{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06903693476009665,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00034518467380048324,
      "grad_norm": 25.833335876464844,
      "learning_rate": 0.0,
      "loss": 2.2926,
      "step": 1
    },
    {
      "epoch": 0.0006903693476009665,
      "grad_norm": 23.58083724975586,
      "learning_rate": 2e-05,
      "loss": 2.1943,
      "step": 2
    },
    {
      "epoch": 0.0010355540214014498,
      "grad_norm": 24.2187442779541,
      "learning_rate": 2e-05,
      "loss": 2.3772,
      "step": 3
    },
    {
      "epoch": 0.001380738695201933,
      "grad_norm": 14.579557418823242,
      "learning_rate": 2e-05,
      "loss": 2.0945,
      "step": 4
    },
    {
      "epoch": 0.0017259233690024164,
      "grad_norm": 15.069305419921875,
      "learning_rate": 2e-05,
      "loss": 2.1537,
      "step": 5
    },
    {
      "epoch": 0.0020711080428028996,
      "grad_norm": 14.385339736938477,
      "learning_rate": 2e-05,
      "loss": 2.1585,
      "step": 6
    },
    {
      "epoch": 0.002416292716603383,
      "grad_norm": 9.95476245880127,
      "learning_rate": 2e-05,
      "loss": 1.8333,
      "step": 7
    },
    {
      "epoch": 0.002761477390403866,
      "grad_norm": 9.15005111694336,
      "learning_rate": 2e-05,
      "loss": 1.937,
      "step": 8
    },
    {
      "epoch": 0.0031066620642043494,
      "grad_norm": 7.361661911010742,
      "learning_rate": 2e-05,
      "loss": 1.9484,
      "step": 9
    },
    {
      "epoch": 0.0034518467380048328,
      "grad_norm": 5.931179046630859,
      "learning_rate": 2e-05,
      "loss": 1.7668,
      "step": 10
    },
    {
      "epoch": 0.0037970314118053157,
      "grad_norm": 8.192151069641113,
      "learning_rate": 2e-05,
      "loss": 1.8234,
      "step": 11
    },
    {
      "epoch": 0.004142216085605799,
      "grad_norm": 6.827078342437744,
      "learning_rate": 2e-05,
      "loss": 1.9133,
      "step": 12
    },
    {
      "epoch": 0.0044874007594062825,
      "grad_norm": 7.808759689331055,
      "learning_rate": 2e-05,
      "loss": 1.8314,
      "step": 13
    },
    {
      "epoch": 0.004832585433206766,
      "grad_norm": 7.531504154205322,
      "learning_rate": 2e-05,
      "loss": 1.7961,
      "step": 14
    },
    {
      "epoch": 0.0051777701070072485,
      "grad_norm": 6.617609977722168,
      "learning_rate": 2e-05,
      "loss": 1.7624,
      "step": 15
    },
    {
      "epoch": 0.005522954780807732,
      "grad_norm": 4.966954708099365,
      "learning_rate": 2e-05,
      "loss": 1.7034,
      "step": 16
    },
    {
      "epoch": 0.005868139454608215,
      "grad_norm": 5.566157817840576,
      "learning_rate": 2e-05,
      "loss": 1.7722,
      "step": 17
    },
    {
      "epoch": 0.006213324128408699,
      "grad_norm": 4.915079593658447,
      "learning_rate": 2e-05,
      "loss": 1.6602,
      "step": 18
    },
    {
      "epoch": 0.006558508802209182,
      "grad_norm": 4.77263069152832,
      "learning_rate": 2e-05,
      "loss": 1.6854,
      "step": 19
    },
    {
      "epoch": 0.0069036934760096655,
      "grad_norm": 4.299682140350342,
      "learning_rate": 2e-05,
      "loss": 1.6217,
      "step": 20
    },
    {
      "epoch": 0.007248878149810148,
      "grad_norm": 4.1203694343566895,
      "learning_rate": 2e-05,
      "loss": 1.6546,
      "step": 21
    },
    {
      "epoch": 0.0075940628236106315,
      "grad_norm": 4.058311939239502,
      "learning_rate": 2e-05,
      "loss": 1.6795,
      "step": 22
    },
    {
      "epoch": 0.007939247497411116,
      "grad_norm": 3.668001651763916,
      "learning_rate": 2e-05,
      "loss": 1.7228,
      "step": 23
    },
    {
      "epoch": 0.008284432171211598,
      "grad_norm": 3.397109270095825,
      "learning_rate": 2e-05,
      "loss": 1.555,
      "step": 24
    },
    {
      "epoch": 0.00862961684501208,
      "grad_norm": 4.351656436920166,
