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

Bi-LSTM+CRF model loss appears "nan" #171

Closed

TIANYUZHOU opened this issue Dec 26, 2022 · 1 comment · Fixed by #365

Labels

bug

Collaborator

TIANYUZHOU commented Dec 26, 2022

Using the CoNLL2000Chunking dataset and the Bi-LSTM+CRF model to train the Chunking task loss will appear "nan".

TIANYUZHOU changed the title ~~Bi-LSTM+CRF model loss will appear "nan"~~ Bi-LSTM+CRF model loss appears "nan"

lvyufeng added the bug label

lvyufeng linked a pull request

that will close this issue

fix crf nan problem #365

Merged

Collaborator

lvyufeng commented Mar 24, 2023

use minspore.ops.logsumexp to avoid overflow problem

lvyufeng closed this as completed

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