google-research / google-research/language
BERT EXTRACTION: Unable to get the result
Open
- 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
Assessment
This issue has not been assessed yet.