Training reproduce
ChaoGaoUCR opened this issue · 2 comments
ChaoGaoUCR commented
HZQ950419 commented
Hi,
Did you resume from previous epoch checkpoints? If so, please ensure every epoch is training from scratch. If not, you can set a random seed to strengthen the result reproducibility. Could you report the results you got? I'd like to know how the results vary. Thanks!
ChaoGaoUCR commented
Dear,
Thanks, it's my fault, I set the batch size too big(512),
I fixed it with batch size 16, now it works perfectly.
Best