      "learning_rate": 2e-05,
      "loss": 1.6977,
      "step": 25
    },
    {
      "epoch": 0.008974801518812565,
      "grad_norm": 3.7789554595947266,
      "learning_rate": 2e-05,
      "loss": 1.6534,
      "step": 26
    },
    {
      "epoch": 0.009319986192613048,
      "grad_norm": 3.4693193435668945,
      "learning_rate": 2e-05,
      "loss": 1.6248,
      "step": 27
    },
    {
      "epoch": 0.009665170866413532,
      "grad_norm": 2.6027116775512695,
      "learning_rate": 2e-05,
      "loss": 1.4901,
      "step": 28
    },
    {
      "epoch": 0.010010355540214014,
      "grad_norm": 2.6816513538360596,
      "learning_rate": 2e-05,
      "loss": 1.4964,
      "step": 29
    },
    {
      "epoch": 0.010355540214014497,
      "grad_norm": 5.244405746459961,
      "learning_rate": 2e-05,
      "loss": 1.5238,
      "step": 30
    },
    {
      "epoch": 0.010700724887814981,
      "grad_norm": 4.071628570556641,
      "learning_rate": 2e-05,
      "loss": 1.5401,
      "step": 31
    },
    {
      "epoch": 0.011045909561615464,
      "grad_norm": 3.897395372390747,
      "learning_rate": 2e-05,
      "loss": 1.4759,
      "step": 32
    },
    {
      "epoch": 0.011391094235415948,
      "grad_norm": 2.9609882831573486,
      "learning_rate": 2e-05,
      "loss": 1.4919,
      "step": 33
    },
    {
      "epoch": 0.01173627890921643,
      "grad_norm": 3.1106183528900146,
      "learning_rate": 2e-05,
      "loss": 1.5436,
      "step": 34
    },
    {
      "epoch": 0.012081463583016915,
      "grad_norm": 3.7441351413726807,
      "learning_rate": 2e-05,
      "loss": 1.5496,
      "step": 35
    },
    {
      "epoch": 0.012426648256817397,
      "grad_norm": 3.6406350135803223,
      "learning_rate": 2e-05,
      "loss": 1.4531,
      "step": 36
    },
    {
      "epoch": 0.01277183293061788,
      "grad_norm": 2.915447950363159,
      "learning_rate": 2e-05,
      "loss": 1.48,
      "step": 37
    },
    {
      "epoch": 0.013117017604418364,
      "grad_norm": 2.8513331413269043,
      "learning_rate": 2e-05,
      "loss": 1.5192,
      "step": 38
    },
    {
      "epoch": 0.013462202278218847,
      "grad_norm": 3.2347466945648193,
      "learning_rate": 2e-05,
      "loss": 1.5727,
      "step": 39
    },
    {
      "epoch": 0.013807386952019331,
      "grad_norm": 2.82135272026062,
      "learning_rate": 2e-05,
      "loss": 1.5098,
      "step": 40
    },
    {
      "epoch": 0.014152571625819814,
      "grad_norm": 2.694873809814453,
      "learning_rate": 2e-05,
      "loss": 1.4223,
      "step": 41
    },
    {
      "epoch": 0.014497756299620296,
      "grad_norm": 2.7129478454589844,
      "learning_rate": 2e-05,
      "loss": 1.4062,
      "step": 42
    },
    {
      "epoch": 0.01484294097342078,
      "grad_norm": 2.6555328369140625,
      "learning_rate": 2e-05,
      "loss": 1.4993,
      "step": 43
    },
    {
      "epoch": 0.015188125647221263,
      "grad_norm": 2.3439159393310547,
      "learning_rate": 2e-05,
      "loss": 1.4281,
      "step": 44
    },
    {
      "epoch": 0.015533310321021747,
      "grad_norm": 2.40368914604187,
      "learning_rate": 2e-05,
      "loss": 1.4261,
      "step": 45
    },
    {
      "epoch": 0.01587849499482223,
      "grad_norm": 2.3288614749908447,
      "learning_rate": 2e-05,
      "loss": 1.3958,
      "step": 46
    },
    {
      "epoch": 0.016223679668622714,
      "grad_norm": 2.474519968032837,
      "learning_rate": 2e-05,
      "loss": 1.4246,
      "step": 47
    },
    {
      "epoch": 0.016568864342423197,
      "grad_norm": 2.680997371673584,
      "learning_rate": 2e-05,
      "loss": 1.4318,
      "step": 48
    },
    {
      "epoch": 0.01691404901622368,
      "grad_norm": 2.6899235248565674,
      "learning_rate": 2e-05,
      "loss": 1.3581,
      "step": 49
    },
    {
      "epoch": 0.01725923369002416,
      "grad_norm": 2.5045225620269775,
      "learning_rate": 2e-05,
