Skip to content
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.

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

Embed longest sentences first to tune batch size #67

Merged
merged 1 commit into from
Jun 30, 2020

Conversation

ethanjperez
Copy link
Contributor

Just a suggestion, but it might help to process the longest texts first, in order to catch OOMs at the beginning of BERT-scoring, instead of at the end. This would help to quickly tune batch size to the largest possible value given your current hardware.

The code is otherwise pretty optimized!

Just a suggestion, but it might help to process the longest texts first, in order to catch OOMs at the beginning of BERT-scoring, instead of at the end. This would help to quickly tune batch size to the largest possible value given your current hardware.

The code is otherwise pretty optimized!
@Tiiiger Tiiiger merged commit 839f230 into Tiiiger:master Jun 30, 2020
@Tiiiger
Copy link
Owner

Tiiiger commented Jun 30, 2020

nice work! thank you!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants