{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.30038022813688214,
  "eval_steps": 500,
  "global_step": 474,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006337135614702154,
      "grad_norm": 0.22353313863277435,
      "learning_rate": 2e-05,
      "loss": 0.795,
      "step": 1
    },
    {
      "epoch": 0.0012674271229404308,
      "grad_norm": 0.270685613155365,
      "learning_rate": 4e-05,
      "loss": 0.9841,
      "step": 2
    },
    {
      "epoch": 0.0019011406844106464,
      "grad_norm": 0.13555319607257843,
      "learning_rate": 6e-05,
      "loss": 0.8728,
      "step": 3
    },
    {
      "epoch": 0.0025348542458808617,
      "grad_norm": 0.1665652096271515,
      "learning_rate": 8e-05,
      "loss": 0.8625,
      "step": 4
    },
    {
      "epoch": 0.0031685678073510772,
      "grad_norm": 0.13588839769363403,
      "learning_rate": 0.0001,
      "loss": 0.6776,
      "step": 5
    },
    {
      "epoch": 0.0038022813688212928,
      "grad_norm": 0.2811749279499054,
      "learning_rate": 0.00012,
      "loss": 0.8813,
      "step": 6
    },
    {
      "epoch": 0.004435994930291508,
      "grad_norm": 0.327694833278656,
      "learning_rate": 0.00014,
      "loss": 0.9009,
      "step": 7
    },
    {
      "epoch": 0.005069708491761723,
      "grad_norm": 0.24555213749408722,
      "learning_rate": 0.00016,
      "loss": 0.7054,
      "step": 8
    },
    {
      "epoch": 0.005703422053231939,
      "grad_norm": 0.14921338856220245,
      "learning_rate": 0.00018,
      "loss": 0.697,
      "step": 9
    },
    {
      "epoch": 0.0063371356147021544,
      "grad_norm": 0.13169103860855103,
      "learning_rate": 0.0002,
      "loss": 0.6007,
      "step": 10
    },
    {
      "epoch": 0.00697084917617237,
      "grad_norm": 0.06807047873735428,
      "learning_rate": 0.00019999979928608238,
      "loss": 0.6155,
      "step": 11
    },
    {
      "epoch": 0.0076045627376425855,
      "grad_norm": 0.08288167417049408,
      "learning_rate": 0.00019999919714513528,
      "loss": 0.5641,
      "step": 12
    },
    {
      "epoch": 0.008238276299112801,
      "grad_norm": 0.12285872548818588,
      "learning_rate": 0.00019999819357957582,
      "loss": 0.7526,
      "step": 13
    },
    {
      "epoch": 0.008871989860583017,
      "grad_norm": 0.15566691756248474,
      "learning_rate": 0.00019999678859343263,
      "loss": 0.4519,
      "step": 14
    },
    {
      "epoch": 0.009505703422053232,
      "grad_norm": 0.1301712989807129,
      "learning_rate": 0.00019999498219234568,
      "loss": 0.486,
      "step": 15
    },
    {
      "epoch": 0.010139416983523447,
      "grad_norm": 0.14493511617183685,
      "learning_rate": 0.00019999277438356638,
      "loss": 0.7146,
      "step": 16
    },
    {
      "epoch": 0.010773130544993664,
      "grad_norm": 0.1372271478176117,
      "learning_rate": 0.00019999016517595753,
      "loss": 0.5933,
      "step": 17
    },
    {
      "epoch": 0.011406844106463879,
      "grad_norm": 0.09944190829992294,
      "learning_rate": 0.00019998715457999314,
      "loss": 0.8399,
      "step": 18
    },
    {
      "epoch": 0.012040557667934094,
      "grad_norm": 0.057923465967178345,
      "learning_rate": 0.0001999837426077586,
      "loss": 0.5613,
      "step": 19
    },
    {
      "epoch": 0.012674271229404309,
      "grad_norm": 0.06214901804924011,
      "learning_rate": 0.00019997992927295059,
      "loss": 0.5374,
      "step": 20
    },
    {
      "epoch": 0.013307984790874524,
      "grad_norm": 0.04898112639784813,
      "learning_rate": 0.0001999757145908768,
      "loss": 0.5451,
      "step": 21
    },
    {
      "epoch": 0.01394169835234474,
      "grad_norm": 0.07026948034763336,
      "learning_rate": 0.0001999710985784562,
      "loss": 0.5635,
      "step": 22
    },
    {
      "epoch": 0.014575411913814956,
      "grad_norm": 0.0672365352511406,
      "learning_rate": 0.00019996608125421873,
      "loss": 0.5996,
      "step": 23
    },
    {
      "epoch": 0.015209125475285171,
      "grad_norm": 0.06477885693311691,
      "learning_rate": 0.00019996066263830531,
      "loss": 0.4707,
      "step": 24
    },
    {
      "epoch": 0.015842839036755388,
      "grad_norm": 0.07720793038606644,
      "learning_rate": 0.0001999548427524678,
      "loss": 0.5891,
      "step": 25
    },
    {
      "epoch": 0.016476552598225603,
      "grad_norm": 0.06699500977993011,
      "learning_rate": 0.0001999486216200688,
      "loss": 0.5316,
      "step": 26
    },
    {
      "epoch": 0.017110266159695818,
      "grad_norm": 0.07539479434490204,
      "learning_rate": 0.00019994199926608172,
      "loss": 0.5854,
      "step": 27
    },
    {
      "epoch": 0.017743979721166033,
      "grad_norm": 4.677523136138916,
      "learning_rate": 0.00019993497571709048,
      "loss": 0.5019,
      "step": 28
    },
    {
      "epoch": 0.018377693282636248,
      "grad_norm": 0.07100815325975418,
      "learning_rate": 0.00019992755100128962,
      "loss": 0.4729,
      "step": 29
    },
    {
      "epoch": 0.019011406844106463,
      "grad_norm": 0.06506210565567017,
      "learning_rate": 0.000199919725148484,
      "loss": 0.5597,
      "step": 30
    },
    {
      "epoch": 0.01964512040557668,
      "grad_norm": 0.04945315420627594,
      "learning_rate": 0.0001999114981900887,
      "loss": 0.5044,
      "step": 31
    },
    {
      "epoch": 0.020278833967046894,
      "grad_norm": 0.05103156715631485,
      "learning_rate": 0.0001999028701591291,
      "loss": 0.3637,
      "step": 32
    },
    {
      "epoch": 0.02091254752851711,
      "grad_norm": 0.05288761481642723,
      "learning_rate": 0.00019989384109024048,
      "loss": 0.4345,
      "step": 33
    },
    {
      "epoch": 0.021546261089987327,
      "grad_norm": 0.05457635968923569,
      "learning_rate": 0.0001998844110196681,
      "loss": 0.4714,
      "step": 34
    },
    {
      "epoch": 0.022179974651457542,
      "grad_norm": 0.055830612778663635,
      "learning_rate": 0.0001998745799852668,
      "loss": 0.5285,
      "step": 35
    },
    {
      "epoch": 0.022813688212927757,
      "grad_norm": 0.05858856439590454,
      "learning_rate": 0.00019986434802650113,
      "loss": 0.5106,
      "step": 36
    },
    {
      "epoch": 0.023447401774397972,
      "grad_norm": 0.05847540497779846,
      "learning_rate": 0.00019985371518444503,
      "loss": 0.4394,
      "step": 37
    },
    {
      "epoch": 0.024081115335868188,
      "grad_norm": 0.1140831857919693,
      "learning_rate": 0.00019984268150178167,
      "loss": 0.4782,
      "step": 38
    },
    {
      "epoch": 0.024714828897338403,
      "grad_norm": 0.06483329832553864,
      "learning_rate": 0.00019983124702280334,
      "loss": 0.396,
      "step": 39
    },
    {
      "epoch": 0.025348542458808618,
      "grad_norm": 0.07212468981742859,
      "learning_rate": 0.00019981941179341117,
      "loss": 0.5173,
      "step": 40
    },
    {
      "epoch": 0.025982256020278833,
      "grad_norm": 0.1697537750005722,
      "learning_rate": 0.00019980717586111512,
      "loss": 0.6164,
      "step": 41
    },
    {
      "epoch": 0.026615969581749048,
      "grad_norm": 0.05975339934229851,
      "learning_rate": 0.00019979453927503364,
      "loss": 0.4981,
      "step": 42
    },
    {
      "epoch": 0.027249683143219267,
      "grad_norm": 0.0607403926551342,
      "learning_rate": 0.00019978150208589348,
      "loss": 0.533,
      "step": 43
    },
    {
      "epoch": 0.02788339670468948,
      "grad_norm": 0.07225210964679718,
      "learning_rate": 0.00019976806434602952,
      "loss": 0.5055,
      "step": 44
    },
    {
      "epoch": 0.028517110266159697,
      "grad_norm": 0.07008686661720276,
      "learning_rate": 0.00019975422610938462,
      "loss": 0.6274,
      "step": 45
    },
    {
      "epoch": 0.029150823827629912,
      "grad_norm": 0.07289402186870575,
      "learning_rate": 0.0001997399874315093,
      "loss": 0.5247,
      "step": 46
    },
    {
      "epoch": 0.029784537389100127,
      "grad_norm": 0.10037431120872498,
      "learning_rate": 0.0001997253483695616,
      "loss": 0.647,
      "step": 47
    },
    {
      "epoch": 0.030418250950570342,
      "grad_norm": 0.06468270719051361,
      "learning_rate": 0.00019971030898230672,
      "loss": 0.5719,
      "step": 48
    },
    {
      "epoch": 0.031051964512040557,
      "grad_norm": 0.0472278967499733,
      "learning_rate": 0.00019969486933011705,
      "loss": 0.5565,
      "step": 49
    },
    {
      "epoch": 0.031685678073510776,
      "grad_norm": 0.0584145151078701,
      "learning_rate": 0.00019967902947497156,
      "loss": 0.5432,
      "step": 50
    },
    {
      "epoch": 0.03231939163498099,
      "grad_norm": 0.08962458372116089,
      "learning_rate": 0.00019966278948045592,
      "loss": 0.6432,
      "step": 51
    },
    {
      "epoch": 0.032953105196451206,
      "grad_norm": 0.08193643391132355,
      "learning_rate": 0.00019964614941176195,
      "loss": 0.5341,
      "step": 52
    },
    {
      "epoch": 0.03358681875792142,
      "grad_norm": 0.07166769355535507,
      "learning_rate": 0.00019962910933568747,
      "loss": 0.5481,
      "step": 53
    },
    {
      "epoch": 0.034220532319391636,
      "grad_norm": 0.10422351956367493,
      "learning_rate": 0.00019961166932063614,
      "loss": 0.6145,
      "step": 54
    },
    {
      "epoch": 0.03485424588086185,
      "grad_norm": 0.06273826211690903,
      "learning_rate": 0.00019959382943661704,
      "loss": 0.4969,
      "step": 55
    },
    {
      "epoch": 0.035487959442332066,
      "grad_norm": 0.06504670530557632,
      "learning_rate": 0.0001995755897552444,
      "loss": 0.6093,
      "step": 56
    },
    {
      "epoch": 0.03612167300380228,
      "grad_norm": 0.05045778304338455,
      "learning_rate": 0.00019955695034973742,
      "loss": 0.4191,
      "step": 57
    },
    {
      "epoch": 0.036755386565272496,
      "grad_norm": 0.06495866179466248,
      "learning_rate": 0.00019953791129491983,
      "loss": 0.4762,
      "step": 58
    },
    {
      "epoch": 0.037389100126742715,
      "grad_norm": 0.0814126655459404,
      "learning_rate": 0.0001995184726672197,
      "loss": 0.5599,
      "step": 59
    },
    {
      "epoch": 0.03802281368821293,
      "grad_norm": 0.052061304450035095,
