_norm": 4.508876800537109,
      "learning_rate": 2e-05,
      "loss": 1.1081,
      "step": 50
    },
    {
      "epoch": 0.017604418363824648,
      "grad_norm": 4.666370391845703,
      "learning_rate": 2e-05,
      "loss": 1.0889,
      "step": 51
    },
    {
      "epoch": 0.01794960303762513,
      "grad_norm": 4.62983512878418,
      "learning_rate": 2e-05,
      "loss": 1.0561,
      "step": 52
    },
    {
      "epoch": 0.018294787711425613,
      "grad_norm": 3.8194386959075928,
      "learning_rate": 2e-05,
      "loss": 1.0314,
      "step": 53
    },
    {
      "epoch": 0.018639972385226095,
      "grad_norm": 4.9420695304870605,
      "learning_rate": 2e-05,
      "loss": 1.1218,
      "step": 54
    },
    {
      "epoch": 0.018985157059026578,
      "grad_norm": 4.9239068031311035,
      "learning_rate": 2e-05,
      "loss": 1.0647,
      "step": 55
    },
    {
      "epoch": 0.019330341732827064,
      "grad_norm": 4.308078289031982,
      "learning_rate": 2e-05,
      "loss": 1.0469,
      "step": 56
    },
    {
      "epoch": 0.019675526406627546,
      "grad_norm": 4.183582782745361,
      "learning_rate": 2e-05,
      "loss": 1.101,
      "step": 57
    },
    {
      "epoch": 0.02002071108042803,
      "grad_norm": 5.259477138519287,
      "learning_rate": 2e-05,
      "loss": 1.1166,
      "step": 58
    },
    {
      "epoch": 0.02036589575422851,
      "grad_norm": 4.483434677124023,
      "learning_rate": 2e-05,
      "loss": 1.0173,
      "step": 59
    },
    {
      "epoch": 0.020711080428028994,
      "grad_norm": 4.112723350524902,
      "learning_rate": 2e-05,
      "loss": 1.062,
      "step": 60
    },
    {
      "epoch": 0.02105626510182948,
      "grad_norm": 4.924528121948242,
      "learning_rate": 2e-05,
      "loss": 1.0574,
      "step": 61
    },
    {
      "epoch": 0.021401449775629963,
      "grad_norm": 3.717799663543701,
      "learning_rate": 2e-05,
      "loss": 1.0268,
      "step": 62
    },
    {
      "epoch": 0.021746634449430445,
      "grad_norm": 4.5001044273376465,
      "learning_rate": 2e-05,
      "loss": 1.057,
      "step": 63
    },
    {
      "epoch": 0.022091819123230928,
      "grad_norm": 4.214874267578125,
      "learning_rate": 2e-05,
      "loss": 1.1244,
      "step": 64
    },
    {
      "epoch": 0.02243700379703141,
      "grad_norm": 4.098433494567871,
      "learning_rate": 2e-05,
      "loss": 1.0685,
      "step": 65
    },
    {
      "epoch": 0.022782188470831896,
      "grad_norm": 3.9524285793304443,
      "learning_rate": 2e-05,
      "loss": 1.0642,
      "step": 66
    },
    {
      "epoch": 0.02312737314463238,
      "grad_norm": 4.906257152557373,
      "learning_rate": 2e-05,
      "loss": 1.0543,
      "step": 67
    },
    {
      "epoch": 0.02347255781843286,
      "grad_norm": 5.597499847412109,
      "learning_rate": 2e-05,
      "loss": 1.0525,
      "step": 68
    },
    {
      "epoch": 0.023817742492233344,
      "grad_norm": 3.9120569229125977,
      "learning_rate": 2e-05,
      "loss": 1.0316,
      "step": 69
    },
    {
      "epoch": 0.02416292716603383,
      "grad_norm": 3.9987313747406006,
      "learning_rate": 2e-05,
      "loss": 1.0415,
      "step": 70
    },
    {
      "epoch": 0.024508111839834312,
      "grad_norm": 3.854943037033081,
      "learning_rate": 2e-05,
      "loss": 1.0162,
      "step": 71
    },
    {
      "epoch": 0.024853296513634795,
      "grad_norm": 4.38804292678833,
      "learning_rate": 2e-05,
      "loss": 0.9893,
      "step": 72
    },
    {
      "epoch": 0.025198481187435277,
      "grad_norm": 3.375614881515503,
      "learning_rate": 2e-05,
      "loss": 1.0135,
      "step": 73
    },
    {
      "epoch": 0.02554366586123576,
      "grad_norm": 3.9334664344787598,
      "learning_rate": 2e-05,
      "loss": 1.0267,
      "step": 74
    },
    {
      "epoch": 0.025888850535036246,
      "grad_norm": 3.8816137313842773,
      "learning_rate": 2e-05,
      "loss": 1.0347,
      "step": 75
    },
    {
      "epoch": 0.02623403520883673,
      "grad_norm": 3.884535551071167,
      "learning_rate": 2e-05,
      "loss": 0.9914,
      "step": 76
    },
    {
      "epoch": 0.02657921988263721,
      "grad_norm": 3.833580493927002,
      "learning_rate": 2e-05,
      "loss": 1.021,
      "step": 77
    },
    {
      "epoch": 0.026924404556437694,
      "grad_norm": 3.6896729469299316,
      "learning_rate": 2e-05,
      "loss": 0.9915,
      "step": 78
    },
    {
      "epoch": 0.027269589230238176,
      "grad_norm": 3.8832285404205322,
      "learning_rate": 2e-05,
      "loss": 1.0081,
      "step": 79
    },
    {
      "epoch": 0.027614773904038662,
      "grad_norm": 4.00054931640625,
      "learning_rate": 2e-05,
      "loss": 0.9723,
      "step": 80
    },
    {
      "epoch": 0.027959958577839145,
      "grad_norm": 3.9635231494903564,
      "learning_rate": 2e-05,
      "loss": 1.0677,
      "step": 81
    },
    {
      "epoch": 0.028305143251639627,
      "grad_norm": 4.25091552734375,
      "learning_rate": 2e-05,
      "loss": 0.9683,
      "step": 82
    },
    {
      "epoch": 0.02865032792544011,
      "grad_norm": 4.387684345245361,
      "learning_rate": 2e-05,
      "loss": 1.0273,
      "step": 83
    },
    {
      "epoch": 0.028995512599240592,
      "grad_norm": 4.047482013702393,
      "learning_rate": 2e-05,
      "loss": 1.0372,
      "step": 84
    },
    {
      "epoch": 0.029340697273041078,
      "grad_norm": 4.226908206939697,
      "learning_rate": 2e-05,
      "loss": 1.0192,
      "step": 85
    },
    {
      "epoch": 0.02968588194684156,
      "grad_norm": 4.123228073120117,
      "learning_rate": 2e-05,
      "loss": 0.9915,
      "step": 86
    },
    {
      "epoch": 0.030031066620642043,
      "grad_norm": 6.669504165649414,
      "learning_rate": 2e-05,
      "loss": 0.9531,
      "step": 87
    },
    {
      "epoch": 0.030376251294442526,
      "grad_norm": 4.364908695220947,
      "learning_rate": 2e-05,
      "loss": 1.0042,
      "step": 88
    },
    {
      "epoch": 0.03072143596824301,
      "grad_norm": 3.7988955974578857,
      "learning_rate": 2e-05,
      "loss": 0.9767,
      "step": 89
    },
    {
      "epoch": 0.031066620642043494,
      "grad_norm": 3.547370433807373,
      "learning_rate": 2e-05,
      "loss": 1.0045,
      "step": 90
    },
    {
      "epoch": 0.03141180531584398,
      "grad_norm": 4.054666042327881,
      "learning_rate": 2e-05,
      "loss": 0.9679,
      "step": 91
    },
    {
      "epoch": 0.03175698998964446,
      "grad_norm": 4.089395523071289,
      "learning_rate": 2e-05,
      "loss": 1.009,
      "step": 92
    },
    {
      "epoch": 0.03210217466344494,
      "grad_norm": 3.888781785964966,
      "learning_rate": 2e-05,
      "loss": 0.9993,
      "step": 93
    },
    {
      "epoch": 0.03244735933724543,
      "grad_norm": 4.337654113769531,
