Files
nyaya-3b-v3/training/figures/training_v3.csv

32 lines
3.1 KiB
CSV
Raw Normal View History

step,epoch,loss,learning_rate,grad_norm,mean_token_accuracy
10,0.06046863189720333,1.4868995666503906,9e-05,0.2206401377916336,0.6501498550176621
20,0.12093726379440665,1.280113124847412,9.980736554638366e-05,0.20303168892860413,0.6815041944384574
30,0.18140589569160998,1.1442659378051758,9.914337409040418e-05,0.12361272424459457,0.7108227916061878
40,0.2418745275888133,1.0783726692199707,9.801196139334195e-05,0.13824407756328583,0.7233529925346375
50,0.30234315948601664,1.0328060150146485,9.642388874981347e-05,0.1718689501285553,0.7331555418670177
60,0.36281179138321995,0.9452245712280274,9.439426092011875e-05,0.19833926856517792,0.7508241727948188
70,0.42328042328042326,0.8957448959350586,9.194238246314599e-05,0.27138301730155945,0.763477711379528
80,0.4837490551776266,0.8388309478759766,8.90915741234015e-05,0.8669945597648621,0.776527363806963
90,0.54421768707483,0.7785130500793457,8.586895101857747e-05,0.3251343071460724,0.7925561927258968
100,0.6046863189720333,0.7025893211364747,8.230516473739935e-05,0.45480582118034363,0.810952752828598
110,0.6651549508692366,0.6717377662658691,7.843411180075794e-05,0.3490012586116791,0.8204429857432842
120,0.7256235827664399,0.634728193283081,7.42926112590631e-05,0.4181080162525177,0.8306220307946205
130,0.7860922146636432,0.5837386608123779,6.992005449231208e-05,0.40689781308174133,0.843410138040781
140,0.8465608465608465,0.5329185962677002,6.535803054375738e-05,0.4665887653827667,0.8579231850802899
150,0.9070294784580499,0.5083013534545898,6.064993055076698e-05,0.4626559019088745,0.8642070218920708
160,0.9674981103552532,0.489164400100708,5.5840535035285025e-05,0.5883871912956238,0.8689255759119987
170,1.0241874527588812,0.43776092529296873,5.0975587979329734e-05,0.6238144040107727,0.8809238640467326
180,1.0846560846560847,0.4174932956695557,4.610136173665751e-05,0.4284566640853882,0.888404282182455
190,1.145124716553288,0.39289538860321044,4.1264216918883656e-05,0.42329925298690796,0.8944049634039402
200,1.2055933484504913,0.39194531440734864,3.651016144214878e-05,0.45279642939567566,0.8959574572741985
210,1.2660619803476947,0.3841248989105225,3.188441292840587e-05,0.4972575604915619,0.896124105155468
220,1.3265306122448979,0.35218961238861085,2.743096862349427e-05,0.5121544003486633,0.9058273300528527
230,1.3869992441421013,0.3745258331298828,2.3192186922673186e-05,0.38717055320739746,0.9008041150867939
240,1.4474678760393047,0.3568585395812988,1.9208384483883817e-05,0.40057459473609924,0.9051908120512963
250,1.507936507936508,0.34092986583709717,1.5517452760747975e-05,0.3971737325191498,0.9089121885597706
260,1.568405139833711,0.33079631328582765,1.2154497602603703e-05,0.36223524808883667,0.9112872503697872
270,1.6288737717309147,0.3347353458404541,9.151505349477902e-06,0.3942708671092987,0.9104152075946331
280,1.689342403628118,0.34016706943511965,6.53703859789348e-06,0.35229650139808655,0.9098294205963612
290,1.7498110355253211,0.3172227621078491,4.335964531197401e-06,0.38456934690475464,0.9160888768732548
300,1.8102796674225246,0.31731643676757815,2.5692183983629713e-06,0.5015138983726501,0.9155210055410862