      "learning_rate": 0.00019949863454466908,
      "loss": 0.4822,
      "step": 60
    },
    {
      "epoch": 0.038656527249683145,
      "grad_norm": 0.05419475957751274,
      "learning_rate": 0.00019947839700690375,
      "loss": 0.5625,
      "step": 61
    },
    {
      "epoch": 0.03929024081115336,
      "grad_norm": 0.06495067477226257,
      "learning_rate": 0.0001994577601351628,
      "loss": 0.5863,
      "step": 62
    },
    {
      "epoch": 0.039923954372623575,
      "grad_norm": 0.055791907012462616,
      "learning_rate": 0.00019943672401228837,
      "loss": 0.4588,
      "step": 63
    },
    {
      "epoch": 0.04055766793409379,
      "grad_norm": 0.03923908621072769,
      "learning_rate": 0.00019941528872272532,
      "loss": 0.3841,
      "step": 64
    },
    {
      "epoch": 0.041191381495564006,
      "grad_norm": 0.08200399577617645,
      "learning_rate": 0.00019939345435252088,
      "loss": 0.6163,
      "step": 65
    },
    {
      "epoch": 0.04182509505703422,
      "grad_norm": 0.05708305537700653,
      "learning_rate": 0.00019937122098932428,
      "loss": 0.6363,
      "step": 66
    },
    {
      "epoch": 0.042458808618504436,
      "grad_norm": 0.053468603640794754,
      "learning_rate": 0.0001993485887223864,
      "loss": 0.4777,
      "step": 67
    },
    {
      "epoch": 0.043092522179974654,
      "grad_norm": 0.08539824187755585,
      "learning_rate": 0.00019932555764255952,
      "loss": 0.4922,
      "step": 68
    },
    {
      "epoch": 0.043726235741444866,
      "grad_norm": 0.07483454793691635,
      "learning_rate": 0.00019930212784229675,
      "loss": 0.6337,
      "step": 69
    },
    {
      "epoch": 0.044359949302915085,
      "grad_norm": 0.06771700084209442,
      "learning_rate": 0.00019927829941565186,
      "loss": 0.4559,
      "step": 70
    },
    {
      "epoch": 0.044993662864385296,
      "grad_norm": 0.05689261853694916,
      "learning_rate": 0.0001992540724582788,
      "loss": 0.5489,
      "step": 71
    },
    {
      "epoch": 0.045627376425855515,
      "grad_norm": 0.05044565722346306,
      "learning_rate": 0.00019922944706743127,
      "loss": 0.4472,
      "step": 72
    },
    {
      "epoch": 0.046261089987325726,
      "grad_norm": 0.07331253588199615,
      "learning_rate": 0.00019920442334196248,
      "loss": 0.4752,
      "step": 73
    },
    {
      "epoch": 0.046894803548795945,
      "grad_norm": 0.057449884712696075,
      "learning_rate": 0.0001991790013823246,
      "loss": 0.4525,
      "step": 74
    },
    {
      "epoch": 0.04752851711026616,
      "grad_norm": 0.08357278257608414,
      "learning_rate": 0.00019915318129056853,
      "loss": 0.5813,
      "step": 75
    },
    {
      "epoch": 0.048162230671736375,
      "grad_norm": 0.051311176270246506,
      "learning_rate": 0.00019912696317034322,
      "loss": 0.4593,
      "step": 76
    },
    {
      "epoch": 0.048795944233206594,
      "grad_norm": 0.06535078585147858,
      "learning_rate": 0.00019910034712689552,
      "loss": 0.5339,
      "step": 77
    },
    {
      "epoch": 0.049429657794676805,
      "grad_norm": 0.13796891272068024,
      "learning_rate": 0.00019907333326706967,
      "loss": 0.5438,
      "step": 78
    },
    {
      "epoch": 0.050063371356147024,
      "grad_norm": 0.05667581036686897,
      "learning_rate": 0.0001990459216993068,
      "loss": 0.6295,
      "step": 79
    },
    {
      "epoch": 0.050697084917617236,
      "grad_norm": 0.05243121087551117,
      "learning_rate": 0.00019901811253364456,
      "loss": 0.4782,
      "step": 80
    },
    {
      "epoch": 0.051330798479087454,
      "grad_norm": 0.0769771933555603,
      "learning_rate": 0.0001989899058817167,
      "loss": 0.5692,
      "step": 81
    },
    {
      "epoch": 0.051964512040557666,
      "grad_norm": 0.07334766536951065,
      "learning_rate": 0.00019896130185675261,
      "loss": 0.569,
      "step": 82
    },
    {
      "epoch": 0.052598225602027884,
      "grad_norm": 0.07953603565692902,
      "learning_rate": 0.00019893230057357671,
      "loss": 0.4059,
      "step": 83
    },
    {
      "epoch": 0.053231939163498096,
      "grad_norm": 0.05282806232571602,
      "learning_rate": 0.00019890290214860833,
      "loss": 0.5186,
      "step": 84
    },
    {
      "epoch": 0.053865652724968315,
      "grad_norm": 0.06661225110292435,
      "learning_rate": 0.00019887310669986085,
      "loss": 0.6404,
      "step": 85
    },
    {
      "epoch": 0.05449936628643853,
      "grad_norm": 0.07150626182556152,
      "learning_rate": 0.00019884291434694152,
      "loss": 0.5865,
      "step": 86
    },
    {
      "epoch": 0.055133079847908745,
      "grad_norm": 0.054674554616212845,
      "learning_rate": 0.00019881232521105089,
      "loss": 0.5429,
      "step": 87
    },
    {
      "epoch": 0.05576679340937896,
      "grad_norm": 0.057950377464294434,
      "learning_rate": 0.00019878133941498224,
      "loss": 0.6705,
      "step": 88
    },
    {
      "epoch": 0.056400506970849175,
      "grad_norm": 0.07045155763626099,
      "learning_rate": 0.0001987499570831211,
      "loss": 0.5393,
      "step": 89
    },
    {
      "epoch": 0.057034220532319393,
      "grad_norm": 0.055960092693567276,
      "learning_rate": 0.00019871817834144504,
      "loss": 0.4481,
      "step": 90
    },
    {
      "epoch": 0.057667934093789605,
      "grad_norm": 0.05631652846932411,
      "learning_rate": 0.00019868600331752264,
      "loss": 0.5963,
      "step": 91
    },
    {
      "epoch": 0.058301647655259824,
      "grad_norm": 0.05120407044887543,
      "learning_rate": 0.00019865343214051347,
      "loss": 0.486,
      "step": 92
    },
    {
      "epoch": 0.058935361216730035,
      "grad_norm": 0.05507562682032585,
      "learning_rate": 0.0001986204649411673,
      "loss": 0.5514,
      "step": 93
    },
    {
      "epoch": 0.059569074778200254,
      "grad_norm": 0.057690516114234924,
      "learning_rate": 0.0001985871018518236,
      "loss": 0.4969,
      "step": 94
    },
    {
      "epoch": 0.060202788339670466,
      "grad_norm": 0.05942325294017792,
      "learning_rate": 0.00019855334300641114,
      "loss": 0.51,
      "step": 95
    },
    {
      "epoch": 0.060836501901140684,
      "grad_norm": 0.05777527391910553,
      "learning_rate": 0.0001985191885404473,
      "loss": 0.5401,
      "step": 96
    },
    {
      "epoch": 0.0614702154626109,
      "grad_norm": 0.07077159732580185,
      "learning_rate": 0.00019848463859103763,
      "loss": 0.5568,
      "step": 97
    },
    {
      "epoch": 0.062103929024081114,
      "grad_norm": 0.050649482756853104,
      "learning_rate": 0.00019844969329687527,
      "loss": 0.5418,
      "step": 98
    },
    {
      "epoch": 0.06273764258555133,
      "grad_norm": 0.059522844851017,
      "learning_rate": 0.00019841435279824028,
      "loss": 0.4679,
      "step": 99
    },
    {
      "epoch": 0.06337135614702155,
      "grad_norm": 0.061260003596544266,
      "learning_rate": 0.0001983786172369993,
      "loss": 0.557,
      "step": 100
    },
    {
      "epoch": 0.06400506970849176,
      "grad_norm": 0.0513591468334198,
      "learning_rate": 0.00019834248675660486,
      "loss": 0.5849,
      "step": 101
    },
    {
      "epoch": 0.06463878326996197,
      "grad_norm": 0.06722971051931381,
      "learning_rate": 0.0001983059615020947,
      "loss": 0.4003,
      "step": 102
    },
    {
      "epoch": 0.06527249683143219,
      "grad_norm": 0.0629379004240036,
      "learning_rate": 0.0001982690416200914,
      "loss": 0.5322,
      "step": 103
    },
    {
      "epoch": 0.06590621039290241,
      "grad_norm": 0.05402471870183945,
      "learning_rate": 0.00019823172725880165,
      "loss": 0.5634,
      "step": 104
    },
    {
      "epoch": 0.06653992395437262,
      "grad_norm": 0.15680162608623505,
      "learning_rate": 0.0001981940185680156,
      "loss": 0.5361,
      "step": 105
    },
    {
      "epoch": 0.06717363751584284,
      "grad_norm": 0.06348865479230881,
      "learning_rate": 0.00019815591569910654,
      "loss": 0.5322,
      "step": 106
    },
    {
      "epoch": 0.06780735107731306,
      "grad_norm": 0.05004284158349037,
      "learning_rate": 0.00019811741880502995,
      "loss": 0.5524,
      "step": 107
    },
    {
      "epoch": 0.06844106463878327,
      "grad_norm": 0.06271985173225403,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.4347,
      "step": 108
    },
    {
      "epoch": 0.06907477820025348,
      "grad_norm": 0.1546468287706375,
      "learning_rate": 0.00019803924356110423,
      "loss": 0.4294,
      "step": 109
    },
    {
      "epoch": 0.0697084917617237,
      "grad_norm": 0.06472460180521011,
      "learning_rate": 0.00019799956552507233,
      "loss": 0.5693,
      "step": 110
    },
    {
      "epoch": 0.07034220532319392,
      "grad_norm": 0.06021984666585922,
      "learning_rate": 0.00019795949409150598,
      "loss": 0.6554,
      "step": 111
    },
    {
      "epoch": 0.07097591888466413,
      "grad_norm": 0.04533032327890396,
      "learning_rate": 0.00019791902942126313,
      "loss": 0.4425,
      "step": 112
    },
    {
      "epoch": 0.07160963244613434,
      "grad_norm": 0.0662391185760498,
      "learning_rate": 0.0001978781716767802,
      "loss": 0.5258,
      "step": 113
    },
    {
      "epoch": 0.07224334600760456,
      "grad_norm": 0.06131117045879364,
      "learning_rate": 0.00019783692102207155,
      "loss": 0.4556,
      "step": 114
    },
    {
      "epoch": 0.07287705956907478,
      "grad_norm": 0.07924918830394745,
      "learning_rate": 0.00019779527762272877,
      "loss": 0.5137,
      "step": 115
    },
    {
      "epoch": 0.07351077313054499,
      "grad_norm": 0.07061261683702469,
      "learning_rate": 0.0001977532416459201,
      "loss": 0.4554,
      "step": 116
    },
    {
      "epoch": 0.0741444866920152,
      "grad_norm": 0.04919254407286644,
      "learning_rate": 0.00019771081326038962,
      "loss": 0.5213,
      "step": 117
    },
    {
      "epoch": 0.07477820025348543,
      "grad_norm": 0.053799472749233246,
      "learning_rate": 0.00019766799263645673,
      "loss": 0.5648,
      "step": 118
    },
    {
      "epoch": 0.07541191381495564,
      "grad_norm": 0.06857369095087051,
      "learning_rate": 0.00019762477994601522,