      "learning_rate": 2e-05,
      "loss": 1.0637,
      "step": 94
    },
    {
      "epoch": 0.03279254401104591,
      "grad_norm": 3.9866831302642822,
      "learning_rate": 2e-05,
      "loss": 1.0415,
      "step": 95
    },
    {
      "epoch": 0.03313772868484639,
      "grad_norm": 3.694230556488037,
      "learning_rate": 2e-05,
      "loss": 1.0111,
      "step": 96
    },
    {
      "epoch": 0.03348291335864688,
      "grad_norm": 3.8903889656066895,
      "learning_rate": 2e-05,
      "loss": 1.0113,
      "step": 97
    },
    {
      "epoch": 0.03382809803244736,
      "grad_norm": 4.173677444458008,
      "learning_rate": 2e-05,
      "loss": 0.9969,
      "step": 98
    },
    {
      "epoch": 0.034173282706247844,
      "grad_norm": 3.679419755935669,
      "learning_rate": 2e-05,
      "loss": 1.0401,
      "step": 99
    },
    {
      "epoch": 0.03451846738004832,
      "grad_norm": 4.073668003082275,
      "learning_rate": 2e-05,
      "loss": 1.0062,
      "step": 100
    },
    {
      "epoch": 0.03486365205384881,
      "grad_norm": 3.659552574157715,
      "learning_rate": 2e-05,
      "loss": 0.9113,
      "step": 101
    },
    {
      "epoch": 0.035208836727649295,
      "grad_norm": 3.581220865249634,
      "learning_rate": 2e-05,
      "loss": 1.0402,
      "step": 102
    },
    {
      "epoch": 0.035554021401449774,
      "grad_norm": 3.6875903606414795,
      "learning_rate": 2e-05,
      "loss": 1.0051,
      "step": 103
    },
    {
      "epoch": 0.03589920607525026,
      "grad_norm": 3.3204426765441895,
      "learning_rate": 2e-05,
      "loss": 1.0041,
      "step": 104
    },
    {
      "epoch": 0.03624439074905074,
      "grad_norm": 3.408184766769409,
      "learning_rate": 2e-05,
      "loss": 0.9501,
      "step": 105
    },
    {
      "epoch": 0.036589575422851225,
      "grad_norm": 3.7698254585266113,
      "learning_rate": 2e-05,
      "loss": 0.9487,
      "step": 106
    },
    {
      "epoch": 0.03693476009665171,
      "grad_norm": 4.5543694496154785,
      "learning_rate": 2e-05,
      "loss": 1.0095,
      "step": 107
    },
    {
      "epoch": 0.03727994477045219,
      "grad_norm": 4.206326961517334,
      "learning_rate": 2e-05,
      "loss": 0.9307,
      "step": 108
    },
    {
      "epoch": 0.037625129444252677,
      "grad_norm": 3.7120132446289062,
      "learning_rate": 2e-05,
      "loss": 0.9017,
      "step": 109
    },
    {
      "epoch": 0.037970314118053156,
      "grad_norm": 3.6532175540924072,
      "learning_rate": 2e-05,
      "loss": 0.9544,
      "step": 110
    },
    {
      "epoch": 0.03831549879185364,
      "grad_norm": 3.4927427768707275,
      "learning_rate": 2e-05,
      "loss": 0.97,
      "step": 111
    },
    {
      "epoch": 0.03866068346565413,
      "grad_norm": 4.344557762145996,
      "learning_rate": 2e-05,
      "loss": 0.9311,
      "step": 112
    },
    {
      "epoch": 0.03900586813945461,
      "grad_norm": 3.0494396686553955,
      "learning_rate": 2e-05,
      "loss": 1.0055,
      "step": 113
    },
    {
      "epoch": 0.03935105281325509,
      "grad_norm": 3.7052459716796875,
      "learning_rate": 2e-05,
      "loss": 0.9356,
      "step": 114
    },
    {
      "epoch": 0.03969623748705557,
      "grad_norm": 4.43536376953125,
      "learning_rate": 2e-05,
      "loss": 0.9695,
      "step": 115
    },
    {
      "epoch": 0.04004142216085606,
      "grad_norm": 3.6565682888031006,
      "learning_rate": 2e-05,
      "loss": 1.0503,
      "step": 116
    },
    {
      "epoch": 0.040386606834656544,
      "grad_norm": 3.5132741928100586,
      "learning_rate": 2e-05,
      "loss": 0.959,
      "step": 117
    },
    {
      "epoch": 0.04073179150845702,
      "grad_norm": 4.00861120223999,
      "learning_rate": 2e-05,
      "loss": 0.8973,
      "step": 118
    },
    {
      "epoch": 0.04107697618225751,
      "grad_norm": 4.118383407592773,
      "learning_rate": 2e-05,
      "loss": 0.961,
      "step": 119
    },
    {
      "epoch": 0.04142216085605799,
      "grad_norm": 3.6368112564086914,
      "learning_rate": 2e-05,
      "loss": 1.0302,
      "step": 120
    },
    {
      "epoch": 0.041767345529858474,
      "grad_norm": 3.668741226196289,
      "learning_rate": 2e-05,
      "loss": 0.9267,
      "step": 121
    },
    {
      "epoch": 0.04211253020365896,
      "grad_norm": 3.392117500305176,
      "learning_rate": 2e-05,
      "loss": 1.0133,
      "step": 122
    },
    {
      "epoch": 0.04245771487745944,
      "grad_norm": 3.939965009689331,
      "learning_rate": 2e-05,
      "loss": 0.9151,
      "step": 123
    },
    {
      "epoch": 0.042802899551259925,
      "grad_norm": 3.3222975730895996,
      "learning_rate": 2e-05,
      "loss": 0.9028,
      "step": 124
    },
    {
      "epoch": 0.043148084225060404,
      "grad_norm": 3.639970541000366,
      "learning_rate": 2e-05,
      "loss": 0.9709,
      "step": 125
    },
    {
      "epoch": 0.04349326889886089,
      "grad_norm": 3.2109615802764893,
      "learning_rate": 2e-05,
      "loss": 0.9867,
      "step": 126
    },
    {
      "epoch": 0.043838453572661376,
      "grad_norm": 3.3262574672698975,
      "learning_rate": 2e-05,
      "loss": 0.964,
      "step": 127
    },
    {
      "epoch": 0.044183638246461855,
      "grad_norm": 5.754081726074219,
      "learning_rate": 2e-05,
      "loss": 0.8765,
      "step": 128
    },
    {
      "epoch": 0.04452882292026234,
      "grad_norm": 3.367676019668579,
      "learning_rate": 2e-05,
      "loss": 0.9724,
      "step": 129
    },
    {
      "epoch": 0.04487400759406282,
      "grad_norm": 3.8047783374786377,
      "learning_rate": 2e-05,
      "loss": 0.9596,
      "step": 130
    },
    {
      "epoch": 0.045219192267863306,
      "grad_norm": 3.5262019634246826,
      "learning_rate": 2e-05,
      "loss": 0.8931,
      "step": 131
    },
    {
      "epoch": 0.04556437694166379,
      "grad_norm": 3.1185085773468018,
      "learning_rate": 2e-05,
      "loss": 0.891,
      "step": 132
    },
    {
      "epoch": 0.04590956161546427,
      "grad_norm": 3.795315980911255,
      "learning_rate": 2e-05,
      "loss": 0.9536,
      "step": 133
    },
    {
      "epoch": 0.04625474628926476,
      "grad_norm": 3.698105812072754,
      "learning_rate": 2e-05,
      "loss": 0.918,
      "step": 134
    },
    {
      "epoch": 0.04659993096306524,
      "grad_norm": 4.450272560119629,
      "learning_rate": 2e-05,
      "loss": 0.9075,
      "step": 135
    },
    {
      "epoch": 0.04694511563686572,
      "grad_norm": 3.3076443672180176,
      "learning_rate": 2e-05,
      "loss": 0.9334,
      "step": 136
    },
    {
      "epoch": 0.04729030031066621,
      "grad_norm": 3.551239252090454,
      "learning_rate": 2e-05,
      "loss": 0.9221,
      "step": 137
    },
    {
      "epoch": 0.04763548498446669,
