How to Avoid Overfitting by Applying Early-stop on Dev Set?
Open
- Dominant language
- C++
- Stars
- 28.8k
- Forks
- 8.9k
- Avg merge
- 1d 12h
- Merged PRs (30d)
- 54
Description
As the title says, how can I apply early-stop strategy on dev-set rather than train-set when training?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.