      "loss": 0.6841,
      "step": 119
    },
    {
      "epoch": 0.07604562737642585,
      "grad_norm": 0.0719090923666954,
      "learning_rate": 0.000197581175362533,
      "loss": 0.4154,
      "step": 120
    },
    {
      "epoch": 0.07667934093789606,
      "grad_norm": 0.10528447479009628,
      "learning_rate": 0.00019753717906105092,
      "loss": 0.5674,
      "step": 121
    },
    {
      "epoch": 0.07731305449936629,
      "grad_norm": 0.05879104137420654,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.5282,
      "step": 122
    },
    {
      "epoch": 0.0779467680608365,
      "grad_norm": 0.050949644297361374,
      "learning_rate": 0.00019744801201211255,
      "loss": 0.4398,
      "step": 123
    },
    {
      "epoch": 0.07858048162230671,
      "grad_norm": 0.061247747391462326,
      "learning_rate": 0.00019740284162259765,
      "loss": 0.4269,
      "step": 124
    },
    {
      "epoch": 0.07921419518377694,
      "grad_norm": 0.09446462988853455,
      "learning_rate": 0.0001973572802309642,
      "loss": 0.6362,
      "step": 125
    },
    {
      "epoch": 0.07984790874524715,
      "grad_norm": 0.06124195456504822,
      "learning_rate": 0.0001973113280201082,
      "loss": 0.435,
      "step": 126
    },
    {
      "epoch": 0.08048162230671736,
      "grad_norm": 0.05198049172759056,
      "learning_rate": 0.0001972649851744948,
      "loss": 0.4617,
      "step": 127
    },
    {
      "epoch": 0.08111533586818757,
      "grad_norm": 0.05457935482263565,
      "learning_rate": 0.00019721825188015693,
      "loss": 0.548,
      "step": 128
    },
    {
      "epoch": 0.0817490494296578,
      "grad_norm": 0.054542481899261475,
      "learning_rate": 0.0001971711283246951,
      "loss": 0.4449,
      "step": 129
    },
    {
      "epoch": 0.08238276299112801,
      "grad_norm": 0.0528152696788311,
      "learning_rate": 0.0001971236146972764,
      "loss": 0.5868,
      "step": 130
    },
    {
      "epoch": 0.08301647655259822,
      "grad_norm": 0.049837883561849594,
      "learning_rate": 0.0001970757111886337,
      "loss": 0.4426,
      "step": 131
    },
    {
      "epoch": 0.08365019011406843,
      "grad_norm": 0.04912682995200157,
      "learning_rate": 0.00019702741799106508,
      "loss": 0.5328,
      "step": 132
    },
    {
      "epoch": 0.08428390367553866,
      "grad_norm": 0.06654444336891174,
      "learning_rate": 0.00019697873529843282,
      "loss": 0.6239,
      "step": 133
    },
    {
      "epoch": 0.08491761723700887,
      "grad_norm": 0.1822642683982849,
      "learning_rate": 0.00019692966330616283,
      "loss": 0.6482,
      "step": 134
    },
    {
      "epoch": 0.08555133079847908,
      "grad_norm": 0.07404999434947968,
      "learning_rate": 0.00019688020221124376,
      "loss": 0.5473,
      "step": 135
    },
    {
      "epoch": 0.08618504435994931,
      "grad_norm": 0.08534666895866394,
      "learning_rate": 0.00019683035221222618,
      "loss": 0.4794,
      "step": 136
    },
    {
      "epoch": 0.08681875792141952,
      "grad_norm": 0.05804799869656563,
      "learning_rate": 0.00019678011350922185,
      "loss": 0.5749,
      "step": 137
    },
    {
      "epoch": 0.08745247148288973,
      "grad_norm": 0.0600556954741478,
      "learning_rate": 0.00019672948630390294,
      "loss": 0.4929,
      "step": 138
    },
    {
      "epoch": 0.08808618504435994,
      "grad_norm": 0.07564158737659454,
      "learning_rate": 0.00019667847079950118,
      "loss": 0.5806,
      "step": 139
    },
    {
      "epoch": 0.08871989860583017,
      "grad_norm": 0.06359097361564636,
      "learning_rate": 0.00019662706720080693,
      "loss": 0.5427,
      "step": 140
    },
    {
      "epoch": 0.08935361216730038,
      "grad_norm": 0.05452190712094307,
      "learning_rate": 0.00019657527571416856,
      "loss": 0.4845,
      "step": 141
    },
    {
      "epoch": 0.08998732572877059,
      "grad_norm": 0.05258841812610626,
      "learning_rate": 0.00019652309654749156,
      "loss": 0.5255,
      "step": 142
    },
    {
      "epoch": 0.09062103929024082,
      "grad_norm": 0.06789179146289825,
      "learning_rate": 0.0001964705299102376,
      "loss": 0.6002,
      "step": 143
    },
    {
      "epoch": 0.09125475285171103,
      "grad_norm": 0.05940316617488861,
      "learning_rate": 0.00019641757601342378,
      "loss": 0.6178,
      "step": 144
    },
    {
      "epoch": 0.09188846641318124,
      "grad_norm": 0.08051005005836487,
      "learning_rate": 0.00019636423506962181,
      "loss": 0.4728,
      "step": 145
    },
    {
      "epoch": 0.09252217997465145,
      "grad_norm": 0.06979210674762726,
      "learning_rate": 0.00019631050729295707,
      "loss": 0.5166,
      "step": 146
    },
    {
      "epoch": 0.09315589353612168,
      "grad_norm": 0.04284743592143059,
      "learning_rate": 0.00019625639289910777,
      "loss": 0.3685,
      "step": 147
    },
    {
      "epoch": 0.09378960709759189,
      "grad_norm": 0.05410388484597206,
      "learning_rate": 0.00019620189210530425,
      "loss": 0.582,
      "step": 148
    },
    {
      "epoch": 0.0944233206590621,
      "grad_norm": 0.08875017613172531,
      "learning_rate": 0.00019614700513032775,
      "loss": 0.6757,
      "step": 149
    },
    {
      "epoch": 0.09505703422053231,
      "grad_norm": 0.06792068481445312,
      "learning_rate": 0.00019609173219450998,
      "loss": 0.5236,
      "step": 150
    },
    {
      "epoch": 0.09569074778200254,
      "grad_norm": 0.060000237077474594,
      "learning_rate": 0.0001960360735197318,
      "loss": 0.4813,
      "step": 151
    },
    {
      "epoch": 0.09632446134347275,
      "grad_norm": 0.052172888070344925,
      "learning_rate": 0.00019598002932942266,
      "loss": 0.5792,
      "step": 152
    },
    {
      "epoch": 0.09695817490494296,
      "grad_norm": 0.04992865398526192,
      "learning_rate": 0.00019592359984855952,
      "loss": 0.4652,
      "step": 153
    },
    {
      "epoch": 0.09759188846641319,
      "grad_norm": 0.05908304825425148,
      "learning_rate": 0.00019586678530366606,
      "loss": 0.4968,
      "step": 154
    },
    {
      "epoch": 0.0982256020278834,
      "grad_norm": 0.16080443561077118,
      "learning_rate": 0.00019580958592281167,
      "loss": 0.4804,
      "step": 155
    },
    {
      "epoch": 0.09885931558935361,
      "grad_norm": 0.05863935872912407,
      "learning_rate": 0.00019575200193561057,
      "loss": 0.5313,
      "step": 156
    },
    {
      "epoch": 0.09949302915082382,
      "grad_norm": 0.047341488301754,
      "learning_rate": 0.0001956940335732209,
      "loss": 0.4939,
      "step": 157
    },
    {
      "epoch": 0.10012674271229405,
      "grad_norm": 0.059797484427690506,
      "learning_rate": 0.00019563568106834383,
      "loss": 0.4806,
      "step": 158
    },
    {
      "epoch": 0.10076045627376426,
      "grad_norm": 0.08543235808610916,
      "learning_rate": 0.00019557694465522255,
      "loss": 0.5691,
      "step": 159
    },
    {
      "epoch": 0.10139416983523447,
      "grad_norm": 0.0614972747862339,
      "learning_rate": 0.00019551782456964136,
      "loss": 0.5143,
      "step": 160
    },
    {
      "epoch": 0.10202788339670468,
      "grad_norm": 0.12742456793785095,
      "learning_rate": 0.00019545832104892475,
      "loss": 0.4987,
      "step": 161
    },
    {
      "epoch": 0.10266159695817491,
      "grad_norm": 0.06898955255746841,
      "learning_rate": 0.00019539843433193639,
      "loss": 0.5504,
      "step": 162
    },
    {
      "epoch": 0.10329531051964512,
      "grad_norm": 0.11239788681268692,
      "learning_rate": 0.0001953381646590783,
      "loss": 0.3448,
      "step": 163
    },
    {
      "epoch": 0.10392902408111533,
      "grad_norm": 0.24028901755809784,
      "learning_rate": 0.00019527751227228963,
      "loss": 0.5294,
      "step": 164
    },
    {
      "epoch": 0.10456273764258556,
      "grad_norm": 0.0903674066066742,
      "learning_rate": 0.00019521647741504604,
      "loss": 0.514,
      "step": 165
    },
    {
      "epoch": 0.10519645120405577,
      "grad_norm": 0.051598865538835526,
      "learning_rate": 0.00019515506033235833,
      "loss": 0.4771,
      "step": 166
    },
    {
      "epoch": 0.10583016476552598,
      "grad_norm": 0.05018608644604683,
      "learning_rate": 0.0001950932612707719,
      "loss": 0.4492,
      "step": 167
    },
    {
      "epoch": 0.10646387832699619,
      "grad_norm": 0.07150580734014511,
      "learning_rate": 0.00019503108047836523,
      "loss": 0.5806,
      "step": 168
    },
    {
      "epoch": 0.10709759188846642,
      "grad_norm": 0.05979820713400841,
      "learning_rate": 0.00019496851820474944,
      "loss": 0.6138,
      "step": 169
    },
    {
      "epoch": 0.10773130544993663,
      "grad_norm": 0.05117090418934822,
      "learning_rate": 0.00019490557470106686,
      "loss": 0.5138,
      "step": 170
    },
    {
      "epoch": 0.10836501901140684,
      "grad_norm": 0.049405183643102646,
      "learning_rate": 0.0001948422502199903,
      "loss": 0.4974,
      "step": 171
    },
    {
      "epoch": 0.10899873257287707,
      "grad_norm": 0.060524292290210724,
      "learning_rate": 0.00019477854501572176,
      "loss": 0.5448,
      "step": 172
    },
    {
      "epoch": 0.10963244613434728,
      "grad_norm": 0.05022512748837471,
      "learning_rate": 0.0001947144593439917,
      "loss": 0.5295,
      "step": 173
    },
    {
      "epoch": 0.11026615969581749,
      "grad_norm": 0.05024838447570801,
      "learning_rate": 0.0001946499934620579,
      "loss": 0.4842,
      "step": 174
    },
    {
      "epoch": 0.1108998732572877,
      "grad_norm": 0.05859989672899246,
      "learning_rate": 0.00019458514762870426,
      "loss": 0.5105,
      "step": 175
    },
    {
      "epoch": 0.11153358681875793,
      "grad_norm": 0.05963319167494774,
      "learning_rate": 0.00019451992210424006,
      "loss": 0.4833,
      "step": 176
    },
    {
      "epoch": 0.11216730038022814,
      "grad_norm": 0.05941782146692276,
      "learning_rate": 0.0001944543171504987,
      "loss": 0.4743,
      "step": 177
    },
    {
      "epoch": 0.11280101394169835,
      "grad_norm": 0.07598856091499329,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.483,
      "step": 178
    },
    {
