New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Transformer training needs more improvements to catch up to SOTA #28

Open

eelcovdw opened this issue Feb 12, 2021 · 0 comments

Collaborator

eelcovdw commented Feb 12, 2021

Transformer training still needs some improvements:

Naom training schedule does not work great. Fairseq seems to have another schedule that works better (sqrt)
Batching based on number of tokens instead of number of sentences would let us use larger batch sizes on average
Possibly another optimizer than Adam.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment