training batch size
#3
by
yyy111
- opened
hi, thank you for your awesome work. There are some doubts about the training batch size in the paper. Does it refer to per device batch size or total batch size? And how many A100 80G are required for training？
Looking forward to your reply!
Same question. It says using 8 A100 during traininig, but not clarify the batchsize refer to.