      "epoch": 0.11343472750316856,
      "grad_norm": 0.05751622095704079,
      "learning_rate": 0.0001943219700101328,
      "loss": 0.563,
      "step": 179
    },
    {
      "epoch": 0.11406844106463879,
      "grad_norm": 0.08273158222436905,
      "learning_rate": 0.0001942552283547865,
      "loss": 0.5514,
      "step": 180
    },
    {
      "epoch": 0.114702154626109,
      "grad_norm": 0.04589926823973656,
      "learning_rate": 0.00019418810833271745,
      "loss": 0.4353,
      "step": 181
    },
    {
      "epoch": 0.11533586818757921,
      "grad_norm": 0.04818568378686905,
      "learning_rate": 0.00019412061021336404,
      "loss": 0.4653,
      "step": 182
    },
    {
      "epoch": 0.11596958174904944,
      "grad_norm": 0.062292054295539856,
      "learning_rate": 0.0001940527342676826,
      "loss": 0.5451,
      "step": 183
    },
    {
      "epoch": 0.11660329531051965,
      "grad_norm": 0.05161510780453682,
      "learning_rate": 0.000193984480768146,
      "loss": 0.5174,
      "step": 184
    },
    {
      "epoch": 0.11723700887198986,
      "grad_norm": 0.0669926106929779,
      "learning_rate": 0.0001939158499887428,
      "loss": 0.5074,
      "step": 185
    },
    {
      "epoch": 0.11787072243346007,
      "grad_norm": 0.04856441915035248,
      "learning_rate": 0.00019384684220497605,
      "loss": 0.3898,
      "step": 186
    },
    {
      "epoch": 0.1185044359949303,
      "grad_norm": 0.05841194465756416,
      "learning_rate": 0.0001937774576938622,
      "loss": 0.5437,
      "step": 187
    },
    {
      "epoch": 0.11913814955640051,
      "grad_norm": 0.05253444239497185,
      "learning_rate": 0.00019370769673393007,
      "loss": 0.5669,
      "step": 188
    },
    {
      "epoch": 0.11977186311787072,
      "grad_norm": 0.05771539360284805,
      "learning_rate": 0.00019363755960521943,
      "loss": 0.4965,
      "step": 189
    },
    {
      "epoch": 0.12040557667934093,
      "grad_norm": 0.07135152071714401,
      "learning_rate": 0.00019356704658928035,
      "loss": 0.4089,
      "step": 190
    },
    {
      "epoch": 0.12103929024081116,
      "grad_norm": 0.05927246809005737,
      "learning_rate": 0.00019349615796917163,
      "loss": 0.465,
      "step": 191
    },
    {
      "epoch": 0.12167300380228137,
      "grad_norm": 0.06522128731012344,
      "learning_rate": 0.00019342489402945998,
      "loss": 0.3797,
      "step": 192
    },
    {
      "epoch": 0.12230671736375158,
      "grad_norm": 0.05745214596390724,
      "learning_rate": 0.0001933532550562187,
      "loss": 0.56,
      "step": 193
    },
    {
      "epoch": 0.1229404309252218,
      "grad_norm": 0.05626146122813225,
      "learning_rate": 0.0001932812413370265,
      "loss": 0.5439,
      "step": 194
    },
    {
      "epoch": 0.12357414448669202,
      "grad_norm": 0.07615689933300018,
      "learning_rate": 0.00019320885316096654,
      "loss": 0.5187,
      "step": 195
    },
    {
      "epoch": 0.12420785804816223,
      "grad_norm": 0.19566097855567932,
      "learning_rate": 0.00019313609081862508,
      "loss": 0.5535,
      "step": 196
    },
    {
      "epoch": 0.12484157160963244,
      "grad_norm": 0.052284326404333115,
      "learning_rate": 0.00019306295460209044,
      "loss": 0.4056,
      "step": 197
    },
    {
      "epoch": 0.12547528517110265,
      "grad_norm": 0.050081610679626465,
      "learning_rate": 0.00019298944480495176,
      "loss": 0.451,
      "step": 198
    },
    {
      "epoch": 0.12610899873257286,
      "grad_norm": 0.07420384138822556,
      "learning_rate": 0.00019291556172229785,
      "loss": 0.5485,
      "step": 199
    },
    {
      "epoch": 0.1267427122940431,
      "grad_norm": 0.046289846301078796,
      "learning_rate": 0.00019284130565071588,
      "loss": 0.4944,
      "step": 200
    },
    {
      "epoch": 0.12737642585551331,
      "grad_norm": 0.041031207889318466,
      "learning_rate": 0.00019276667688829043,
      "loss": 0.4507,
      "step": 201
    },
    {
      "epoch": 0.12801013941698353,
      "grad_norm": 0.07089229673147202,
      "learning_rate": 0.0001926916757346022,
      "loss": 0.513,
      "step": 202
    },
    {
      "epoch": 0.12864385297845374,
      "grad_norm": 0.04405022785067558,
      "learning_rate": 0.00019261630249072659,
      "loss": 0.3709,
      "step": 203
    },
    {
      "epoch": 0.12927756653992395,
      "grad_norm": 0.059661708772182465,
      "learning_rate": 0.00019254055745923285,
      "loss": 0.4813,
      "step": 204
    },
    {
      "epoch": 0.12991128010139416,
      "grad_norm": 0.07400868833065033,
      "learning_rate": 0.00019246444094418255,
      "loss": 0.5346,
      "step": 205
    },
    {
      "epoch": 0.13054499366286437,
      "grad_norm": 0.05862591415643692,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.4856,
      "step": 206
    },
    {
      "epoch": 0.1311787072243346,
      "grad_norm": 0.05793355405330658,
      "learning_rate": 0.00019231109468711405,
      "loss": 0.5129,
      "step": 207
    },
    {
      "epoch": 0.13181242078580482,
      "grad_norm": 0.043961625546216965,
      "learning_rate": 0.00019223386556067033,
      "loss": 0.4803,
      "step": 208
    },
    {
      "epoch": 0.13244613434727504,
      "grad_norm": 0.07102088630199432,
      "learning_rate": 0.00019215626618181676,
      "loss": 0.5078,
      "step": 209
    },
    {
      "epoch": 0.13307984790874525,
      "grad_norm": 0.07707204669713974,
      "learning_rate": 0.00019207829686205882,
      "loss": 0.5465,
      "step": 210
    },
    {
      "epoch": 0.13371356147021546,
      "grad_norm": 0.06010926514863968,
      "learning_rate": 0.0001919999579143871,
      "loss": 0.5532,
      "step": 211
    },
    {
      "epoch": 0.13434727503168567,
      "grad_norm": 0.0627330020070076,
      "learning_rate": 0.0001919212496532759,
      "loss": 0.4055,
      "step": 212
    },
    {
      "epoch": 0.13498098859315588,
      "grad_norm": 0.04347623884677887,
      "learning_rate": 0.00019184217239468212,
      "loss": 0.4581,
      "step": 213
    },
    {
      "epoch": 0.13561470215462612,
      "grad_norm": 0.05672100558876991,
      "learning_rate": 0.00019176272645604386,
      "loss": 0.5335,
      "step": 214
    },
    {
      "epoch": 0.13624841571609633,
      "grad_norm": 0.05062992498278618,
      "learning_rate": 0.00019168291215627926,
      "loss": 0.4801,
      "step": 215
    },
    {
      "epoch": 0.13688212927756654,
      "grad_norm": 8.16939640045166,
      "learning_rate": 0.00019160272981578512,
      "loss": 0.5814,
      "step": 216
    },
    {
      "epoch": 0.13751584283903676,
      "grad_norm": 0.058165278285741806,
      "learning_rate": 0.00019152217975643566,
      "loss": 0.5163,
      "step": 217
    },
    {
      "epoch": 0.13814955640050697,
      "grad_norm": 0.06994735449552536,
      "learning_rate": 0.00019144126230158127,
      "loss": 0.5558,
      "step": 218
    },
    {
      "epoch": 0.13878326996197718,
      "grad_norm": 0.05495104938745499,
      "learning_rate": 0.0001913599777760471,
      "loss": 0.5298,
      "step": 219
    },
    {
      "epoch": 0.1394169835234474,
      "grad_norm": 0.060677338391542435,
      "learning_rate": 0.00019127832650613189,
      "loss": 0.5614,
      "step": 220
    },
    {
      "epoch": 0.14005069708491763,
      "grad_norm": 0.060457441955804825,
      "learning_rate": 0.00019119630881960658,
      "loss": 0.5139,
      "step": 221
    },
    {
      "epoch": 0.14068441064638784,
      "grad_norm": 0.0608784481883049,
      "learning_rate": 0.00019111392504571296,
      "loss": 0.4711,
      "step": 222
    },
    {
      "epoch": 0.14131812420785805,
      "grad_norm": 0.07560902833938599,
      "learning_rate": 0.00019103117551516244,
      "loss": 0.486,
      "step": 223
    },
    {
      "epoch": 0.14195183776932827,
      "grad_norm": 0.0847187414765358,
      "learning_rate": 0.00019094806056013468,
      "loss": 0.5934,
      "step": 224
    },
    {
      "epoch": 0.14258555133079848,
      "grad_norm": 0.06016870215535164,
      "learning_rate": 0.00019086458051427622,
      "loss": 0.4529,
      "step": 225
    },
    {
      "epoch": 0.1432192648922687,
      "grad_norm": 0.17245864868164062,
      "learning_rate": 0.00019078073571269922,
      "loss": 0.5307,
      "step": 226
    },
    {
      "epoch": 0.1438529784537389,
      "grad_norm": 0.0647033080458641,
      "learning_rate": 0.00019069652649198005,
      "loss": 0.569,
      "step": 227
    },
    {
      "epoch": 0.1444866920152091,
      "grad_norm": 0.07447489351034164,
      "learning_rate": 0.00019061195319015797,
      "loss": 0.547,
      "step": 228
    },
    {
      "epoch": 0.14512040557667935,
      "grad_norm": 0.05335066467523575,
      "learning_rate": 0.00019052701614673373,
      "loss": 0.5363,
      "step": 229
    },
    {
      "epoch": 0.14575411913814956,
      "grad_norm": 0.04057115688920021,
      "learning_rate": 0.0001904417157026683,
      "loss": 0.4354,
      "step": 230
    },
    {
      "epoch": 0.14638783269961977,
      "grad_norm": 0.05564083158969879,
      "learning_rate": 0.00019035605220038137,
      "loss": 0.5674,
      "step": 231
    },
    {
      "epoch": 0.14702154626108999,
      "grad_norm": 0.1210884302854538,
      "learning_rate": 0.00019027002598375012,
      "loss": 0.5645,
      "step": 232
    },
    {
      "epoch": 0.1476552598225602,
      "grad_norm": 0.05494518578052521,
      "learning_rate": 0.00019018363739810767,
      "loss": 0.6239,
      "step": 233
    },
    {
      "epoch": 0.1482889733840304,
      "grad_norm": 0.04633218050003052,
      "learning_rate": 0.0001900968867902419,
      "loss": 0.4787,
      "step": 234
    },
    {
      "epoch": 0.14892268694550062,
      "grad_norm": 0.06846950203180313,
      "learning_rate": 0.00019000977450839393,
      "loss": 0.5607,
      "step": 235
    },
    {
      "epoch": 0.14955640050697086,
      "grad_norm": 0.0618814192712307,
      "learning_rate": 0.0001899223009022566,
      "loss": 0.631,
      "step": 236
    },
    {
      "epoch": 0.15019011406844107,
      "grad_norm": 0.06061235070228577,
      "learning_rate": 0.00018983446632297343,
      "loss": 0.5989,
      "step": 237
    },
    {
      "epoch": 0.15082382762991128,
      "grad_norm": 0.06494279205799103,
