Farseer-Scaling-Law

https://farseer-scaling-law.github.io/

AI & ML interests

None defined yet.

Farseer-Scaling-Law 's models 456

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1920_ffnh5184_numh30_numl30_lr2.11e-03_bs1280_ti164237

Farseer-Scaling-Law/step2v2_0726_2049_sc_h3328_ffnh9136_numh52_numl47_lr4.29e-04_bs512_ti86316

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2176_ffnh5712_numh34_numl34_lr1.48e-03_bs1024_ti145166

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2752_ffnh7336_numh43_numl42_lr7.30e-04_bs640_ti116133

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1728_ffnh4528_numh27_numl27_lr2.70e-03_bs1280_ti164237

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2048_ffnh5448_numh32_numl32_lr1.77e-03_bs1152_ti153451

Farseer-Scaling-Law/step2v2_0726_2049_sc_h3072_ffnh8264_numh48_numl47_lr5.12e-04_bs512_ti102648

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2880_ffnh7744_numh45_numl45_lr5.50e-04_bs512_ti86316

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1600_ffnh4264_numh25_numl26_lr3.22e-03_bs1408_ti177556

Farseer-Scaling-Law/step2v2_0726_2049_sc_h960_ffnh2592_numh15_numl15_lr6.740e-03_bs688_ti108031

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2432_ffnh6488_numh38_numl38_lr1.04e-03_bs896_ti117312

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1920_ffnh5184_numh30_numl30_lr1.89e-03_bs1024_ti145166

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1792_ffnh4832_numh28_numl29_lr2.26e-03_bs1152_ti153451

Farseer-Scaling-Law/step2v2_0726_2049_sc_h3328_ffnh9136_numh52_numl47_lr1.70e-04_bs88_ti24414

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1088_ffnh2856_numh17_numl17_lr3.94e-03_bs400_ti72265

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1280_ffnh3472_numh20_numl20_lr2.33e-03_bs296_ti58065

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2560_ffnh6952_numh40_numl40_lr3.84e-04_bs160_ti37979

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1280_ffnh3472_numh20_numl20_lr1.69e-03_bs168_ti36170

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2560_ffnh6952_numh40_numl40_lr2.25e-04_bs64_ti16784

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2880_ffnh7744_numh45_numl45_lr2.18e-04_bs88_ti24414

Farseer-Scaling-Law/step2v2_0726_2049_sc_h3072_ffnh8264_numh48_numl47_lr4.28e-04_bs384_ti75276

Farseer-Scaling-Law/step2v2_0726_2049_sc_h960_ffnh2592_numh15_numl15_lr5.05e-03_bs400_ti72265

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2048_ffnh5448_numh32_numl32_lr3.66e-04_bs64_ti16784

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1600_ffnh4264_numh25_numl26_lr7.47e-04_bs88_ti24414

Farseer-Scaling-Law/step2v2_0726_2049_sc_h832_ffnh2216_numh13_numl12_lr4.54e-03_bs168_ti36170

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1472_ffnh3888_numh23_numl22_lr9.52e-04_bs88_ti24414

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1600_ffnh4264_numh25_numl26_lr6.04e-04_bs64_ti16784

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2752_ffnh7336_numh43_numl42_lr5.44e-04_bs384_ti75276

Farseer-Scaling-Law/step2v2_0726_2049_sc_h2304_ffnh6064_numh36_numl36_lr6.72e-04_bs288_ti59678

Farseer-Scaling-Law/step2v2_0726_2049_sc_h1152_ffnh3032_numh18_numl18_lr2.96e-03_bs296_ti58065