      "loss": 1.3983,
      "step": 50
    },
    {
      "epoch": 0.017604418363824648,
      "grad_norm": 2.650184154510498,
      "learning_rate": 2e-05,
      "loss": 1.4005,
      "step": 51
    },
    {
      "epoch": 0.01794960303762513,
      "grad_norm": 2.560302495956421,
      "learning_rate": 2e-05,
      "loss": 1.3706,
      "step": 52
    },
    {
      "epoch": 0.018294787711425613,
      "grad_norm": 2.116626739501953,
      "learning_rate": 2e-05,
      "loss": 1.2987,
      "step": 53
    },
    {
      "epoch": 0.018639972385226095,
      "grad_norm": 3.0732431411743164,
      "learning_rate": 2e-05,
      "loss": 1.4394,
      "step": 54
    },
    {
      "epoch": 0.018985157059026578,
      "grad_norm": 2.880014657974243,
      "learning_rate": 2e-05,
      "loss": 1.3772,
      "step": 55
    },
    {
      "epoch": 0.019330341732827064,
      "grad_norm": 2.65002179145813,
      "learning_rate": 2e-05,
      "loss": 1.344,
      "step": 56
    },
    {
      "epoch": 0.019675526406627546,
      "grad_norm": 2.4109294414520264,
      "learning_rate": 2e-05,
      "loss": 1.3818,
      "step": 57
    },
    {
      "epoch": 0.02002071108042803,
      "grad_norm": 3.318305730819702,
      "learning_rate": 2e-05,
      "loss": 1.4488,
      "step": 58
    },
    {
      "epoch": 0.02036589575422851,
      "grad_norm": 2.9551541805267334,
      "learning_rate": 2e-05,
      "loss": 1.3245,
      "step": 59
    },
    {
      "epoch": 0.020711080428028994,
      "grad_norm": 2.512965679168701,
      "learning_rate": 2e-05,
      "loss": 1.3476,
      "step": 60
    },
    {
      "epoch": 0.02105626510182948,
      "grad_norm": 2.608680248260498,
      "learning_rate": 2e-05,
      "loss": 1.335,
      "step": 61
    },
    {
      "epoch": 0.021401449775629963,
      "grad_norm": 2.2880616188049316,
      "learning_rate": 2e-05,
      "loss": 1.2781,
      "step": 62
    },
    {
      "epoch": 0.021746634449430445,
      "grad_norm": 2.7310123443603516,
      "learning_rate": 2e-05,
      "loss": 1.3449,
      "step": 63
    },
    {
      "epoch": 0.022091819123230928,
      "grad_norm": 2.5008130073547363,
      "learning_rate": 2e-05,
      "loss": 1.4042,
      "step": 64
    },
    {
      "epoch": 0.02243700379703141,
      "grad_norm": 3.5907320976257324,
      "learning_rate": 2e-05,
      "loss": 1.344,
      "step": 65
    },
    {
      "epoch": 0.022782188470831896,
      "grad_norm": 2.4797489643096924,
      "learning_rate": 2e-05,
      "loss": 1.3342,
      "step": 66
    },
    {
      "epoch": 0.02312737314463238,
      "grad_norm": 2.556204319000244,
      "learning_rate": 2e-05,
      "loss": 1.3244,
      "step": 67
    },
    {
      "epoch": 0.02347255781843286,
      "grad_norm": 5.068964004516602,
      "learning_rate": 2e-05,
      "loss": 1.3041,
      "step": 68
    },
    {
      "epoch": 0.023817742492233344,
      "grad_norm": 2.165076494216919,
      "learning_rate": 2e-05,
      "loss": 1.2727,
      "step": 69
    },
    {
      "epoch": 0.02416292716603383,
      "grad_norm": 2.202164649963379,
      "learning_rate": 2e-05,
      "loss": 1.2887,
      "step": 70
    },
    {
      "epoch": 0.024508111839834312,
      "grad_norm": 2.3834869861602783,
      "learning_rate": 2e-05,
      "loss": 1.2694,
      "step": 71
    },
    {
      "epoch": 0.024853296513634795,
      "grad_norm": 2.5316550731658936,
      "learning_rate": 2e-05,
      "loss": 1.2514,
      "step": 72
    },
    {
      "epoch": 0.025198481187435277,
      "grad_norm": 1.9449459314346313,
      "learning_rate": 2e-05,
      "loss": 1.26,
      "step": 73
    },
    {
      "epoch": 0.02554366586123576,
      "grad_norm": 2.2826900482177734,
      "learning_rate": 2e-05,
      "loss": 1.2931,
      "step": 74
    },
    {
      "epoch": 0.025888850535036246,
      "grad_norm": 2.260650396347046,
      "learning_rate": 2e-05,
      "loss": 1.2732,
      "step": 75
    },
    {
