nicoboss's picture
Upload folder using huggingface_hub
25b3f76 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.10012674271229405,
"eval_steps": 500,
"global_step": 158,
"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
}
],
"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": 2.1719132780982436e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}