      "grad_norm": 3.3865537643432617,
      "learning_rate": 2e-05,
      "loss": 0.96,
      "step": 138
    },
    {
      "epoch": 0.047980669658267174,
      "grad_norm": 3.477189302444458,
      "learning_rate": 2e-05,
      "loss": 0.9794,
      "step": 139
    },
    {
      "epoch": 0.04832585433206766,
      "grad_norm": 3.2932441234588623,
      "learning_rate": 2e-05,
      "loss": 0.9078,
      "step": 140
    },
    {
      "epoch": 0.04867103900586814,
      "grad_norm": 3.095069646835327,
      "learning_rate": 2e-05,
      "loss": 0.9045,
      "step": 141
    },
    {
      "epoch": 0.049016223679668625,
      "grad_norm": 3.386526107788086,
      "learning_rate": 2e-05,
      "loss": 0.937,
      "step": 142
    },
    {
      "epoch": 0.049361408353469104,
      "grad_norm": 3.274214267730713,
      "learning_rate": 2e-05,
      "loss": 0.9356,
      "step": 143
    },
    {
      "epoch": 0.04970659302726959,
      "grad_norm": 3.472280263900757,
      "learning_rate": 2e-05,
      "loss": 0.8798,
      "step": 144
    },
    {
      "epoch": 0.050051777701070076,
      "grad_norm": 3.4150500297546387,
      "learning_rate": 2e-05,
      "loss": 1.0118,
      "step": 145
    },
    {
      "epoch": 0.050396962374870555,
      "grad_norm": 3.7823333740234375,
      "learning_rate": 2e-05,
      "loss": 0.9675,
      "step": 146
    },
    {
      "epoch": 0.05074214704867104,
      "grad_norm": 3.460674524307251,
      "learning_rate": 2e-05,
      "loss": 0.9366,
      "step": 147
    },
    {
      "epoch": 0.05108733172247152,
      "grad_norm": 4.081386089324951,
      "learning_rate": 2e-05,
      "loss": 0.9596,
      "step": 148
    },
    {
      "epoch": 0.051432516396272006,
      "grad_norm": 3.5548624992370605,
      "learning_rate": 2e-05,
      "loss": 0.9369,
      "step": 149
    },
    {
      "epoch": 0.05177770107007249,
      "grad_norm": 3.713184118270874,
      "learning_rate": 2e-05,
      "loss": 0.9645,
      "step": 150
    },
    {
      "epoch": 0.05212288574387297,
      "grad_norm": 9.342556953430176,
      "learning_rate": 2e-05,
      "loss": 0.953,
      "step": 151
    },
    {
      "epoch": 0.05246807041767346,
      "grad_norm": 3.330892562866211,
      "learning_rate": 2e-05,
      "loss": 0.9851,
      "step": 152
    },
    {
      "epoch": 0.052813255091473936,
      "grad_norm": 3.2820513248443604,
      "learning_rate": 2e-05,
      "loss": 0.9881,
      "step": 153
    },
    {
      "epoch": 0.05315843976527442,
      "grad_norm": 3.08601713180542,
      "learning_rate": 2e-05,
      "loss": 0.8678,
      "step": 154
    },
    {
      "epoch": 0.05350362443907491,
      "grad_norm": 3.466398239135742,
      "learning_rate": 2e-05,
      "loss": 0.9688,
      "step": 155
    },
    {
      "epoch": 0.05384880911287539,
      "grad_norm": 3.8165998458862305,
      "learning_rate": 2e-05,
      "loss": 0.9516,
      "step": 156
    },
    {
      "epoch": 0.05419399378667587,
      "grad_norm": 3.843984365463257,
      "learning_rate": 2e-05,
      "loss": 0.8846,
      "step": 157
    },
    {
      "epoch": 0.05453917846047635,
      "grad_norm": 3.6460742950439453,
      "learning_rate": 2e-05,
      "loss": 0.9738,
      "step": 158
    },
    {
      "epoch": 0.05488436313427684,
      "grad_norm": 3.6064538955688477,
      "learning_rate": 2e-05,
      "loss": 0.8974,
      "step": 159
    },
    {
      "epoch": 0.055229547808077324,
      "grad_norm": 3.8065435886383057,
      "learning_rate": 2e-05,
      "loss": 0.9804,
      "step": 160
    },
    {
      "epoch": 0.0555747324818778,
      "grad_norm": 3.020841121673584,
      "learning_rate": 2e-05,
      "loss": 0.9037,
      "step": 161
    },
    {
      "epoch": 0.05591991715567829,
      "grad_norm": 3.5063493251800537,
      "learning_rate": 2e-05,
      "loss": 0.892,
      "step": 162
    },
    {
      "epoch": 0.05626510182947877,
      "grad_norm": 3.2224860191345215,
      "learning_rate": 2e-05,
      "loss": 0.8995,
      "step": 163
    },
    {
      "epoch": 0.056610286503279254,
      "grad_norm": 3.520097494125366,
      "learning_rate": 2e-05,
      "loss": 0.9791,
      "step": 164
    },
    {
      "epoch": 0.05695547117707974,
      "grad_norm": 3.435135841369629,
      "learning_rate": 2e-05,
      "loss": 1.0013,
      "step": 165
    },
    {
      "epoch": 0.05730065585088022,
      "grad_norm": 3.173973321914673,
      "learning_rate": 2e-05,
      "loss": 0.9146,
      "step": 166
    },
    {
      "epoch": 0.057645840524680705,
      "grad_norm": 3.4863386154174805,
      "learning_rate": 2e-05,
      "loss": 0.9885,
      "step": 167
    },
    {
      "epoch": 0.057991025198481184,
      "grad_norm": 3.2673957347869873,
      "learning_rate": 2e-05,
      "loss": 0.9354,
      "step": 168
    },
    {
      "epoch": 0.05833620987228167,
      "grad_norm": 3.613051652908325,
      "learning_rate": 2e-05,
      "loss": 0.9169,
      "step": 169
    },
    {
      "epoch": 0.058681394546082156,
      "grad_norm": 3.6220316886901855,
      "learning_rate": 2e-05,
      "loss": 0.9123,
      "step": 170
    },
    {
      "epoch": 0.059026579219882636,
      "grad_norm": 2.9920058250427246,
      "learning_rate": 2e-05,
      "loss": 0.9228,
      "step": 171
    },
    {
      "epoch": 0.05937176389368312,
      "grad_norm": 3.1163201332092285,
      "learning_rate": 2e-05,
      "loss": 0.9196,
      "step": 172
    },
    {
      "epoch": 0.0597169485674836,
      "grad_norm": 3.5045080184936523,
      "learning_rate": 2e-05,
      "loss": 0.9711,
      "step": 173
    },
    {
      "epoch": 0.06006213324128409,
      "grad_norm": 3.3398544788360596,
      "learning_rate": 2e-05,
      "loss": 0.8714,
      "step": 174
    },
    {
      "epoch": 0.06040731791508457,
      "grad_norm": 2.9095466136932373,
      "learning_rate": 2e-05,
      "loss": 0.8746,
      "step": 175
    },
    {
      "epoch": 0.06075250258888505,
      "grad_norm": 3.1426031589508057,
      "learning_rate": 2e-05,
      "loss": 0.8826,
      "step": 176
    },
    {
      "epoch": 0.06109768726268554,
      "grad_norm": 4.104501724243164,
      "learning_rate": 2e-05,
      "loss": 0.9346,
      "step": 177
    },
    {
      "epoch": 0.06144287193648602,
      "grad_norm": 2.990579128265381,
      "learning_rate": 2e-05,
      "loss": 0.9675,
      "step": 178
    },
    {
      "epoch": 0.0617880566102865,
      "grad_norm": 3.756319284439087,
      "learning_rate": 2e-05,
      "loss": 0.9229,
      "step": 179
    },
    {
      "epoch": 0.06213324128408699,
      "grad_norm": 3.5764338970184326,
      "learning_rate": 2e-05,
      "loss": 0.9925,
      "step": 180
    },
    {
      "epoch": 0.06247842595788747,
      "grad_norm": 3.068021774291992,
      "learning_rate": 2e-05,
      "loss": 0.8987,
      "step": 181
    },
    {
      "epoch": 0.06282361063168795,