      "epoch": 0.02623403520883673,
      "grad_norm": 2.356182336807251,
      "learning_rate": 2e-05,
      "loss": 1.2449,
      "step": 76
    },
    {
      "epoch": 0.02657921988263721,
      "grad_norm": 2.199906826019287,
      "learning_rate": 2e-05,
      "loss": 1.2733,
      "step": 77
    },
    {
      "epoch": 0.026924404556437694,
      "grad_norm": 2.3083510398864746,
      "learning_rate": 2e-05,
      "loss": 1.2257,
      "step": 78
    },
    {
      "epoch": 0.027269589230238176,
      "grad_norm": 2.2658169269561768,
      "learning_rate": 2e-05,
      "loss": 1.2525,
      "step": 79
    },
    {
      "epoch": 0.027614773904038662,
      "grad_norm": 2.352308988571167,
      "learning_rate": 2e-05,
      "loss": 1.2202,
      "step": 80
    },
    {
      "epoch": 0.027959958577839145,
      "grad_norm": 2.523381471633911,
      "learning_rate": 2e-05,
      "loss": 1.2996,
      "step": 81
    },
    {
      "epoch": 0.028305143251639627,
      "grad_norm": 2.4327428340911865,
      "learning_rate": 2e-05,
      "loss": 1.2135,
      "step": 82
    },
    {
      "epoch": 0.02865032792544011,
      "grad_norm": 2.4549570083618164,
      "learning_rate": 2e-05,
      "loss": 1.2813,
      "step": 83
    },
    {
      "epoch": 0.028995512599240592,
      "grad_norm": 2.4394640922546387,
      "learning_rate": 2e-05,
      "loss": 1.2828,
      "step": 84
    },
    {
      "epoch": 0.029340697273041078,
      "grad_norm": 2.4780633449554443,
      "learning_rate": 2e-05,
      "loss": 1.2517,
      "step": 85
    },
    {
      "epoch": 0.02968588194684156,
      "grad_norm": 2.326880931854248,
      "learning_rate": 2e-05,
      "loss": 1.2288,
      "step": 86
    },
    {
      "epoch": 0.030031066620642043,
      "grad_norm": 3.1833627223968506,
      "learning_rate": 2e-05,
      "loss": 1.1978,
      "step": 87
    },
    {
      "epoch": 0.030376251294442526,
      "grad_norm": 2.624091625213623,
      "learning_rate": 2e-05,
      "loss": 1.2534,
      "step": 88
    },
    {
      "epoch": 0.03072143596824301,
      "grad_norm": 2.531895160675049,
      "learning_rate": 2e-05,
      "loss": 1.2263,
      "step": 89
    },
    {
      "epoch": 0.031066620642043494,
      "grad_norm": 2.2346715927124023,
      "learning_rate": 2e-05,
      "loss": 1.2301,
      "step": 90
    },
    {
      "epoch": 0.03141180531584398,
      "grad_norm": 2.237839698791504,
      "learning_rate": 2e-05,
      "loss": 1.1897,
      "step": 91
    },
    {
      "epoch": 0.03175698998964446,
      "grad_norm": 2.4267807006835938,
      "learning_rate": 2e-05,
      "loss": 1.2508,
      "step": 92
    },
    {
      "epoch": 0.03210217466344494,
      "grad_norm": 2.2506682872772217,
      "learning_rate": 2e-05,
      "loss": 1.2262,
      "step": 93
    },
    {
      "epoch": 0.03244735933724543,
      "grad_norm": 2.5266077518463135,
      "learning_rate": 2e-05,
      "loss": 1.3139,
      "step": 94
    },
    {
      "epoch": 0.03279254401104591,
      "grad_norm": 2.2002406120300293,
      "learning_rate": 2e-05,
      "loss": 1.2755,
      "step": 95
    },
    {
      "epoch": 0.03313772868484639,
      "grad_norm": 2.20263409614563,
      "learning_rate": 2e-05,
      "loss": 1.2388,
      "step": 96
    },
    {
      "epoch": 0.03348291335864688,
      "grad_norm": 2.297576665878296,
      "learning_rate": 2e-05,
      "loss": 1.2406,
      "step": 97
    },
    {
      "epoch": 0.03382809803244736,
      "grad_norm": 2.3951361179351807,
      "learning_rate": 2e-05,
      "loss": 1.2244,
      "step": 98
    },
    {
      "epoch": 0.034173282706247844,
      "grad_norm": 2.2707271575927734,
      "learning_rate": 2e-05,
      "loss": 1.2719,
      "step": 99
    },
    {
      "epoch": 0.03451846738004832,
      "grad_norm": 2.2766411304473877,
      "learning_rate": 2e-05,
      "loss": 1.23,
      "step": 100
    },
    {
      "epoch": 0.03486365205384881,