      "learning_rate": 0.00018974627112313677,
      "loss": 0.5816,
      "step": 238
    },
    {
      "epoch": 0.1514575411913815,
      "grad_norm": 0.04907020181417465,
      "learning_rate": 0.0001896577156567868,
      "loss": 0.5097,
      "step": 239
    },
    {
      "epoch": 0.1520912547528517,
      "grad_norm": 0.04682941362261772,
      "learning_rate": 0.00018956880027940967,
      "loss": 0.5828,
      "step": 240
    },
    {
      "epoch": 0.15272496831432192,
      "grad_norm": 0.05498978868126869,
      "learning_rate": 0.00018947952534793661,
      "loss": 0.5257,
      "step": 241
    },
    {
      "epoch": 0.15335868187579213,
      "grad_norm": 0.04309950768947601,
      "learning_rate": 0.00018938989122074197,
      "loss": 0.3662,
      "step": 242
    },
    {
      "epoch": 0.15399239543726237,
      "grad_norm": 0.06519515067338943,
      "learning_rate": 0.00018929989825764207,
      "loss": 0.4058,
      "step": 243
    },
    {
      "epoch": 0.15462610899873258,
      "grad_norm": 0.046929214149713516,
      "learning_rate": 0.00018920954681989378,
      "loss": 0.4916,
      "step": 244
    },
    {
      "epoch": 0.1552598225602028,
      "grad_norm": 0.05388319492340088,
      "learning_rate": 0.00018911883727019285,
      "loss": 0.4143,
      "step": 245
    },
    {
      "epoch": 0.155893536121673,
      "grad_norm": 0.05619863048195839,
      "learning_rate": 0.00018902776997267268,
      "loss": 0.5107,
      "step": 246
    },
    {
      "epoch": 0.15652724968314322,
      "grad_norm": 0.053882747888565063,
      "learning_rate": 0.00018893634529290279,
      "loss": 0.5559,
      "step": 247
    },
    {
      "epoch": 0.15716096324461343,
      "grad_norm": 0.05231885239481926,
      "learning_rate": 0.00018884456359788724,
      "loss": 0.5076,
      "step": 248
    },
    {
      "epoch": 0.15779467680608364,
      "grad_norm": 0.07149146497249603,
      "learning_rate": 0.00018875242525606334,
      "loss": 0.558,
      "step": 249
    },
    {
      "epoch": 0.15842839036755388,
      "grad_norm": 0.04615316912531853,
      "learning_rate": 0.00018865993063730004,
      "loss": 0.4971,
      "step": 250
    },
    {
      "epoch": 0.1590621039290241,
      "grad_norm": 0.05331886187195778,
      "learning_rate": 0.00018856708011289643,
      "loss": 0.5506,
      "step": 251
    },
    {
      "epoch": 0.1596958174904943,
      "grad_norm": 0.05348580330610275,
      "learning_rate": 0.00018847387405558045,
      "loss": 0.4515,
      "step": 252
    },
    {
      "epoch": 0.1603295310519645,
      "grad_norm": 0.0438147634267807,
      "learning_rate": 0.00018838031283950705,
      "loss": 0.3818,
      "step": 253
    },
    {
      "epoch": 0.16096324461343473,
      "grad_norm": 0.0473354198038578,
      "learning_rate": 0.0001882863968402571,
      "loss": 0.4458,
      "step": 254
    },
    {
      "epoch": 0.16159695817490494,
      "grad_norm": 0.05930502712726593,
      "learning_rate": 0.0001881921264348355,
      "loss": 0.6228,
      "step": 255
    },
    {
      "epoch": 0.16223067173637515,
      "grad_norm": 0.04982107877731323,
      "learning_rate": 0.00018809750200166994,
      "loss": 0.5916,
      "step": 256
    },
    {
      "epoch": 0.1628643852978454,
      "grad_norm": 0.09739918261766434,
      "learning_rate": 0.0001880025239206092,
      "loss": 0.651,
      "step": 257
    },
    {
      "epoch": 0.1634980988593156,
      "grad_norm": 0.09072676301002502,
      "learning_rate": 0.00018790719257292174,
      "loss": 0.5564,
      "step": 258
    },
    {
      "epoch": 0.1641318124207858,
      "grad_norm": 0.0638791099190712,
      "learning_rate": 0.00018781150834129413,
      "loss": 0.4545,
      "step": 259
    },
    {
      "epoch": 0.16476552598225602,
      "grad_norm": 0.05755198001861572,
      "learning_rate": 0.0001877154716098295,
      "loss": 0.4457,
      "step": 260
    },
    {
      "epoch": 0.16539923954372623,
      "grad_norm": 0.2049247920513153,
      "learning_rate": 0.00018761908276404603,
      "loss": 0.5447,
      "step": 261
    },
    {
      "epoch": 0.16603295310519645,
      "grad_norm": 0.06760350614786148,
      "learning_rate": 0.00018752234219087538,
      "loss": 0.4743,
      "step": 262
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.061410121619701385,
      "learning_rate": 0.00018742525027866115,
      "loss": 0.547,
      "step": 263
    },
    {
      "epoch": 0.16730038022813687,
      "grad_norm": 0.04981521889567375,
      "learning_rate": 0.00018732780741715724,
      "loss": 0.4924,
      "step": 264
    },
    {
      "epoch": 0.1679340937896071,
      "grad_norm": 0.06636273115873337,
      "learning_rate": 0.00018723001399752653,
      "loss": 0.591,
      "step": 265
    },
    {
      "epoch": 0.16856780735107732,
      "grad_norm": 0.0517747662961483,
      "learning_rate": 0.00018713187041233896,
      "loss": 0.5294,
      "step": 266
    },
    {
      "epoch": 0.16920152091254753,
      "grad_norm": 0.11798780411481857,
      "learning_rate": 0.00018703337705557017,
      "loss": 0.4953,
      "step": 267
    },
    {
      "epoch": 0.16983523447401774,
      "grad_norm": 0.1441587656736374,
      "learning_rate": 0.00018693453432259998,
      "loss": 0.4898,
      "step": 268
    },
    {
      "epoch": 0.17046894803548795,
      "grad_norm": 0.06387986242771149,
      "learning_rate": 0.00018683534261021057,
      "loss": 0.4663,
      "step": 269
    },
    {
      "epoch": 0.17110266159695817,
      "grad_norm": 0.05943833664059639,
      "learning_rate": 0.0001867358023165851,
      "loss": 0.5607,
      "step": 270
    },
    {
      "epoch": 0.17173637515842838,
      "grad_norm": 0.05011943355202675,
      "learning_rate": 0.00018663591384130606,
      "loss": 0.5297,
      "step": 271
    },
    {
      "epoch": 0.17237008871989862,
      "grad_norm": 0.059131983667612076,
      "learning_rate": 0.00018653567758535354,
      "loss": 0.4896,
      "step": 272
    },
    {
      "epoch": 0.17300380228136883,
      "grad_norm": 0.06053609773516655,
      "learning_rate": 0.0001864350939511038,
      "loss": 0.5446,
      "step": 273
    },
    {
      "epoch": 0.17363751584283904,
      "grad_norm": 0.05496980994939804,
      "learning_rate": 0.00018633416334232753,
      "loss": 0.5427,
      "step": 274
    },
    {
      "epoch": 0.17427122940430925,
      "grad_norm": 0.05304751545190811,
      "learning_rate": 0.0001862328861641883,
      "loss": 0.4189,
      "step": 275
    },
    {
      "epoch": 0.17490494296577946,
      "grad_norm": 0.04881710559129715,
      "learning_rate": 0.00018613126282324092,
      "loss": 0.4555,
      "step": 276
    },
    {
      "epoch": 0.17553865652724968,
      "grad_norm": 0.051984284073114395,
      "learning_rate": 0.0001860292937274297,
      "loss": 0.5282,
      "step": 277
    },
    {
      "epoch": 0.1761723700887199,
      "grad_norm": 0.05241424962878227,
      "learning_rate": 0.00018592697928608703,
      "loss": 0.4924,
      "step": 278
    },
    {
      "epoch": 0.17680608365019013,
      "grad_norm": 0.04947778955101967,
      "learning_rate": 0.00018582431990993151,
      "loss": 0.4867,
      "step": 279
    },
    {
      "epoch": 0.17743979721166034,
      "grad_norm": 0.04952229931950569,
      "learning_rate": 0.00018572131601106654,
      "loss": 0.4362,
      "step": 280
    },
    {
      "epoch": 0.17807351077313055,
      "grad_norm": 0.061900023370981216,
      "learning_rate": 0.00018561796800297832,
      "loss": 0.6342,
      "step": 281
    },
    {
      "epoch": 0.17870722433460076,
      "grad_norm": 0.04405650496482849,
      "learning_rate": 0.00018551427630053463,
      "loss": 0.4612,
      "step": 282
    },
    {
      "epoch": 0.17934093789607097,
      "grad_norm": 0.5723605155944824,
      "learning_rate": 0.00018541024131998274,
      "loss": 0.4917,
      "step": 283
    },
    {
      "epoch": 0.17997465145754118,
      "grad_norm": 0.07066962867975235,
      "learning_rate": 0.0001853058634789481,
      "loss": 0.5386,
      "step": 284
    },
    {
      "epoch": 0.1806083650190114,
      "grad_norm": 0.041575830429792404,
      "learning_rate": 0.00018520114319643235,
      "loss": 0.4894,
      "step": 285
    },
    {
      "epoch": 0.18124207858048164,
      "grad_norm": 0.07731833308935165,
      "learning_rate": 0.0001850960808928119,
      "loss": 0.5382,
      "step": 286
    },
    {
      "epoch": 0.18187579214195185,
      "grad_norm": 0.05468999221920967,
      "learning_rate": 0.00018499067698983605,
      "loss": 0.4514,
      "step": 287
    },
    {
      "epoch": 0.18250950570342206,
      "grad_norm": 0.04942842200398445,
      "learning_rate": 0.00018488493191062542,
      "loss": 0.4329,
      "step": 288
    },
    {
      "epoch": 0.18314321926489227,
      "grad_norm": 0.053615666925907135,
      "learning_rate": 0.0001847788460796702,
      "loss": 0.5182,
      "step": 289
    },
    {
      "epoch": 0.18377693282636248,
      "grad_norm": 0.04232574254274368,
      "learning_rate": 0.00018467241992282843,
      "loss": 0.3108,
      "step": 290
    },
    {
      "epoch": 0.1844106463878327,
      "grad_norm": 0.04795556515455246,
      "learning_rate": 0.00018456565386732433,
      "loss": 0.383,
      "step": 291
    },
    {
      "epoch": 0.1850443599493029,
      "grad_norm": 0.053252723067998886,
      "learning_rate": 0.00018445854834174655,
      "loss": 0.4597,
      "step": 292
    },
    {
      "epoch": 0.18567807351077312,
      "grad_norm": 0.044747479259967804,
      "learning_rate": 0.00018435110377604654,
      "loss": 0.5066,
      "step": 293
    },
    {
      "epoch": 0.18631178707224336,
      "grad_norm": 0.0473531037569046,
      "learning_rate": 0.00018424332060153664,
      "loss": 0.4258,
      "step": 294
    },
    {
      "epoch": 0.18694550063371357,
      "grad_norm": 0.05739828571677208,
      "learning_rate": 0.0001841351992508885,
      "loss": 0.4498,
      "step": 295
    },
    {
      "epoch": 0.18757921419518378,
      "grad_norm": 0.0635855570435524,
      "learning_rate": 0.0001840267401581314,
      "loss": 0.5368,
      "step": 296
    },
    {
      "epoch": 0.188212927756654,
      "grad_norm": 0.05470935255289078,
      "learning_rate": 0.00018391794375865024,
      "loss": 0.5367,