      "grad_norm": 3.2142879962921143,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 182
    },
    {
      "epoch": 0.06316879530548844,
      "grad_norm": 3.3960886001586914,
      "learning_rate": 2e-05,
      "loss": 0.8892,
      "step": 183
    },
    {
      "epoch": 0.06351397997928893,
      "grad_norm": 4.435737609863281,
      "learning_rate": 2e-05,
      "loss": 0.9485,
      "step": 184
    },
    {
      "epoch": 0.0638591646530894,
      "grad_norm": 11.62714958190918,
      "learning_rate": 2e-05,
      "loss": 0.8685,
      "step": 185
    },
    {
      "epoch": 0.06420434932688988,
      "grad_norm": 3.0193748474121094,
      "learning_rate": 2e-05,
      "loss": 0.9131,
      "step": 186
    },
    {
      "epoch": 0.06454953400069037,
      "grad_norm": 3.1290862560272217,
      "learning_rate": 2e-05,
      "loss": 0.9776,
      "step": 187
    },
    {
      "epoch": 0.06489471867449086,
      "grad_norm": 3.153416872024536,
      "learning_rate": 2e-05,
      "loss": 0.9031,
      "step": 188
    },
    {
      "epoch": 0.06523990334829134,
      "grad_norm": 3.450758457183838,
      "learning_rate": 2e-05,
      "loss": 0.8928,
      "step": 189
    },
    {
      "epoch": 0.06558508802209181,
      "grad_norm": 3.281147003173828,
      "learning_rate": 2e-05,
      "loss": 1.0054,
      "step": 190
    },
    {
      "epoch": 0.0659302726958923,
      "grad_norm": 3.1141176223754883,
      "learning_rate": 2e-05,
      "loss": 0.913,
      "step": 191
    },
    {
      "epoch": 0.06627545736969279,
      "grad_norm": 2.945939064025879,
      "learning_rate": 2e-05,
      "loss": 0.895,
      "step": 192
    },
    {
      "epoch": 0.06662064204349327,
      "grad_norm": 3.141927719116211,
      "learning_rate": 2e-05,
      "loss": 0.9336,
      "step": 193
    },
    {
      "epoch": 0.06696582671729376,
      "grad_norm": 3.6074554920196533,
      "learning_rate": 2e-05,
      "loss": 0.9821,
      "step": 194
    },
    {
      "epoch": 0.06731101139109423,
      "grad_norm": 2.96323823928833,
      "learning_rate": 2e-05,
      "loss": 0.9417,
      "step": 195
    },
    {
      "epoch": 0.06765619606489472,
      "grad_norm": 3.4270036220550537,
      "learning_rate": 2e-05,
      "loss": 0.9268,
      "step": 196
    },
    {
      "epoch": 0.0680013807386952,
      "grad_norm": 3.006737232208252,
      "learning_rate": 2e-05,
      "loss": 0.9125,
      "step": 197
    },
    {
      "epoch": 0.06834656541249569,
      "grad_norm": 3.3677432537078857,
      "learning_rate": 2e-05,
      "loss": 0.9403,
      "step": 198
    },
    {
      "epoch": 0.06869175008629617,
      "grad_norm": 3.6785035133361816,
      "learning_rate": 2e-05,
      "loss": 0.8477,
      "step": 199
    },
    {
      "epoch": 0.06903693476009665,
      "grad_norm": 3.1328837871551514,
      "learning_rate": 2e-05,
      "loss": 0.8866,
      "step": 200
    },
    {
      "epoch": 0.06938211943389713,
      "grad_norm": 3.178600311279297,
      "learning_rate": 2e-05,
      "loss": 0.8418,
      "step": 201
    },
    {
      "epoch": 0.06972730410769762,
      "grad_norm": 3.471315622329712,
      "learning_rate": 2e-05,
      "loss": 0.8908,
      "step": 202
    },
    {
      "epoch": 0.0700724887814981,
      "grad_norm": 3.3694980144500732,
      "learning_rate": 2e-05,
      "loss": 0.8825,
      "step": 203
    },
    {
      "epoch": 0.07041767345529859,
      "grad_norm": 3.511202812194824,
      "learning_rate": 2e-05,
      "loss": 0.89,
      "step": 204
    },
    {
      "epoch": 0.07076285812909906,
      "grad_norm": 3.5508413314819336,
      "learning_rate": 2e-05,
      "loss": 0.8933,
      "step": 205
    },
    {
      "epoch": 0.07110804280289955,
      "grad_norm": 2.9084413051605225,
      "learning_rate": 2e-05,
      "loss": 0.9258,
      "step": 206
    },
    {
      "epoch": 0.07145322747670003,
      "grad_norm": 3.2880771160125732,
      "learning_rate": 2e-05,
      "loss": 0.9357,
      "step": 207
    },
    {
      "epoch": 0.07179841215050052,
      "grad_norm": 3.110895872116089,
      "learning_rate": 2e-05,
      "loss": 0.8697,
      "step": 208
    },
    {
      "epoch": 0.072143596824301,
      "grad_norm": 3.059079170227051,
      "learning_rate": 2e-05,
      "loss": 0.8579,
      "step": 209
    },
    {
      "epoch": 0.07248878149810148,
      "grad_norm": 2.9385037422180176,
      "learning_rate": 2e-05,
      "loss": 0.8913,
      "step": 210
    },
    {
      "epoch": 0.07283396617190196,
      "grad_norm": 2.984720468521118,
      "learning_rate": 2e-05,
      "loss": 0.9311,
      "step": 211
    },
    {
      "epoch": 0.07317915084570245,
      "grad_norm": 3.1889357566833496,
      "learning_rate": 2e-05,
      "loss": 0.931,
      "step": 212
    },
    {
      "epoch": 0.07352433551950294,
      "grad_norm": 3.020983934402466,
      "learning_rate": 2e-05,
      "loss": 0.8572,
      "step": 213
    },
    {
      "epoch": 0.07386952019330342,
      "grad_norm": 3.3382914066314697,
      "learning_rate": 2e-05,
      "loss": 0.9128,
      "step": 214
    },
    {
      "epoch": 0.0742147048671039,
      "grad_norm": 3.1657910346984863,
      "learning_rate": 2e-05,
      "loss": 0.8976,
      "step": 215
    },
    {
      "epoch": 0.07455988954090438,
      "grad_norm": 3.058868885040283,
      "learning_rate": 2e-05,
      "loss": 0.8939,
      "step": 216
    },
    {
      "epoch": 0.07490507421470487,
      "grad_norm": 3.422123908996582,
      "learning_rate": 2e-05,
      "loss": 0.9378,
      "step": 217
    },
    {
      "epoch": 0.07525025888850535,
      "grad_norm": 3.1783478260040283,
      "learning_rate": 2e-05,
      "loss": 0.9485,
      "step": 218
    },
    {
      "epoch": 0.07559544356230584,
      "grad_norm": 3.0557048320770264,
      "learning_rate": 2e-05,
      "loss": 0.8256,
      "step": 219
    },
    {
      "epoch": 0.07594062823610631,
      "grad_norm": 2.9779226779937744,
      "learning_rate": 2e-05,
      "loss": 0.8713,
      "step": 220
    },
    {
      "epoch": 0.0762858129099068,
      "grad_norm": 3.3758676052093506,
      "learning_rate": 2e-05,
      "loss": 0.8843,
      "step": 221
    },
    {
      "epoch": 0.07663099758370728,
      "grad_norm": 3.1416192054748535,
      "learning_rate": 2e-05,
      "loss": 0.9064,
      "step": 222
    },
    {
      "epoch": 0.07697618225750777,
      "grad_norm": 2.9653568267822266,
      "learning_rate": 2e-05,
      "loss": 0.8296,
      "step": 223
    },
    {
      "epoch": 0.07732136693130826,
      "grad_norm": 3.2615296840667725,
      "learning_rate": 2e-05,
      "loss": 0.9057,
      "step": 224
    },
    {
      "epoch": 0.07766655160510873,
      "grad_norm": 3.3381457328796387,
      "learning_rate": 2e-05,
      "loss": 0.9088,
      "step": 225
    },
    {
      "epoch": 0.07801173627890921,
