google-research / google-research/language

BERT EXTRACTION: Unable to get the result

Open
#138 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
1.8k
Forks
362
PR merge metrics
No merged PRs in 30d

Description

Hi, when I try to implement the code of bert extraction experiment, the eval accuracy for both MNLI and SST-2 are lower than 50 percent. I doubt that the weight of the model is not updated and loss never decreases. However, I am a beginner in this field and I do not know how to get the loss after training each batch. Anyone can give a hint? Thanks a lot!!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.