      "grad_norm": 2.253887414932251,
      "learning_rate": 2e-05,
      "loss": 1.1369,
      "step": 101
    },
    {
      "epoch": 0.035208836727649295,
      "grad_norm": 2.0003821849823,
      "learning_rate": 2e-05,
      "loss": 1.2547,
      "step": 102
    },
    {
      "epoch": 0.035554021401449774,
      "grad_norm": 2.277153253555298,
      "learning_rate": 2e-05,
      "loss": 1.2244,
      "step": 103
    },
    {
      "epoch": 0.03589920607525026,
      "grad_norm": 2.1561081409454346,
      "learning_rate": 2e-05,
      "loss": 1.2222,
      "step": 104
    },
    {
      "epoch": 0.03624439074905074,
      "grad_norm": 2.0002012252807617,
      "learning_rate": 2e-05,
      "loss": 1.1599,
      "step": 105
    },
    {
      "epoch": 0.036589575422851225,
      "grad_norm": 2.3313021659851074,
      "learning_rate": 2e-05,
      "loss": 1.1658,
      "step": 106
    },
    {
      "epoch": 0.03693476009665171,
      "grad_norm": 2.58686900138855,
      "learning_rate": 2e-05,
      "loss": 1.2282,
      "step": 107
    },
    {
      "epoch": 0.03727994477045219,
      "grad_norm": 2.485671043395996,
      "learning_rate": 2e-05,
      "loss": 1.1537,
      "step": 108
    },
    {
      "epoch": 0.037625129444252677,
      "grad_norm": 2.3962278366088867,
      "learning_rate": 2e-05,
      "loss": 1.133,
      "step": 109
    },
    {
      "epoch": 0.037970314118053156,
      "grad_norm": 2.118319034576416,
      "learning_rate": 2e-05,
      "loss": 1.1769,
      "step": 110
    },
    {
      "epoch": 0.03831549879185364,
      "grad_norm": 2.095940113067627,
      "learning_rate": 2e-05,
      "loss": 1.1763,
      "step": 111
    },
    {
      "epoch": 0.03866068346565413,
      "grad_norm": 2.0862512588500977,
      "learning_rate": 2e-05,
      "loss": 1.1356,
      "step": 112
    },
    {
      "epoch": 0.03900586813945461,
      "grad_norm": 1.9276546239852905,
      "learning_rate": 2e-05,
      "loss": 1.2068,
      "step": 113
    },
    {
      "epoch": 0.03935105281325509,
      "grad_norm": 2.5604825019836426,
      "learning_rate": 2e-05,
      "loss": 1.16,
      "step": 114
    },
    {
      "epoch": 0.03969623748705557,
      "grad_norm": 2.200289726257324,
      "learning_rate": 2e-05,
      "loss": 1.1811,
      "step": 115
    },
    {
      "epoch": 0.04004142216085606,
      "grad_norm": 2.2654318809509277,
      "learning_rate": 2e-05,
      "loss": 1.2745,
      "step": 116
    },
    {
      "epoch": 0.040386606834656544,
      "grad_norm": 2.194129228591919,
      "learning_rate": 2e-05,
      "loss": 1.1633,
      "step": 117
    },
    {
      "epoch": 0.04073179150845702,
      "grad_norm": 2.267609119415283,
      "learning_rate": 2e-05,
      "loss": 1.1025,
      "step": 118
    },
    {
      "epoch": 0.04107697618225751,
      "grad_norm": 2.3966379165649414,
      "learning_rate": 2e-05,
      "loss": 1.1624,
      "step": 119
    },
    {
      "epoch": 0.04142216085605799,
      "grad_norm": 2.3428127765655518,
      "learning_rate": 2e-05,
      "loss": 1.2521,
      "step": 120
    },
    {
      "epoch": 0.041767345529858474,
      "grad_norm": 2.257154941558838,
      "learning_rate": 2e-05,
      "loss": 1.1427,
      "step": 121
    },
    {
      "epoch": 0.04211253020365896,
      "grad_norm": 2.4615261554718018,
      "learning_rate": 2e-05,
      "loss": 1.209,
      "step": 122
    },
    {
      "epoch": 0.04245771487745944,
      "grad_norm": 2.215366840362549,
      "learning_rate": 2e-05,
      "loss": 1.1213,
      "step": 123
    },
    {
      "epoch": 0.042802899551259925,
      "grad_norm": 2.293936014175415,
      "learning_rate": 2e-05,
      "loss": 1.1118,
      "step": 124
    },
    {
      "epoch": 0.043148084225060404,
      "grad_norm": 2.351991653442383,
      "learning_rate": 2e-05,
      "loss": 1.1849,
      "step": 125
    },
    {
      "epoch": 0.04349326889886089,
      "grad_norm": 2.118906259536743,