      "step": 297
    },
    {
      "epoch": 0.1888466413181242,
      "grad_norm": 0.04850434139370918,
      "learning_rate": 0.00018380881048918405,
      "loss": 0.5369,
      "step": 298
    },
    {
      "epoch": 0.18948035487959441,
      "grad_norm": 0.1420743763446808,
      "learning_rate": 0.00018369934078782426,
      "loss": 0.5101,
      "step": 299
    },
    {
      "epoch": 0.19011406844106463,
      "grad_norm": 0.0749795064330101,
      "learning_rate": 0.00018358953509401262,
      "loss": 0.5756,
      "step": 300
    },
    {
      "epoch": 0.19074778200253487,
      "grad_norm": 0.05331069603562355,
      "learning_rate": 0.00018347939384853978,
      "loss": 0.5759,
      "step": 301
    },
    {
      "epoch": 0.19138149556400508,
      "grad_norm": 0.05981903895735741,
      "learning_rate": 0.00018336891749354335,
      "loss": 0.6036,
      "step": 302
    },
    {
      "epoch": 0.1920152091254753,
      "grad_norm": 0.08048289269208908,
      "learning_rate": 0.00018325810647250616,
      "loss": 0.4424,
      "step": 303
    },
    {
      "epoch": 0.1926489226869455,
      "grad_norm": 0.07861804962158203,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.5725,
      "step": 304
    },
    {
      "epoch": 0.1932826362484157,
      "grad_norm": 0.14672251045703888,
      "learning_rate": 0.0001830354822129564,
      "loss": 0.5068,
      "step": 305
    },
    {
      "epoch": 0.19391634980988592,
      "grad_norm": 0.06640765070915222,
      "learning_rate": 0.0001829236698681195,
      "loss": 0.585,
      "step": 306
    },
    {
      "epoch": 0.19455006337135614,
      "grad_norm": 0.0588274821639061,
      "learning_rate": 0.0001828115246445898,
      "loss": 0.5779,
      "step": 307
    },
    {
      "epoch": 0.19518377693282637,
      "grad_norm": 0.05600736290216446,
      "learning_rate": 0.0001826990469925494,
      "loss": 0.5216,
      "step": 308
    },
    {
      "epoch": 0.1958174904942966,
      "grad_norm": 0.052844930440187454,
      "learning_rate": 0.0001825862373635149,
      "loss": 0.5482,
      "step": 309
    },
    {
      "epoch": 0.1964512040557668,
      "grad_norm": 0.04969317838549614,
      "learning_rate": 0.0001824730962103356,
      "loss": 0.5928,
      "step": 310
    },
    {
      "epoch": 0.197084917617237,
      "grad_norm": 0.06168043613433838,
      "learning_rate": 0.00018235962398719147,
      "loss": 0.5185,
      "step": 311
    },
    {
      "epoch": 0.19771863117870722,
      "grad_norm": 0.051151130348443985,
      "learning_rate": 0.00018224582114959172,
      "loss": 0.4677,
      "step": 312
    },
    {
      "epoch": 0.19835234474017743,
      "grad_norm": 0.060467127710580826,
      "learning_rate": 0.00018213168815437255,
      "loss": 0.5566,
      "step": 313
    },
    {
      "epoch": 0.19898605830164764,
      "grad_norm": 0.043170325458049774,
      "learning_rate": 0.0001820172254596956,
      "loss": 0.489,
      "step": 314
    },
    {
      "epoch": 0.19961977186311788,
      "grad_norm": 0.06550537794828415,
      "learning_rate": 0.00018190243352504597,
      "loss": 0.5809,
      "step": 315
    },
    {
      "epoch": 0.2002534854245881,
      "grad_norm": 0.04956373944878578,
      "learning_rate": 0.00018178731281123044,
      "loss": 0.462,
      "step": 316
    },
    {
      "epoch": 0.2008871989860583,
      "grad_norm": 0.05908495932817459,
      "learning_rate": 0.00018167186378037563,
      "loss": 0.4611,
      "step": 317
    },
    {
      "epoch": 0.20152091254752852,
      "grad_norm": 0.047168437391519547,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.5283,
      "step": 318
    },
    {
      "epoch": 0.20215462610899873,
      "grad_norm": 0.04968830570578575,
      "learning_rate": 0.00018143998262264233,
      "loss": 0.4982,
      "step": 319
    },
    {
      "epoch": 0.20278833967046894,
      "grad_norm": 0.06764087826013565,
      "learning_rate": 0.00018132355142659937,
      "loss": 0.5244,
      "step": 320
    },
    {
      "epoch": 0.20342205323193915,
      "grad_norm": 0.06344570964574814,
      "learning_rate": 0.0001812067937751844,
      "loss": 0.606,
      "step": 321
    },
    {
      "epoch": 0.20405576679340937,
      "grad_norm": 0.06029113009572029,
      "learning_rate": 0.0001810897101370951,
      "loss": 0.5407,
      "step": 322
    },
    {
      "epoch": 0.2046894803548796,
      "grad_norm": 0.08346560597419739,
      "learning_rate": 0.00018097230098233785,
      "loss": 0.4814,
      "step": 323
    },
    {
      "epoch": 0.20532319391634982,
      "grad_norm": 0.04595065116882324,
      "learning_rate": 0.00018085456678222558,
      "loss": 0.471,
      "step": 324
    },
    {
      "epoch": 0.20595690747782003,
      "grad_norm": 0.4050588309764862,
      "learning_rate": 0.00018073650800937624,
      "loss": 0.4586,
      "step": 325
    },
    {
      "epoch": 0.20659062103929024,
      "grad_norm": 0.055679477751255035,
      "learning_rate": 0.00018061812513771053,
      "loss": 0.516,
      "step": 326
    },
    {
      "epoch": 0.20722433460076045,
      "grad_norm": 0.05209626257419586,
      "learning_rate": 0.00018049941864245033,
      "loss": 0.4528,
      "step": 327
    },
    {
      "epoch": 0.20785804816223066,
      "grad_norm": 0.05503727123141289,
      "learning_rate": 0.00018038038900011652,
      "loss": 0.4297,
      "step": 328
    },
    {
      "epoch": 0.20849176172370087,
      "grad_norm": 0.05453247204422951,
      "learning_rate": 0.0001802610366885271,
      "loss": 0.4731,
      "step": 329
    },
    {
      "epoch": 0.20912547528517111,
      "grad_norm": 0.05371938645839691,
      "learning_rate": 0.00018014136218679567,
      "loss": 0.569,
      "step": 330
    },
    {
      "epoch": 0.20975918884664133,
      "grad_norm": 0.05164814740419388,
      "learning_rate": 0.0001800213659753289,
      "loss": 0.4883,
      "step": 331
    },
    {
      "epoch": 0.21039290240811154,
      "grad_norm": 0.06455442309379578,
      "learning_rate": 0.00017990104853582493,
      "loss": 0.4829,
      "step": 332
    },
    {
      "epoch": 0.21102661596958175,
      "grad_norm": 0.04764432832598686,
      "learning_rate": 0.0001797804103512715,
      "loss": 0.5525,
      "step": 333
    },
    {
      "epoch": 0.21166032953105196,
      "grad_norm": 0.0578368604183197,
      "learning_rate": 0.00017965945190594388,
      "loss": 0.4824,
      "step": 334
    },
    {
      "epoch": 0.21229404309252217,
      "grad_norm": 0.05196613445878029,
      "learning_rate": 0.00017953817368540292,
      "loss": 0.5036,
      "step": 335
    },
    {
      "epoch": 0.21292775665399238,
      "grad_norm": 0.044868264347314835,
      "learning_rate": 0.00017941657617649316,
      "loss": 0.36,
      "step": 336
    },
    {
      "epoch": 0.21356147021546262,
      "grad_norm": 0.0686643123626709,
      "learning_rate": 0.00017929465986734084,
      "loss": 0.6069,
      "step": 337
    },
    {
      "epoch": 0.21419518377693283,
      "grad_norm": 0.08286602050065994,
      "learning_rate": 0.000179172425247352,
      "loss": 0.5635,
      "step": 338
    },
    {
      "epoch": 0.21482889733840305,
      "grad_norm": 0.5979371070861816,
      "learning_rate": 0.00017904987280721035,
      "loss": 0.3994,
      "step": 339
    },
    {
      "epoch": 0.21546261089987326,
      "grad_norm": 0.05577315390110016,
      "learning_rate": 0.00017892700303887558,
      "loss": 0.5699,
      "step": 340
    },
    {
      "epoch": 0.21609632446134347,
      "grad_norm": 0.06650438159704208,
      "learning_rate": 0.0001788038164355811,
      "loss": 0.5557,
      "step": 341
    },
    {
      "epoch": 0.21673003802281368,
      "grad_norm": 0.06644187867641449,
      "learning_rate": 0.00017868031349183217,
      "loss": 0.5593,
      "step": 342
    },
    {
      "epoch": 0.2173637515842839,
      "grad_norm": 0.05286836251616478,
      "learning_rate": 0.00017855649470340413,
      "loss": 0.4902,
      "step": 343
    },
    {
      "epoch": 0.21799746514575413,
      "grad_norm": 0.05314694344997406,
      "learning_rate": 0.00017843236056733992,
      "loss": 0.5036,
      "step": 344
    },
    {
      "epoch": 0.21863117870722434,
      "grad_norm": 0.0668027251958847,
      "learning_rate": 0.0001783079115819486,
      "loss": 0.6198,
      "step": 345
    },
    {
      "epoch": 0.21926489226869456,
      "grad_norm": 0.04909252002835274,
      "learning_rate": 0.000178183148246803,
      "loss": 0.4273,
      "step": 346
    },
    {
      "epoch": 0.21989860583016477,
      "grad_norm": 0.053546786308288574,
      "learning_rate": 0.00017805807106273787,
      "loss": 0.5077,
      "step": 347
    },
    {
      "epoch": 0.22053231939163498,
      "grad_norm": 0.0647466629743576,
      "learning_rate": 0.00017793268053184786,
      "loss": 0.5262,
      "step": 348
    },
    {
      "epoch": 0.2211660329531052,
      "grad_norm": 0.05518212169408798,
      "learning_rate": 0.00017780697715748546,
      "loss": 0.5621,
      "step": 349
    },
    {
      "epoch": 0.2217997465145754,
      "grad_norm": 0.0661974772810936,
      "learning_rate": 0.00017768096144425902,
      "loss": 0.5727,
      "step": 350
    },
    {
      "epoch": 0.2224334600760456,
      "grad_norm": 0.09333747625350952,
      "learning_rate": 0.00017755463389803065,
      "loss": 0.4891,
      "step": 351
    },
    {
      "epoch": 0.22306717363751585,
      "grad_norm": 0.04791216179728508,
      "learning_rate": 0.0001774279950259143,
      "loss": 0.5569,
      "step": 352
    },
    {
      "epoch": 0.22370088719898606,
      "grad_norm": 0.05712969973683357,
      "learning_rate": 0.0001773010453362737,
      "loss": 0.5433,
      "step": 353
    },
    {
      "epoch": 0.22433460076045628,
      "grad_norm": 0.05735623091459274,
      "learning_rate": 0.00017717378533872017,
      "loss": 0.5702,
      "step": 354
    },
    {
      "epoch": 0.2249683143219265,
      "grad_norm": 0.05040268227458,
      "learning_rate": 0.00017704621554411084,
      "loss": 0.4964,
      "step": 355
    },
    {
      "epoch": 0.2256020278833967,
      "grad_norm": 0.04687810316681862,
      "learning_rate": 0.00017691833646454628,
      "loss": 0.5242,
      "step": 356
    },
    {
      "epoch": 0.2262357414448669,
      "grad_norm": 0.051406193524599075,