      "grad_norm": 3.4600749015808105,
      "learning_rate": 2e-05,
      "loss": 0.86,
      "step": 226
    },
    {
      "epoch": 0.0783569209527097,
      "grad_norm": 3.2292826175689697,
      "learning_rate": 2e-05,
      "loss": 0.9591,
      "step": 227
    },
    {
      "epoch": 0.07870210562651019,
      "grad_norm": 3.345545530319214,
      "learning_rate": 2e-05,
      "loss": 0.8476,
      "step": 228
    },
    {
      "epoch": 0.07904729030031067,
      "grad_norm": 3.09397292137146,
      "learning_rate": 2e-05,
      "loss": 0.8652,
      "step": 229
    },
    {
      "epoch": 0.07939247497411114,
      "grad_norm": 3.004117965698242,
      "learning_rate": 2e-05,
      "loss": 0.9689,
      "step": 230
    },
    {
      "epoch": 0.07973765964791163,
      "grad_norm": 3.200100898742676,
      "learning_rate": 2e-05,
      "loss": 0.8666,
      "step": 231
    },
    {
      "epoch": 0.08008284432171212,
      "grad_norm": 2.7272403240203857,
      "learning_rate": 2e-05,
      "loss": 0.8602,
      "step": 232
    },
    {
      "epoch": 0.0804280289955126,
      "grad_norm": 3.2486329078674316,
      "learning_rate": 2e-05,
      "loss": 0.8464,
      "step": 233
    },
    {
      "epoch": 0.08077321366931309,
      "grad_norm": 3.303467035293579,
      "learning_rate": 2e-05,
      "loss": 0.873,
      "step": 234
    },
    {
      "epoch": 0.08111839834311356,
      "grad_norm": 3.0120198726654053,
      "learning_rate": 2e-05,
      "loss": 0.8934,
      "step": 235
    },
    {
      "epoch": 0.08146358301691405,
      "grad_norm": 2.962071657180786,
      "learning_rate": 2e-05,
      "loss": 0.8904,
      "step": 236
    },
    {
      "epoch": 0.08180876769071453,
      "grad_norm": 3.7542247772216797,
      "learning_rate": 2e-05,
      "loss": 0.9119,
      "step": 237
    },
    {
      "epoch": 0.08215395236451502,
      "grad_norm": 3.281599521636963,
      "learning_rate": 2e-05,
      "loss": 0.9107,
      "step": 238
    },
    {
      "epoch": 0.0824991370383155,
      "grad_norm": 3.1624579429626465,
      "learning_rate": 2e-05,
      "loss": 0.8766,
      "step": 239
    },
    {
      "epoch": 0.08284432171211598,
      "grad_norm": 3.3022897243499756,
      "learning_rate": 2e-05,
      "loss": 0.9303,
      "step": 240
    },
    {
      "epoch": 0.08318950638591646,
      "grad_norm": 3.1247267723083496,
      "learning_rate": 2e-05,
      "loss": 0.9125,
      "step": 241
    },
    {
      "epoch": 0.08353469105971695,
      "grad_norm": 3.2210910320281982,
      "learning_rate": 2e-05,
      "loss": 0.9221,
      "step": 242
    },
    {
      "epoch": 0.08387987573351743,
      "grad_norm": 3.1737873554229736,
      "learning_rate": 2e-05,
      "loss": 0.8178,
      "step": 243
    },
    {
      "epoch": 0.08422506040731792,
      "grad_norm": 3.2427146434783936,
      "learning_rate": 2e-05,
      "loss": 0.9566,
      "step": 244
    },
    {
      "epoch": 0.08457024508111839,
      "grad_norm": 3.4193999767303467,
      "learning_rate": 2e-05,
      "loss": 0.8557,
      "step": 245
    },
    {
      "epoch": 0.08491542975491888,
      "grad_norm": 3.4254438877105713,
      "learning_rate": 2e-05,
      "loss": 0.8968,
      "step": 246
    },
    {
      "epoch": 0.08526061442871936,
      "grad_norm": 3.159757614135742,
      "learning_rate": 2e-05,
      "loss": 0.9018,
      "step": 247
    },
    {
      "epoch": 0.08560579910251985,
      "grad_norm": 3.187760353088379,
      "learning_rate": 2e-05,
      "loss": 0.9057,
      "step": 248
    },
    {
      "epoch": 0.08595098377632034,
      "grad_norm": 2.959864616394043,
      "learning_rate": 2e-05,
      "loss": 0.904,
      "step": 249
    },
    {
      "epoch": 0.08629616845012081,
      "grad_norm": 3.240973711013794,
      "learning_rate": 2e-05,
      "loss": 0.9294,
      "step": 250
    },
    {
      "epoch": 0.0866413531239213,
      "grad_norm": 2.98917555809021,
      "learning_rate": 2e-05,
      "loss": 0.8764,
      "step": 251
    },
    {
      "epoch": 0.08698653779772178,
      "grad_norm": 2.8783609867095947,
      "learning_rate": 2e-05,
      "loss": 0.8941,
      "step": 252
    },
    {
      "epoch": 0.08733172247152227,
      "grad_norm": 3.0823488235473633,
      "learning_rate": 2e-05,
      "loss": 0.9319,
      "step": 253
    },
    {
      "epoch": 0.08767690714532275,
      "grad_norm": 3.0972771644592285,
      "learning_rate": 2e-05,
      "loss": 0.8236,
      "step": 254
    },
    {
      "epoch": 0.08802209181912322,
      "grad_norm": 3.005472421646118,
      "learning_rate": 2e-05,
      "loss": 0.8301,
      "step": 255
    },
    {
      "epoch": 0.08836727649292371,
      "grad_norm": 3.145705223083496,
      "learning_rate": 2e-05,
      "loss": 0.866,
      "step": 256
    },
    {
      "epoch": 0.0887124611667242,
      "grad_norm": 2.7804439067840576,
      "learning_rate": 2e-05,
      "loss": 0.8594,
      "step": 257
    },
    {
      "epoch": 0.08905764584052468,
      "grad_norm": 3.092439889907837,
      "learning_rate": 2e-05,
      "loss": 0.8486,
      "step": 258
    },
    {
      "epoch": 0.08940283051432517,
      "grad_norm": 3.228419303894043,
      "learning_rate": 2e-05,
      "loss": 0.8338,
      "step": 259
    },
    {
      "epoch": 0.08974801518812564,
      "grad_norm": 3.093811273574829,
      "learning_rate": 2e-05,
      "loss": 0.9424,
      "step": 260
    },
    {
      "epoch": 0.09009319986192613,
      "grad_norm": 3.0747523307800293,
      "learning_rate": 2e-05,
      "loss": 0.8944,
      "step": 261
    },
    {
      "epoch": 0.09043838453572661,
      "grad_norm": 3.186995267868042,
      "learning_rate": 2e-05,
      "loss": 0.8586,
      "step": 262
    },
    {
      "epoch": 0.0907835692095271,
      "grad_norm": 3.1833300590515137,
      "learning_rate": 2e-05,
      "loss": 0.8728,
      "step": 263
    },
    {
      "epoch": 0.09112875388332758,
      "grad_norm": 3.0900795459747314,
      "learning_rate": 2e-05,
      "loss": 0.9022,
      "step": 264
    },
    {
      "epoch": 0.09147393855712806,
      "grad_norm": 3.004206895828247,
      "learning_rate": 2e-05,
      "loss": 0.9062,
      "step": 265
    },
    {
      "epoch": 0.09181912323092854,
      "grad_norm": 3.1954448223114014,
      "learning_rate": 2e-05,
      "loss": 0.8732,
      "step": 266
    },
    {
      "epoch": 0.09216430790472903,
      "grad_norm": 3.324725866317749,
      "learning_rate": 2e-05,
      "loss": 0.9214,
      "step": 267
    },
    {
      "epoch": 0.09250949257852951,
      "grad_norm": 2.8366189002990723,
      "learning_rate": 2e-05,
      "loss": 0.9153,
      "step": 268
    },
    {
      "epoch": 0.09285467725233,
      "grad_norm": 3.264113187789917,
      "learning_rate": 2e-05,
      "loss": 0.8697,
      "step": 269
    },
    {
      "epoch": 0.09319986192613049,