      "learning_rate": 2e-05,
      "loss": 1.1905,
      "step": 126
    },
    {
      "epoch": 0.043838453572661376,
      "grad_norm": 2.1108460426330566,
      "learning_rate": 2e-05,
      "loss": 1.1787,
      "step": 127
    },
    {
      "epoch": 0.044183638246461855,
      "grad_norm": 2.560715436935425,
      "learning_rate": 2e-05,
      "loss": 1.0727,
      "step": 128
    },
    {
      "epoch": 0.04452882292026234,
      "grad_norm": 1.9983900785446167,
      "learning_rate": 2e-05,
      "loss": 1.1665,
      "step": 129
    },
    {
      "epoch": 0.04487400759406282,
      "grad_norm": 2.3714847564697266,
      "learning_rate": 2e-05,
      "loss": 1.1488,
      "step": 130
    },
    {
      "epoch": 0.045219192267863306,
      "grad_norm": 2.243546724319458,
      "learning_rate": 2e-05,
      "loss": 1.0965,
      "step": 131
    },
    {
      "epoch": 0.04556437694166379,
      "grad_norm": 1.989858627319336,
      "learning_rate": 2e-05,
      "loss": 1.0833,
      "step": 132
    },
    {
      "epoch": 0.04590956161546427,
      "grad_norm": 2.298943519592285,
      "learning_rate": 2e-05,
      "loss": 1.1548,
      "step": 133
    },
    {
      "epoch": 0.04625474628926476,
      "grad_norm": 2.256289005279541,
      "learning_rate": 2e-05,
      "loss": 1.1139,
      "step": 134
    },
    {
      "epoch": 0.04659993096306524,
      "grad_norm": 2.386530876159668,
      "learning_rate": 2e-05,
      "loss": 1.1245,
      "step": 135
    },
    {
      "epoch": 0.04694511563686572,
      "grad_norm": 2.073687791824341,
      "learning_rate": 2e-05,
      "loss": 1.1337,
      "step": 136
    },
    {
      "epoch": 0.04729030031066621,
      "grad_norm": 2.307697057723999,
      "learning_rate": 2e-05,
      "loss": 1.1325,
      "step": 137
    },
    {
      "epoch": 0.04763548498446669,
      "grad_norm": 2.1158194541931152,
      "learning_rate": 2e-05,
      "loss": 1.1637,
      "step": 138
    },
    {
      "epoch": 0.047980669658267174,
      "grad_norm": 2.21449613571167,
      "learning_rate": 2e-05,
      "loss": 1.1802,
      "step": 139
    },
    {
      "epoch": 0.04832585433206766,
      "grad_norm": 2.041476249694824,
      "learning_rate": 2e-05,
      "loss": 1.1007,
      "step": 140
    },
    {
      "epoch": 0.04867103900586814,
      "grad_norm": 2.262849807739258,
      "learning_rate": 2e-05,
      "loss": 1.1006,
      "step": 141
    },
    {
      "epoch": 0.049016223679668625,
      "grad_norm": 2.207761287689209,
      "learning_rate": 2e-05,
      "loss": 1.133,
      "step": 142
    },
    {
      "epoch": 0.049361408353469104,
      "grad_norm": 2.083613872528076,
      "learning_rate": 2e-05,
      "loss": 1.1319,
      "step": 143
    },
    {
      "epoch": 0.04970659302726959,
      "grad_norm": 2.1225838661193848,
      "learning_rate": 2e-05,
      "loss": 1.0786,
      "step": 144
    },
    {
      "epoch": 0.050051777701070076,
      "grad_norm": 2.17154598236084,
      "learning_rate": 2e-05,
      "loss": 1.2138,
      "step": 145
    },
    {
      "epoch": 0.050396962374870555,
      "grad_norm": 2.655251979827881,
      "learning_rate": 2e-05,
      "loss": 1.1639,
      "step": 146
    },
    {
      "epoch": 0.05074214704867104,
      "grad_norm": 2.241605758666992,
      "learning_rate": 2e-05,
      "loss": 1.1345,
      "step": 147
    },
    {
      "epoch": 0.05108733172247152,
      "grad_norm": 2.397520065307617,
      "learning_rate": 2e-05,
      "loss": 1.1592,
      "step": 148
    },
    {
      "epoch": 0.051432516396272006,
      "grad_norm": 2.2444629669189453,
      "learning_rate": 2e-05,
      "loss": 1.134,
      "step": 149
    },
    {
      "epoch": 0.05177770107007249,
      "grad_norm": 2.179332971572876,
      "learning_rate": 2e-05,
      "loss": 1.1726,
      "step": 150
    },
    {
      "epoch": 0.05212288574387297,
      "grad_norm": 2.1803085803985596,