      "learning_rate": 0.00017679014861336878,
      "loss": 0.5146,
      "step": 357
    },
    {
      "epoch": 0.22686945500633712,
      "grad_norm": 0.04884679988026619,
      "learning_rate": 0.00017666165250516006,
      "loss": 0.4825,
      "step": 358
    },
    {
      "epoch": 0.22750316856780736,
      "grad_norm": 0.053725842386484146,
      "learning_rate": 0.0001765328486557392,
      "loss": 0.4932,
      "step": 359
    },
    {
      "epoch": 0.22813688212927757,
      "grad_norm": 0.06212908402085304,
      "learning_rate": 0.00017640373758216077,
      "loss": 0.506,
      "step": 360
    },
    {
      "epoch": 0.22877059569074779,
      "grad_norm": 0.05059286579489708,
      "learning_rate": 0.0001762743198027125,
      "loss": 0.4719,
      "step": 361
    },
    {
      "epoch": 0.229404309252218,
      "grad_norm": 0.04520050436258316,
      "learning_rate": 0.00017614459583691346,
      "loss": 0.4553,
      "step": 362
    },
    {
      "epoch": 0.2300380228136882,
      "grad_norm": 0.05503036454319954,
      "learning_rate": 0.0001760145662055117,
      "loss": 0.4706,
      "step": 363
    },
    {
      "epoch": 0.23067173637515842,
      "grad_norm": 0.046107854694128036,
      "learning_rate": 0.00017588423143048235,
      "loss": 0.4177,
      "step": 364
    },
    {
      "epoch": 0.23130544993662863,
      "grad_norm": 0.12301266193389893,
      "learning_rate": 0.0001757535920350255,
      "loss": 0.5922,
      "step": 365
    },
    {
      "epoch": 0.23193916349809887,
      "grad_norm": 1.179470419883728,
      "learning_rate": 0.00017562264854356405,
      "loss": 0.5123,
      "step": 366
    },
    {
      "epoch": 0.23257287705956908,
      "grad_norm": 0.11167129874229431,
      "learning_rate": 0.0001754914014817416,
      "loss": 0.3884,
      "step": 367
    },
    {
      "epoch": 0.2332065906210393,
      "grad_norm": 0.055067550390958786,
      "learning_rate": 0.00017535985137642044,
      "loss": 0.4544,
      "step": 368
    },
    {
      "epoch": 0.2338403041825095,
      "grad_norm": 0.07947530597448349,
      "learning_rate": 0.0001752279987556792,
      "loss": 0.6575,
      "step": 369
    },
    {
      "epoch": 0.23447401774397972,
      "grad_norm": 0.10236025601625443,
      "learning_rate": 0.00017509584414881113,
      "loss": 0.5334,
      "step": 370
    },
    {
      "epoch": 0.23510773130544993,
      "grad_norm": 0.12996040284633636,
      "learning_rate": 0.00017496338808632155,
      "loss": 0.3897,
      "step": 371
    },
    {
      "epoch": 0.23574144486692014,
      "grad_norm": 0.07005209475755692,
      "learning_rate": 0.00017483063109992596,
      "loss": 0.5077,
      "step": 372
    },
    {
      "epoch": 0.23637515842839038,
      "grad_norm": 0.04446430131793022,
      "learning_rate": 0.00017469757372254785,
      "loss": 0.4467,
      "step": 373
    },
    {
      "epoch": 0.2370088719898606,
      "grad_norm": 6.105027198791504,
      "learning_rate": 0.00017456421648831655,
      "loss": 1.722,
      "step": 374
    },
    {
      "epoch": 0.2376425855513308,
      "grad_norm": 0.07488813251256943,
      "learning_rate": 0.0001744305599325652,
      "loss": 0.7018,
      "step": 375
    },
    {
      "epoch": 0.23827629911280102,
      "grad_norm": 0.05676595866680145,
      "learning_rate": 0.00017429660459182834,
      "loss": 0.4865,
      "step": 376
    },
    {
      "epoch": 0.23891001267427123,
      "grad_norm": 0.058106616139411926,
      "learning_rate": 0.00017416235100384007,
      "loss": 0.4453,
      "step": 377
    },
    {
      "epoch": 0.23954372623574144,
      "grad_norm": 0.4252207577228546,
      "learning_rate": 0.00017402779970753155,
      "loss": 3.008,
      "step": 378
    },
    {
      "epoch": 0.24017743979721165,
      "grad_norm": 0.24036817252635956,
      "learning_rate": 0.00017389295124302923,
      "loss": 0.7246,
      "step": 379
    },
    {
      "epoch": 0.24081115335868186,
      "grad_norm": 4.316144943237305,
      "learning_rate": 0.00017375780615165235,
      "loss": 0.664,
      "step": 380
    },
    {
      "epoch": 0.2414448669201521,
      "grad_norm": 6.4877166748046875,
      "learning_rate": 0.00017362236497591094,
      "loss": 0.487,
      "step": 381
    },
    {
      "epoch": 0.2420785804816223,
      "grad_norm": 0.12358918786048889,
      "learning_rate": 0.00017348662825950357,
      "loss": 0.4839,
      "step": 382
    },
    {
      "epoch": 0.24271229404309252,
      "grad_norm": 0.7211472988128662,
      "learning_rate": 0.0001733505965473152,
      "loss": 0.6351,
      "step": 383
    },
    {
      "epoch": 0.24334600760456274,
      "grad_norm": 0.10177785158157349,
      "learning_rate": 0.00017321427038541494,
      "loss": 0.6043,
      "step": 384
    },
    {
      "epoch": 0.24397972116603295,
      "grad_norm": 0.054658226668834686,
      "learning_rate": 0.00017307765032105406,
      "loss": 0.473,
      "step": 385
    },
    {
      "epoch": 0.24461343472750316,
      "grad_norm": 0.10075858235359192,
      "learning_rate": 0.00017294073690266344,
      "loss": 0.4892,
      "step": 386
    },
    {
      "epoch": 0.24524714828897337,
      "grad_norm": 0.06497970223426819,
      "learning_rate": 0.00017280353067985167,
      "loss": 0.4986,
      "step": 387
    },
    {
      "epoch": 0.2458808618504436,
      "grad_norm": 0.7542481422424316,
      "learning_rate": 0.0001726660322034027,
      "loss": 0.5513,
      "step": 388
    },
    {
      "epoch": 0.24651457541191382,
      "grad_norm": 0.08190987259149551,
      "learning_rate": 0.00017252824202527376,
      "loss": 0.5077,
      "step": 389
    },
    {
      "epoch": 0.24714828897338403,
      "grad_norm": 0.08874624967575073,
      "learning_rate": 0.0001723901606985929,
      "loss": 0.3973,
      "step": 390
    },
    {
      "epoch": 0.24778200253485425,
      "grad_norm": 0.32968223094940186,
      "learning_rate": 0.00017225178877765704,
      "loss": 0.4411,
      "step": 391
    },
    {
      "epoch": 0.24841571609632446,
      "grad_norm": 0.39434677362442017,
      "learning_rate": 0.00017211312681792958,
      "loss": 0.5201,
      "step": 392
    },
    {
      "epoch": 0.24904942965779467,
      "grad_norm": 0.11154969036579132,
      "learning_rate": 0.00017197417537603827,
      "loss": 0.6205,
      "step": 393
    },
    {
      "epoch": 0.24968314321926488,
      "grad_norm": 0.07316391915082932,
      "learning_rate": 0.00017183493500977278,
      "loss": 0.5129,
      "step": 394
    },
    {
      "epoch": 0.2503168567807351,
      "grad_norm": 0.08883780986070633,
      "learning_rate": 0.00017169540627808274,
      "loss": 0.5036,
      "step": 395
    },
    {
      "epoch": 0.2509505703422053,
      "grad_norm": 0.07377318292856216,
      "learning_rate": 0.00017155558974107536,
      "loss": 0.591,
      "step": 396
    },
    {
      "epoch": 0.25158428390367554,
      "grad_norm": 0.064984992146492,
      "learning_rate": 0.00017141548596001305,
      "loss": 0.645,
      "step": 397
    },
    {
      "epoch": 0.2522179974651457,
      "grad_norm": 0.07279626280069351,
      "learning_rate": 0.00017127509549731148,
      "loss": 0.5108,
      "step": 398
    },
    {
      "epoch": 0.25285171102661597,
      "grad_norm": 0.06948740035295486,
      "learning_rate": 0.000171134418916537,
      "loss": 0.4959,
      "step": 399
    },
    {
      "epoch": 0.2534854245880862,
      "grad_norm": 1.0025055408477783,
      "learning_rate": 0.00017099345678240452,
      "loss": 0.5248,
      "step": 400
    },
    {
      "epoch": 0.2541191381495564,
      "grad_norm": 0.34188470244407654,
      "learning_rate": 0.00017085220966077538,
      "loss": 0.5588,
      "step": 401
    },
    {
      "epoch": 0.25475285171102663,
      "grad_norm": 0.04984923452138901,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.4033,
      "step": 402
    },
    {
      "epoch": 0.2553865652724968,
      "grad_norm": 0.05613204464316368,
      "learning_rate": 0.0001705688627241897,
      "loss": 0.5774,
      "step": 403
    },
    {
      "epoch": 0.25602027883396705,
      "grad_norm": 0.058507829904556274,
      "learning_rate": 0.0001704267640466667,
      "loss": 0.52,
      "step": 404
    },
    {
      "epoch": 0.25665399239543724,
      "grad_norm": 0.23744581639766693,
      "learning_rate": 0.00017028438265650933,
      "loss": 0.6028,
      "step": 405
    },
    {
      "epoch": 0.2572877059569075,
      "grad_norm": 0.11817914992570877,
      "learning_rate": 0.00017014171912527616,
      "loss": 0.5416,
      "step": 406
    },
    {
      "epoch": 0.2579214195183777,
      "grad_norm": 0.29011303186416626,
      "learning_rate": 0.00016999877402565833,
      "loss": 0.4381,
      "step": 407
    },
    {
      "epoch": 0.2585551330798479,
      "grad_norm": 0.06895189732313156,
      "learning_rate": 0.00016985554793147727,
      "loss": 0.5046,
      "step": 408
    },
    {
      "epoch": 0.25918884664131814,
      "grad_norm": 0.059166181832551956,
      "learning_rate": 0.00016971204141768233,
      "loss": 0.582,
      "step": 409
    },
    {
      "epoch": 0.2598225602027883,
      "grad_norm": 0.09994165599346161,
      "learning_rate": 0.00016956825506034867,
      "loss": 0.6042,
      "step": 410
    },
    {
      "epoch": 0.26045627376425856,
      "grad_norm": 0.09195294976234436,
      "learning_rate": 0.00016942418943667468,
      "loss": 0.577,
      "step": 411
    },
    {
      "epoch": 0.26108998732572875,
      "grad_norm": 0.08966407924890518,
      "learning_rate": 0.00016927984512497992,
      "loss": 0.5795,
      "step": 412
    },
    {
      "epoch": 0.261723700887199,
      "grad_norm": 0.08420640975236893,
      "learning_rate": 0.00016913522270470263,
      "loss": 0.4446,
      "step": 413
    },
    {
      "epoch": 0.2623574144486692,
      "grad_norm": 0.05902143940329552,
      "learning_rate": 0.0001689903227563975,
      "loss": 0.4458,
      "step": 414
    },
    {
      "epoch": 0.2629911280101394,
      "grad_norm": 0.046236153692007065,
      "learning_rate": 0.0001688451458617332,
      "loss": 0.3762,
      "step": 415
    },
    {
      "epoch": 0.26362484157160965,
      "grad_norm": 0.10383841395378113,
      "learning_rate": 0.00016869969260349018,
      "loss": 0.6076,