      "grad_norm": 3.186286211013794,
      "learning_rate": 2e-05,
      "loss": 0.9348,
      "step": 270
    },
    {
      "epoch": 0.09354504659993096,
      "grad_norm": 2.8541440963745117,
      "learning_rate": 2e-05,
      "loss": 0.9067,
      "step": 271
    },
    {
      "epoch": 0.09389023127373144,
      "grad_norm": 3.074235200881958,
      "learning_rate": 2e-05,
      "loss": 0.8935,
      "step": 272
    },
    {
      "epoch": 0.09423541594753193,
      "grad_norm": 3.0192456245422363,
      "learning_rate": 2e-05,
      "loss": 0.8231,
      "step": 273
    },
    {
      "epoch": 0.09458060062133242,
      "grad_norm": 2.740384101867676,
      "learning_rate": 2e-05,
      "loss": 0.8533,
      "step": 274
    },
    {
      "epoch": 0.0949257852951329,
      "grad_norm": 2.9101722240448,
      "learning_rate": 2e-05,
      "loss": 0.8529,
      "step": 275
    },
    {
      "epoch": 0.09527096996893337,
      "grad_norm": 3.137927770614624,
      "learning_rate": 2e-05,
      "loss": 0.9192,
      "step": 276
    },
    {
      "epoch": 0.09561615464273386,
      "grad_norm": 3.054185628890991,
      "learning_rate": 2e-05,
      "loss": 0.8945,
      "step": 277
    },
    {
      "epoch": 0.09596133931653435,
      "grad_norm": 3.1088597774505615,
      "learning_rate": 2e-05,
      "loss": 0.9008,
      "step": 278
    },
    {
      "epoch": 0.09630652399033483,
      "grad_norm": 2.7827138900756836,
      "learning_rate": 2e-05,
      "loss": 0.8461,
      "step": 279
    },
    {
      "epoch": 0.09665170866413532,
      "grad_norm": 2.864086389541626,
      "learning_rate": 2e-05,
      "loss": 0.8751,
      "step": 280
    },
    {
      "epoch": 0.09699689333793579,
      "grad_norm": 3.1949148178100586,
      "learning_rate": 2e-05,
      "loss": 0.8377,
      "step": 281
    },
    {
      "epoch": 0.09734207801173628,
      "grad_norm": 2.7971835136413574,
      "learning_rate": 2e-05,
      "loss": 0.9062,
      "step": 282
    },
    {
      "epoch": 0.09768726268553676,
      "grad_norm": 6.014020919799805,
      "learning_rate": 2e-05,
      "loss": 0.8477,
      "step": 283
    },
    {
      "epoch": 0.09803244735933725,
      "grad_norm": 3.1988205909729004,
      "learning_rate": 2e-05,
      "loss": 0.8605,
      "step": 284
    },
    {
      "epoch": 0.09837763203313774,
      "grad_norm": 3.0080959796905518,
      "learning_rate": 2e-05,
      "loss": 0.9122,
      "step": 285
    },
    {
      "epoch": 0.09872281670693821,
      "grad_norm": 2.848585844039917,
      "learning_rate": 2e-05,
      "loss": 0.861,
      "step": 286
    },
    {
      "epoch": 0.0990680013807387,
      "grad_norm": 3.069856882095337,
      "learning_rate": 2e-05,
      "loss": 0.9373,
      "step": 287
    },
    {
      "epoch": 0.09941318605453918,
      "grad_norm": 3.0742900371551514,
      "learning_rate": 2e-05,
      "loss": 0.907,
      "step": 288
    },
    {
      "epoch": 0.09975837072833967,
      "grad_norm": 2.8606960773468018,
      "learning_rate": 2e-05,
      "loss": 0.8644,
      "step": 289
    },
    {
      "epoch": 0.10010355540214015,
      "grad_norm": 2.9489126205444336,
      "learning_rate": 2e-05,
      "loss": 0.8922,
      "step": 290
    },
    {
      "epoch": 0.10044874007594062,
      "grad_norm": 3.0227949619293213,
      "learning_rate": 2e-05,
      "loss": 0.9255,
      "step": 291
    },
    {
      "epoch": 0.10079392474974111,
      "grad_norm": 2.758237361907959,
      "learning_rate": 2e-05,
      "loss": 0.8339,
      "step": 292
    },
    {
      "epoch": 0.1011391094235416,
      "grad_norm": 2.8767168521881104,
      "learning_rate": 2e-05,
      "loss": 0.8697,
      "step": 293
    },
    {
      "epoch": 0.10148429409734208,
      "grad_norm": 2.8063676357269287,
      "learning_rate": 2e-05,
      "loss": 0.8628,
      "step": 294
    },
    {
      "epoch": 0.10182947877114257,
      "grad_norm": 2.9139151573181152,
      "learning_rate": 2e-05,
      "loss": 0.9157,
      "step": 295
    },
    {
      "epoch": 0.10217466344494304,
      "grad_norm": 2.857400894165039,
      "learning_rate": 2e-05,
      "loss": 0.892,
      "step": 296
    },
    {
      "epoch": 0.10251984811874353,
      "grad_norm": 2.8675410747528076,
      "learning_rate": 2e-05,
      "loss": 0.8438,
      "step": 297
    },
    {
      "epoch": 0.10286503279254401,
      "grad_norm": 2.8956315517425537,
      "learning_rate": 2e-05,
      "loss": 0.847,
      "step": 298
    },
    {
      "epoch": 0.1032102174663445,
      "grad_norm": 2.743086099624634,
      "learning_rate": 2e-05,
      "loss": 0.9041,
      "step": 299
    },
    {
      "epoch": 0.10355540214014498,
      "grad_norm": 3.0366575717926025,
      "learning_rate": 2e-05,
      "loss": 0.8704,
      "step": 300
    },
    {
      "epoch": 0.10390058681394546,
      "grad_norm": 3.290945291519165,
      "learning_rate": 2e-05,
      "loss": 0.7993,
      "step": 301
    },
    {
      "epoch": 0.10424577148774594,
      "grad_norm": 2.562634229660034,
      "learning_rate": 2e-05,
      "loss": 0.7964,
      "step": 302
    },
    {
      "epoch": 0.10459095616154643,
      "grad_norm": 3.005824089050293,
      "learning_rate": 2e-05,
      "loss": 0.8158,
      "step": 303
    },
    {
      "epoch": 0.10493614083534691,
      "grad_norm": 2.912410259246826,
      "learning_rate": 2e-05,
      "loss": 0.8584,
      "step": 304
    },
    {
      "epoch": 0.1052813255091474,
      "grad_norm": 2.7015678882598877,
      "learning_rate": 2e-05,
      "loss": 0.8731,
      "step": 305
    },
    {
      "epoch": 0.10562651018294787,
      "grad_norm": 2.857595682144165,
      "learning_rate": 2e-05,
      "loss": 0.8809,
      "step": 306
    },
    {
      "epoch": 0.10597169485674836,
      "grad_norm": 2.7211265563964844,
      "learning_rate": 2e-05,
      "loss": 0.9234,
      "step": 307
    },
    {
      "epoch": 0.10631687953054884,
      "grad_norm": 3.018676519393921,
      "learning_rate": 2e-05,
      "loss": 0.9101,
      "step": 308
    },
    {
      "epoch": 0.10666206420434933,
      "grad_norm": 2.8703527450561523,
      "learning_rate": 2e-05,
      "loss": 0.852,
      "step": 309
    },
    {
      "epoch": 0.10700724887814982,
      "grad_norm": 2.912076473236084,
      "learning_rate": 2e-05,
      "loss": 0.8749,
      "step": 310
    },
    {
      "epoch": 0.10735243355195029,
      "grad_norm": 2.652156352996826,
      "learning_rate": 2e-05,
      "loss": 0.8838,
      "step": 311
    },
    {
      "epoch": 0.10769761822575077,
      "grad_norm": 2.8902244567871094,
      "learning_rate": 2e-05,
      "loss": 0.8898,
      "step": 312
    },
    {
      "epoch": 0.10804280289955126,
      "grad_norm": 2.7108359336853027,
      "learning_rate": 2e-05,
      "loss": 0.8312,
      "step": 313
    },
    {
      "epoch": 0.10838798757335175,
