require'nn'require'optim'require'nnlr'--Networklocalnet=nn.Sequential()---This layer is locked down. No learning happens---Conv 1net:add(nn.SpatialConvolution(1,32,5,5,1,1,2,2) :learningRate('weight',0) :learningRate('bias',0) :weightDecay('weight',0) :weightDecay('bias',0) )...
(0.9,0.98)"--lr 0.0005\--lr-scheduler inverse_sqrt --stop-min-lr 1e-09 --warmup-updates 10000 --warmup-init-lr 1e-07 --apply-bert-init --weight-decay 0.01 \ --fp16 --clip-norm 2.0 --max-update 300000 --task translation_glat --criterion glat_loss --arch glat_sd --noise ...