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

Fixing BERT mask size #2429

Merged
merged 2 commits into from Jan 23, 2019

Conversation

Projects
None yet
2 participants
@ethanjperez
Copy link
Contributor

commented Jan 23, 2019

Input tokens are truncated to <512 tokens long to fit into BERT. When this happens, the mask associated with that sample appears to not also be truncated. This edit is a fix for that issue, which can cause size mismatch errors downstream when the mask is used (See this issue). @joelgrus

ethanjperez and others added some commits Jan 23, 2019

Fixing BERT mask size
Input tokens are truncated to <512 tokens long to fit into BERT. When this happens, the mask associated with that sample appears to not also be truncated. This edit is a fix for that issue, which can cause size mismatch errors downstream when the mask is used.
@joelgrus
Copy link
Contributor

left a comment

looks good, thanks for catching this

@joelgrus joelgrus merged commit 585c19e into allenai:master Jan 23, 2019

3 checks passed

Pull Requests (AllenNLP Library) TeamCity build finished
Details
codecov/patch 100% of diff hit (target 90%)
Details
codecov/project 92% (+0%) compared to b7d56ae
Details
@ethanjperez

This comment has been minimized.

Copy link
Contributor Author

commented Jan 23, 2019

No problem, thanks for adding BERT :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.