      "learning_rate": 2e-05,
      "loss": 1.1458,
      "step": 151
    },
    {
      "epoch": 0.05246807041767346,
      "grad_norm": 2.06752872467041,
      "learning_rate": 2e-05,
      "loss": 1.1741,
      "step": 152
    },
    {
      "epoch": 0.052813255091473936,
      "grad_norm": 1.9567921161651611,
      "learning_rate": 2e-05,
      "loss": 1.1783,
      "step": 153
    },
    {
      "epoch": 0.05315843976527442,
      "grad_norm": 1.8780710697174072,
      "learning_rate": 2e-05,
      "loss": 1.0461,
      "step": 154
    },
    {
      "epoch": 0.05350362443907491,
      "grad_norm": 2.142355442047119,
      "learning_rate": 2e-05,
      "loss": 1.1683,
      "step": 155
    },
    {
      "epoch": 0.05384880911287539,
      "grad_norm": 2.404834270477295,
      "learning_rate": 2e-05,
      "loss": 1.1367,
      "step": 156
    },
    {
      "epoch": 0.05419399378667587,
      "grad_norm": 2.467586040496826,
      "learning_rate": 2e-05,
      "loss": 1.0616,
      "step": 157
    },
    {
      "epoch": 0.05453917846047635,
      "grad_norm": 2.428678035736084,
      "learning_rate": 2e-05,
      "loss": 1.1587,
      "step": 158
    },
    {
      "epoch": 0.05488436313427684,
      "grad_norm": 1.9721519947052002,
      "learning_rate": 2e-05,
      "loss": 1.0864,
      "step": 159
    },
    {
      "epoch": 0.055229547808077324,
      "grad_norm": 2.282735586166382,
      "learning_rate": 2e-05,
      "loss": 1.1805,
      "step": 160
    },
    {
      "epoch": 0.0555747324818778,
      "grad_norm": 2.136899471282959,
      "learning_rate": 2e-05,
      "loss": 1.0941,
      "step": 161
    },
    {
      "epoch": 0.05591991715567829,
      "grad_norm": 2.0251846313476562,
      "learning_rate": 2e-05,
      "loss": 1.0796,
      "step": 162
    },
    {
      "epoch": 0.05626510182947877,
      "grad_norm": 2.1328299045562744,
      "learning_rate": 2e-05,
      "loss": 1.0917,
      "step": 163
    },
    {
      "epoch": 0.056610286503279254,
      "grad_norm": 2.205331802368164,
      "learning_rate": 2e-05,
      "loss": 1.1792,
      "step": 164
    },
    {
      "epoch": 0.05695547117707974,
      "grad_norm": 2.0339744091033936,
      "learning_rate": 2e-05,
      "loss": 1.1874,
      "step": 165
    },
    {
      "epoch": 0.05730065585088022,
      "grad_norm": 1.8030365705490112,
      "learning_rate": 2e-05,
      "loss": 1.0929,
      "step": 166
    },
    {
      "epoch": 0.057645840524680705,
      "grad_norm": 2.1905670166015625,
      "learning_rate": 2e-05,
      "loss": 1.1831,
      "step": 167
    },
    {
      "epoch": 0.057991025198481184,
      "grad_norm": 2.142336845397949,
      "learning_rate": 2e-05,
      "loss": 1.1237,
      "step": 168
    },
    {
      "epoch": 0.05833620987228167,
      "grad_norm": 2.3521053791046143,
      "learning_rate": 2e-05,
      "loss": 1.1077,
      "step": 169
    },
    {
      "epoch": 0.058681394546082156,
      "grad_norm": 2.105743408203125,
      "learning_rate": 2e-05,
      "loss": 1.1048,
      "step": 170
    },
    {
      "epoch": 0.059026579219882636,
      "grad_norm": 1.9414738416671753,
      "learning_rate": 2e-05,
      "loss": 1.112,
      "step": 171
    },
    {
      "epoch": 0.05937176389368312,
      "grad_norm": 1.9606658220291138,
      "learning_rate": 2e-05,
      "loss": 1.1109,
      "step": 172
    },
    {
      "epoch": 0.0597169485674836,
      "grad_norm": 2.3274831771850586,
      "learning_rate": 2e-05,
      "loss": 1.1803,
      "step": 173
    },
    {
      "epoch": 0.06006213324128409,
      "grad_norm": 2.1384570598602295,
      "learning_rate": 2e-05,
      "loss": 1.0515,
      "step": 174
    },
    {
      "epoch": 0.06040731791508457,
      "grad_norm": 2.0795719623565674,
      "learning_rate": 2e-05,
      "loss": 1.0581,
      "step": 175
    },
    {
      "epoch": 0.06075250258888505,
      "grad_norm": 2.0180423259735107,
      "learning_rate": 2e-05,