      "grad_norm": 2.6468076705932617,
      "learning_rate": 2e-05,
      "loss": 0.7757,
      "step": 314
    },
    {
      "epoch": 0.10873317224715223,
      "grad_norm": 2.969503402709961,
      "learning_rate": 2e-05,
      "loss": 0.8498,
      "step": 315
    },
    {
      "epoch": 0.1090783569209527,
      "grad_norm": 2.7394843101501465,
      "learning_rate": 2e-05,
      "loss": 0.9067,
      "step": 316
    },
    {
      "epoch": 0.10942354159475319,
      "grad_norm": 2.8321640491485596,
      "learning_rate": 2e-05,
      "loss": 0.8693,
      "step": 317
    },
    {
      "epoch": 0.10976872626855368,
      "grad_norm": 3.0017828941345215,
      "learning_rate": 2e-05,
      "loss": 0.8555,
      "step": 318
    },
    {
      "epoch": 0.11011391094235416,
      "grad_norm": 2.7267954349517822,
      "learning_rate": 2e-05,
      "loss": 0.8947,
      "step": 319
    },
    {
      "epoch": 0.11045909561615465,
      "grad_norm": 2.9304072856903076,
      "learning_rate": 2e-05,
      "loss": 0.9042,
      "step": 320
    },
    {
      "epoch": 0.11080428028995512,
      "grad_norm": 2.9202630519866943,
      "learning_rate": 2e-05,
      "loss": 0.8426,
      "step": 321
    },
    {
      "epoch": 0.1111494649637556,
      "grad_norm": 3.0602047443389893,
      "learning_rate": 2e-05,
      "loss": 0.8573,
      "step": 322
    },
    {
      "epoch": 0.11149464963755609,
      "grad_norm": 2.987820863723755,
      "learning_rate": 2e-05,
      "loss": 0.8695,
      "step": 323
    },
    {
      "epoch": 0.11183983431135658,
      "grad_norm": 3.158129930496216,
      "learning_rate": 2e-05,
      "loss": 0.9306,
      "step": 324
    },
    {
      "epoch": 0.11218501898515706,
      "grad_norm": 2.893429756164551,
      "learning_rate": 2e-05,
      "loss": 0.9157,
      "step": 325
    },
    {
      "epoch": 0.11253020365895754,
      "grad_norm": 3.009833335876465,
      "learning_rate": 2e-05,
      "loss": 0.9162,
      "step": 326
    },
    {
      "epoch": 0.11287538833275802,
      "grad_norm": 2.768258571624756,
      "learning_rate": 2e-05,
      "loss": 0.8547,
      "step": 327
    },
    {
      "epoch": 0.11322057300655851,
      "grad_norm": 3.0964066982269287,
      "learning_rate": 2e-05,
      "loss": 0.8735,
      "step": 328
    },
    {
      "epoch": 0.113565757680359,
      "grad_norm": 2.9525063037872314,
      "learning_rate": 2e-05,
      "loss": 0.8907,
      "step": 329
    },
    {
      "epoch": 0.11391094235415948,
      "grad_norm": 3.317748785018921,
      "learning_rate": 2e-05,
      "loss": 0.8673,
      "step": 330
    },
    {
      "epoch": 0.11425612702795995,
      "grad_norm": 2.934115409851074,
      "learning_rate": 2e-05,
      "loss": 0.8477,
      "step": 331
    },
    {
      "epoch": 0.11460131170176044,
      "grad_norm": 2.8080825805664062,
      "learning_rate": 2e-05,
      "loss": 0.9336,
      "step": 332
    },
    {
      "epoch": 0.11494649637556092,
      "grad_norm": 2.938957929611206,
      "learning_rate": 2e-05,
      "loss": 0.8972,
      "step": 333
    },
    {
      "epoch": 0.11529168104936141,
      "grad_norm": 2.778604745864868,
      "learning_rate": 2e-05,
      "loss": 0.8013,
      "step": 334
    },
    {
      "epoch": 0.1156368657231619,
      "grad_norm": 2.779245376586914,
      "learning_rate": 2e-05,
      "loss": 0.9065,
      "step": 335
    },
    {
      "epoch": 0.11598205039696237,
      "grad_norm": 2.834568738937378,
      "learning_rate": 2e-05,
      "loss": 0.8904,
      "step": 336
    },
    {
      "epoch": 0.11632723507076285,
      "grad_norm": 2.7382054328918457,
      "learning_rate": 2e-05,
      "loss": 0.8932,
      "step": 337
    },
    {
      "epoch": 0.11667241974456334,
      "grad_norm": 2.746325731277466,
      "learning_rate": 2e-05,
      "loss": 0.8365,
      "step": 338
    },
    {
      "epoch": 0.11701760441836383,
      "grad_norm": 2.750140905380249,
      "learning_rate": 2e-05,
      "loss": 0.8255,
      "step": 339
    },
    {
      "epoch": 0.11736278909216431,
      "grad_norm": 3.3976187705993652,
      "learning_rate": 2e-05,
      "loss": 0.859,
      "step": 340
    },
    {
      "epoch": 0.11770797376596479,
      "grad_norm": 3.004563093185425,
      "learning_rate": 2e-05,
      "loss": 0.8895,
      "step": 341
    },
    {
      "epoch": 0.11805315843976527,
      "grad_norm": 3.343090295791626,
      "learning_rate": 2e-05,
      "loss": 0.8644,
      "step": 342
    },
    {
      "epoch": 0.11839834311356576,
      "grad_norm": 2.7037289142608643,
      "learning_rate": 2e-05,
      "loss": 0.834,
      "step": 343
    },
    {
      "epoch": 0.11874352778736624,
      "grad_norm": 2.881302833557129,
      "learning_rate": 2e-05,
      "loss": 0.8343,
      "step": 344
    },
    {
      "epoch": 0.11908871246116673,
      "grad_norm": 2.9096665382385254,
      "learning_rate": 2e-05,
      "loss": 0.8559,
      "step": 345
    },
    {
      "epoch": 0.1194338971349672,
      "grad_norm": 3.109509229660034,
      "learning_rate": 2e-05,
      "loss": 0.9016,
      "step": 346
    },
    {
      "epoch": 0.11977908180876769,
      "grad_norm": 2.9444544315338135,
      "learning_rate": 2e-05,
      "loss": 0.8391,
      "step": 347
    },
    {
      "epoch": 0.12012426648256817,
      "grad_norm": 3.122678518295288,
      "learning_rate": 2e-05,
      "loss": 0.8868,
      "step": 348
    },
    {
      "epoch": 0.12046945115636866,
      "grad_norm": 2.646322250366211,
      "learning_rate": 2e-05,
      "loss": 0.8174,
      "step": 349
    },
    {
      "epoch": 0.12081463583016915,
      "grad_norm": 2.9330692291259766,
      "learning_rate": 2e-05,
      "loss": 0.8805,
      "step": 350
    },
    {
      "epoch": 0.12115982050396962,
      "grad_norm": 2.9383981227874756,
      "learning_rate": 2e-05,
      "loss": 0.8618,
      "step": 351
    },
    {
      "epoch": 0.1215050051777701,
      "grad_norm": 2.9238908290863037,
      "learning_rate": 2e-05,
      "loss": 0.9407,
      "step": 352
    },
    {
      "epoch": 0.12185018985157059,
      "grad_norm": 2.8855233192443848,
      "learning_rate": 2e-05,
      "loss": 0.8713,
      "step": 353
    },
    {
      "epoch": 0.12219537452537108,
      "grad_norm": 2.822115182876587,
      "learning_rate": 2e-05,
      "loss": 0.8916,
      "step": 354
    },
    {
      "epoch": 0.12254055919917156,
      "grad_norm": 2.8500313758850098,
      "learning_rate": 2e-05,
      "loss": 0.8349,
      "step": 355
    },
    {
      "epoch": 0.12288574387297203,
      "grad_norm": 3.022473096847534,
      "learning_rate": 2e-05,
      "loss": 0.8479,
      "step": 356
    },
    {
      "epoch": 0.12323092854677252,
      "grad_norm": 2.7787365913391113,
      "learning_rate": 2e-05,
      "loss": 0.8833,
      "step": 357
    },
    {