      "step": 416
    },
    {
      "epoch": 0.26425855513307983,
      "grad_norm": 0.059753723442554474,
      "learning_rate": 0.00016855396356555834,
      "loss": 0.4116,
      "step": 417
    },
    {
      "epoch": 0.26489226869455007,
      "grad_norm": 0.05825261399149895,
      "learning_rate": 0.00016840795933293463,
      "loss": 0.5377,
      "step": 418
    },
    {
      "epoch": 0.26552598225602025,
      "grad_norm": 0.07149126380681992,
      "learning_rate": 0.00016826168049172062,
      "loss": 0.5946,
      "step": 419
    },
    {
      "epoch": 0.2661596958174905,
      "grad_norm": 0.0636037141084671,
      "learning_rate": 0.00016811512762912034,
      "loss": 0.4232,
      "step": 420
    },
    {
      "epoch": 0.26679340937896073,
      "grad_norm": 0.06662221997976303,
      "learning_rate": 0.00016796830133343775,
      "loss": 0.5406,
      "step": 421
    },
    {
      "epoch": 0.2674271229404309,
      "grad_norm": 0.058340173214673996,
      "learning_rate": 0.00016782120219407452,
      "loss": 0.5402,
      "step": 422
    },
    {
      "epoch": 0.26806083650190116,
      "grad_norm": 0.054275717586278915,
      "learning_rate": 0.00016767383080152742,
      "loss": 0.5215,
      "step": 423
    },
    {
      "epoch": 0.26869455006337134,
      "grad_norm": 0.055525969713926315,
      "learning_rate": 0.00016752618774738639,
      "loss": 0.5743,
      "step": 424
    },
    {
      "epoch": 0.2693282636248416,
      "grad_norm": 0.05762525647878647,
      "learning_rate": 0.00016737827362433164,
      "loss": 0.5806,
      "step": 425
    },
    {
      "epoch": 0.26996197718631176,
      "grad_norm": 0.059116896241903305,
      "learning_rate": 0.0001672300890261317,
      "loss": 0.4828,
      "step": 426
    },
    {
      "epoch": 0.270595690747782,
      "grad_norm": 0.046420734375715256,
      "learning_rate": 0.00016708163454764075,
      "loss": 0.4509,
      "step": 427
    },
    {
      "epoch": 0.27122940430925224,
      "grad_norm": 0.11202160269021988,
      "learning_rate": 0.00016693291078479638,
      "loss": 0.5139,
      "step": 428
    },
    {
      "epoch": 0.2718631178707224,
      "grad_norm": 0.08383259177207947,
      "learning_rate": 0.00016678391833461722,
      "loss": 0.7026,
      "step": 429
    },
    {
      "epoch": 0.27249683143219267,
      "grad_norm": 0.058648403733968735,
      "learning_rate": 0.0001666346577952004,
      "loss": 0.4704,
      "step": 430
    },
    {
      "epoch": 0.27313054499366285,
      "grad_norm": 0.08609268069267273,
      "learning_rate": 0.0001664851297657193,
      "loss": 0.5186,
      "step": 431
    },
    {
      "epoch": 0.2737642585551331,
      "grad_norm": 0.10570003092288971,
      "learning_rate": 0.00016633533484642103,
      "loss": 0.4615,
      "step": 432
    },
    {
      "epoch": 0.2743979721166033,
      "grad_norm": 0.09764793515205383,
      "learning_rate": 0.00016618527363862408,
      "loss": 0.4519,
      "step": 433
    },
    {
      "epoch": 0.2750316856780735,
      "grad_norm": 0.08797989040613174,
      "learning_rate": 0.00016603494674471593,
      "loss": 0.6139,
      "step": 434
    },
    {
      "epoch": 0.27566539923954375,
      "grad_norm": 0.0714520812034607,
      "learning_rate": 0.0001658843547681506,
      "loss": 0.5027,
      "step": 435
    },
    {
      "epoch": 0.27629911280101394,
      "grad_norm": 0.08733757585287094,
      "learning_rate": 0.00016573349831344616,
      "loss": 0.4582,
      "step": 436
    },
    {
      "epoch": 0.2769328263624842,
      "grad_norm": 0.0712830200791359,
      "learning_rate": 0.00016558237798618245,
      "loss": 0.4336,
      "step": 437
    },
    {
      "epoch": 0.27756653992395436,
      "grad_norm": 0.06345337629318237,
      "learning_rate": 0.00016543099439299844,
      "loss": 0.4587,
      "step": 438
    },
    {
      "epoch": 0.2782002534854246,
      "grad_norm": 0.06224706023931503,
      "learning_rate": 0.0001652793481415901,
      "loss": 0.5171,
      "step": 439
    },
    {
      "epoch": 0.2788339670468948,
      "grad_norm": 0.0549205057322979,
      "learning_rate": 0.00016512743984070769,
      "loss": 0.5189,
      "step": 440
    },
    {
      "epoch": 0.279467680608365,
      "grad_norm": 0.07211892306804657,
      "learning_rate": 0.00016497527010015336,
      "loss": 0.6118,
      "step": 441
    },
    {
      "epoch": 0.28010139416983526,
      "grad_norm": 0.05902037024497986,
      "learning_rate": 0.00016482283953077887,
      "loss": 0.5376,
      "step": 442
    },
    {
      "epoch": 0.28073510773130544,
      "grad_norm": 0.04935478791594505,
      "learning_rate": 0.00016467014874448288,
      "loss": 0.5468,
      "step": 443
    },
    {
      "epoch": 0.2813688212927757,
      "grad_norm": 0.08219460397958755,
      "learning_rate": 0.00016451719835420877,
      "loss": 0.5723,
      "step": 444
    },
    {
      "epoch": 0.28200253485424587,
      "grad_norm": 0.08607888221740723,
      "learning_rate": 0.000164363988973942,
      "loss": 0.4821,
      "step": 445
    },
    {
      "epoch": 0.2826362484157161,
      "grad_norm": 0.05368666350841522,
      "learning_rate": 0.00016421052121870755,
      "loss": 0.4759,
      "step": 446
    },
    {
      "epoch": 0.2832699619771863,
      "grad_norm": 0.09421613812446594,
      "learning_rate": 0.00016405679570456782,
      "loss": 0.4634,
      "step": 447
    },
    {
      "epoch": 0.28390367553865653,
      "grad_norm": 0.06585177779197693,
      "learning_rate": 0.0001639028130486198,
      "loss": 0.5049,
      "step": 448
    },
    {
      "epoch": 0.28453738910012677,
      "grad_norm": 0.07445032149553299,
      "learning_rate": 0.00016374857386899268,
      "loss": 0.6255,
      "step": 449
    },
    {
      "epoch": 0.28517110266159695,
      "grad_norm": 0.05892190709710121,
      "learning_rate": 0.00016359407878484552,
      "loss": 0.5035,
      "step": 450
    },
    {
      "epoch": 0.2858048162230672,
      "grad_norm": 0.08238600939512253,
      "learning_rate": 0.00016343932841636456,
      "loss": 0.4818,
      "step": 451
    },
    {
      "epoch": 0.2864385297845374,
      "grad_norm": 0.0664915144443512,
      "learning_rate": 0.00016328432338476084,
      "loss": 0.4375,
      "step": 452
    },
    {
      "epoch": 0.2870722433460076,
      "grad_norm": 0.04862099885940552,
      "learning_rate": 0.00016312906431226773,
      "loss": 0.4138,
      "step": 453
    },
    {
      "epoch": 0.2877059569074778,
      "grad_norm": 0.04187007248401642,
      "learning_rate": 0.00016297355182213837,
      "loss": 0.3836,
      "step": 454
    },
    {
      "epoch": 0.28833967046894804,
      "grad_norm": 0.05451095104217529,
      "learning_rate": 0.00016281778653864316,
      "loss": 0.4451,
      "step": 455
    },
    {
      "epoch": 0.2889733840304182,
      "grad_norm": 0.061764512211084366,
      "learning_rate": 0.0001626617690870673,
      "loss": 0.6315,
      "step": 456
    },
    {
      "epoch": 0.28960709759188846,
      "grad_norm": 0.05365981534123421,
      "learning_rate": 0.0001625055000937083,
      "loss": 0.4399,
      "step": 457
    },
    {
      "epoch": 0.2902408111533587,
      "grad_norm": 0.10771326720714569,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.5229,
      "step": 458
    },
    {
      "epoch": 0.2908745247148289,
      "grad_norm": 0.05859148129820824,
      "learning_rate": 0.000162192209991877,
      "loss": 0.4254,
      "step": 459
    },
    {
      "epoch": 0.2915082382762991,
      "grad_norm": 0.08183909952640533,
      "learning_rate": 0.00016203519014103837,
      "loss": 0.3658,
      "step": 460
    },
    {
      "epoch": 0.2921419518377693,
      "grad_norm": 0.04404648020863533,
      "learning_rate": 0.00016187792126367886,
      "loss": 0.4138,
      "step": 461
    },
    {
      "epoch": 0.29277566539923955,
      "grad_norm": 0.056379418820142746,
      "learning_rate": 0.00016172040399111957,
      "loss": 0.4781,
      "step": 462
    },
    {
      "epoch": 0.29340937896070973,
      "grad_norm": 0.0440094955265522,
      "learning_rate": 0.00016156263895567867,
      "loss": 0.4623,
      "step": 463
    },
    {
      "epoch": 0.29404309252217997,
      "grad_norm": 0.055651161819696426,
      "learning_rate": 0.00016140462679066885,
      "loss": 0.5002,
      "step": 464
    },
    {
      "epoch": 0.2946768060836502,
      "grad_norm": 0.09338720887899399,
      "learning_rate": 0.00016124636813039502,
      "loss": 0.5199,
      "step": 465
    },
    {
      "epoch": 0.2953105196451204,
      "grad_norm": 0.07024485617876053,
      "learning_rate": 0.00016108786361015143,
      "loss": 0.5378,
      "step": 466
    },
    {
      "epoch": 0.29594423320659063,
      "grad_norm": 0.05211356282234192,
      "learning_rate": 0.00016092911386621938,
      "loss": 0.5895,
      "step": 467
    },
    {
      "epoch": 0.2965779467680608,
      "grad_norm": 0.05571569502353668,
      "learning_rate": 0.00016077011953586452,
      "loss": 0.4952,
      "step": 468
    },
    {
      "epoch": 0.29721166032953106,
      "grad_norm": 0.07663686573505402,
      "learning_rate": 0.00016061088125733433,
      "loss": 0.5341,
      "step": 469
    },
    {
      "epoch": 0.29784537389100124,
      "grad_norm": 0.04910871386528015,
      "learning_rate": 0.0001604513996698556,
      "loss": 0.445,
      "step": 470
    },
    {
      "epoch": 0.2984790874524715,
      "grad_norm": 0.07365076243877411,
      "learning_rate": 0.0001602916754136318,
      "loss": 0.5364,
      "step": 471
    },
    {
      "epoch": 0.2991128010139417,
      "grad_norm": 0.08367875218391418,
      "learning_rate": 0.00016013170912984058,
      "loss": 0.5709,
      "step": 472
    },
    {
      "epoch": 0.2997465145754119,
      "grad_norm": 0.06659605354070663,
      "learning_rate": 0.00015997150146063115,
      "loss": 0.5351,
      "step": 473
    },
    {
      "epoch": 0.30038022813688214,
      "grad_norm": 0.05647695064544678,
      "learning_rate": 0.00015981105304912162,
      "loss": 0.4103,
      "step": 474
    }
  ],
  "logging_steps": 1,
  "max_steps": 1578,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 158,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.515739834294731e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}