      "loss": 1.0686,
      "step": 176
    },
    {
      "epoch": 0.06109768726268554,
      "grad_norm": 2.0913267135620117,
      "learning_rate": 2e-05,
      "loss": 1.117,
      "step": 177
    },
    {
      "epoch": 0.06144287193648602,
      "grad_norm": 2.0325934886932373,
      "learning_rate": 2e-05,
      "loss": 1.1526,
      "step": 178
    },
    {
      "epoch": 0.0617880566102865,
      "grad_norm": 2.222254991531372,
      "learning_rate": 2e-05,
      "loss": 1.113,
      "step": 179
    },
    {
      "epoch": 0.06213324128408699,
      "grad_norm": 2.2039270401000977,
      "learning_rate": 2e-05,
      "loss": 1.1886,
      "step": 180
    },
    {
      "epoch": 0.06247842595788747,
      "grad_norm": 2.0291781425476074,
      "learning_rate": 2e-05,
      "loss": 1.0884,
      "step": 181
    },
    {
      "epoch": 0.06282361063168795,
      "grad_norm": 2.2183430194854736,
      "learning_rate": 2e-05,
      "loss": 1.0223,
      "step": 182
    },
    {
      "epoch": 0.06316879530548844,
      "grad_norm": 2.37440824508667,
      "learning_rate": 2e-05,
      "loss": 1.0775,
      "step": 183
    },
    {
      "epoch": 0.06351397997928893,
      "grad_norm": 1.8214384317398071,
      "learning_rate": 2e-05,
      "loss": 1.1279,
      "step": 184
    },
    {
      "epoch": 0.0638591646530894,
      "grad_norm": 2.205291271209717,
      "learning_rate": 2e-05,
      "loss": 1.0396,
      "step": 185
    },
    {
      "epoch": 0.06420434932688988,
      "grad_norm": 2.137577533721924,
      "learning_rate": 2e-05,
      "loss": 1.0861,
      "step": 186
    },
    {
      "epoch": 0.06454953400069037,
      "grad_norm": 1.982663869857788,
      "learning_rate": 2e-05,
      "loss": 1.1612,
      "step": 187
    },
    {
      "epoch": 0.06489471867449086,
      "grad_norm": 21.140506744384766,
      "learning_rate": 2e-05,
      "loss": 1.0824,
      "step": 188
    },
    {
      "epoch": 0.06523990334829134,
      "grad_norm": 2.2611193656921387,
      "learning_rate": 2e-05,
      "loss": 1.0795,
      "step": 189
    },
    {
      "epoch": 0.06558508802209181,
      "grad_norm": 2.0905325412750244,
      "learning_rate": 2e-05,
      "loss": 1.1989,
      "step": 190
    },
    {
      "epoch": 0.0659302726958923,
      "grad_norm": 1.9430997371673584,
      "learning_rate": 2e-05,
      "loss": 1.0885,
      "step": 191
    },
    {
      "epoch": 0.06627545736969279,
      "grad_norm": 1.8876497745513916,
      "learning_rate": 2e-05,
      "loss": 1.0708,
      "step": 192
    },
    {
      "epoch": 0.06662064204349327,
      "grad_norm": 2.0716099739074707,
      "learning_rate": 2e-05,
      "loss": 1.124,
      "step": 193
    },
    {
      "epoch": 0.06696582671729376,
      "grad_norm": 2.413959503173828,
      "learning_rate": 2e-05,
      "loss": 1.1856,
      "step": 194
    },
    {
      "epoch": 0.06731101139109423,
      "grad_norm": 1.8021107912063599,
      "learning_rate": 2e-05,
      "loss": 1.1284,
      "step": 195
    },
    {
      "epoch": 0.06765619606489472,
      "grad_norm": 2.2795395851135254,
      "learning_rate": 2e-05,
      "loss": 1.1101,
      "step": 196
    },
    {
      "epoch": 0.0680013807386952,
      "grad_norm": 1.936448097229004,
      "learning_rate": 2e-05,
      "loss": 1.0921,
      "step": 197
    },
    {
      "epoch": 0.06834656541249569,
      "grad_norm": 1.940928339958191,
      "learning_rate": 2e-05,
      "loss": 1.1236,
      "step": 198
    },
    {
      "epoch": 0.06869175008629617,
      "grad_norm": 2.1147520542144775,
      "learning_rate": 2e-05,
      "loss": 1.0332,
      "step": 199
    },
    {
      "epoch": 0.06903693476009665,
      "grad_norm": 1.9784513711929321,
      "learning_rate": 2e-05,
      "loss": 1.0644,
      "step": 200
    }
  ],
  "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": 82624433356800.0,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}