      "epoch": 0.123576113220573,
      "grad_norm": 2.9101765155792236,
      "learning_rate": 2e-05,
      "loss": 0.888,
      "step": 358
    },
    {
      "epoch": 0.12392129789437349,
      "grad_norm": 2.7252466678619385,
      "learning_rate": 2e-05,
      "loss": 0.8657,
      "step": 359
    },
    {
      "epoch": 0.12426648256817398,
      "grad_norm": 2.8830056190490723,
      "learning_rate": 2e-05,
      "loss": 0.8259,
      "step": 360
    },
    {
      "epoch": 0.12461166724197445,
      "grad_norm": 2.671375274658203,
      "learning_rate": 2e-05,
      "loss": 0.8253,
      "step": 361
    },
    {
      "epoch": 0.12495685191577494,
      "grad_norm": 2.706015110015869,
      "learning_rate": 2e-05,
      "loss": 0.838,
      "step": 362
    },
    {
      "epoch": 0.12530203658957542,
      "grad_norm": 2.616062641143799,
      "learning_rate": 2e-05,
      "loss": 0.8607,
      "step": 363
    },
    {
      "epoch": 0.1256472212633759,
      "grad_norm": 3.385586738586426,
      "learning_rate": 2e-05,
      "loss": 0.8603,
      "step": 364
    },
    {
      "epoch": 0.1259924059371764,
      "grad_norm": 2.9748425483703613,
      "learning_rate": 2e-05,
      "loss": 0.8802,
      "step": 365
    },
    {
      "epoch": 0.12633759061097688,
      "grad_norm": 3.009232759475708,
      "learning_rate": 2e-05,
      "loss": 0.8572,
      "step": 366
    },
    {
      "epoch": 0.12668277528477737,
      "grad_norm": 2.995032548904419,
      "learning_rate": 2e-05,
      "loss": 0.8542,
      "step": 367
    },
    {
      "epoch": 0.12702795995857785,
      "grad_norm": 3.1191444396972656,
      "learning_rate": 2e-05,
      "loss": 0.9096,
      "step": 368
    },
    {
      "epoch": 0.1273731446323783,
      "grad_norm": 3.3370883464813232,
      "learning_rate": 2e-05,
      "loss": 0.8456,
      "step": 369
    },
    {
      "epoch": 0.1277183293061788,
      "grad_norm": 2.910351276397705,
      "learning_rate": 2e-05,
      "loss": 0.8415,
      "step": 370
    },
    {
      "epoch": 0.12806351397997928,
      "grad_norm": 2.381078004837036,
      "learning_rate": 2e-05,
      "loss": 0.7864,
      "step": 371
    },
    {
      "epoch": 0.12840869865377977,
      "grad_norm": 2.8764638900756836,
      "learning_rate": 2e-05,
      "loss": 0.8731,
      "step": 372
    },
    {
      "epoch": 0.12875388332758025,
      "grad_norm": 2.9746713638305664,
      "learning_rate": 2e-05,
      "loss": 0.8447,
      "step": 373
    },
    {
      "epoch": 0.12909906800138074,
      "grad_norm": 2.7619199752807617,
      "learning_rate": 2e-05,
      "loss": 0.8315,
      "step": 374
    },
    {
      "epoch": 0.12944425267518123,
      "grad_norm": 2.5940611362457275,
      "learning_rate": 2e-05,
      "loss": 0.8749,
      "step": 375
    },
    {
      "epoch": 0.1297894373489817,
      "grad_norm": 2.9887807369232178,
      "learning_rate": 2e-05,
      "loss": 0.9069,
      "step": 376
    },
    {
      "epoch": 0.1301346220227822,
      "grad_norm": 3.1408069133758545,
      "learning_rate": 2e-05,
      "loss": 0.9029,
      "step": 377
    },
    {
      "epoch": 0.13047980669658268,
      "grad_norm": 2.876115083694458,
      "learning_rate": 2e-05,
      "loss": 0.9135,
      "step": 378
    },
    {
      "epoch": 0.13082499137038314,
      "grad_norm": 2.7395379543304443,
      "learning_rate": 2e-05,
      "loss": 0.8597,
      "step": 379
    },
    {
      "epoch": 0.13117017604418363,
      "grad_norm": 3.036904811859131,
      "learning_rate": 2e-05,
      "loss": 0.8886,
      "step": 380
    },
    {
      "epoch": 0.13151536071798411,
      "grad_norm": 3.047651767730713,
      "learning_rate": 2e-05,
      "loss": 0.8923,
      "step": 381
    },
    {
      "epoch": 0.1318605453917846,
      "grad_norm": 2.8202462196350098,
      "learning_rate": 2e-05,
      "loss": 0.8434,
      "step": 382
    },
    {
      "epoch": 0.1322057300655851,
      "grad_norm": 2.605100393295288,
      "learning_rate": 2e-05,
      "loss": 0.8975,
      "step": 383
    },
    {
      "epoch": 0.13255091473938557,
      "grad_norm": 2.781841516494751,
      "learning_rate": 2e-05,
      "loss": 0.809,
      "step": 384
    },
    {
      "epoch": 0.13289609941318606,
      "grad_norm": 2.6456520557403564,
      "learning_rate": 2e-05,
      "loss": 0.8827,
      "step": 385
    },
    {
      "epoch": 0.13324128408698654,
      "grad_norm": 10.660346984863281,
      "learning_rate": 2e-05,
      "loss": 0.8615,
      "step": 386
    },
    {
      "epoch": 0.13358646876078703,
      "grad_norm": 3.2193210124969482,
      "learning_rate": 2e-05,
      "loss": 0.8553,
      "step": 387
    },
    {
      "epoch": 0.13393165343458752,
      "grad_norm": 2.9482877254486084,
      "learning_rate": 2e-05,
      "loss": 0.7931,
      "step": 388
    },
    {
      "epoch": 0.13427683810838797,
      "grad_norm": 2.851332664489746,
      "learning_rate": 2e-05,
      "loss": 0.8291,
      "step": 389
    },
    {
      "epoch": 0.13462202278218846,
      "grad_norm": 3.519622802734375,
      "learning_rate": 2e-05,
      "loss": 0.8803,
      "step": 390
    },
    {
      "epoch": 0.13496720745598895,
      "grad_norm": 2.979022741317749,
      "learning_rate": 2e-05,
      "loss": 0.9023,
      "step": 391
    },
    {
      "epoch": 0.13531239212978943,
      "grad_norm": 2.8534867763519287,
      "learning_rate": 2e-05,
      "loss": 0.8652,
      "step": 392
    },
    {
      "epoch": 0.13565757680358992,
      "grad_norm": 2.7661948204040527,
      "learning_rate": 2e-05,
      "loss": 0.8136,
      "step": 393
    },
    {
      "epoch": 0.1360027614773904,
      "grad_norm": 2.6558003425598145,
      "learning_rate": 2e-05,
      "loss": 0.8805,
      "step": 394
    },
    {
      "epoch": 0.1363479461511909,
      "grad_norm": 2.9477477073669434,
      "learning_rate": 2e-05,
      "loss": 0.8341,
      "step": 395
    },
    {
      "epoch": 0.13669313082499138,
      "grad_norm": 2.777376174926758,
      "learning_rate": 2e-05,
      "loss": 0.8435,
      "step": 396
    },
    {
      "epoch": 0.13703831549879186,
      "grad_norm": 2.947483777999878,
      "learning_rate": 2e-05,
      "loss": 0.8495,
      "step": 397
    },
    {
      "epoch": 0.13738350017259235,
      "grad_norm": 2.923473834991455,
      "learning_rate": 2e-05,
      "loss": 0.8357,
      "step": 398
    },
    {
      "epoch": 0.1377286848463928,
      "grad_norm": 2.5483436584472656,
      "learning_rate": 2e-05,
      "loss": 0.7862,
      "step": 399
    },
    {
      "epoch": 0.1380738695201933,
      "grad_norm": 2.5327706336975098,
      "learning_rate": 2e-05,
      "loss": 0.8527,
      "step": 400
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 14485,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 251255586816000.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}