-
Notifications
You must be signed in to change notification settings - Fork 19
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
언더피팅 해결하기 #22
Comments
eubinecto
added a commit
that referenced
this issue
Jun 4, 2022
eubinecto
added a commit
that referenced
this issue
Jun 4, 2022
eubinecto
added a commit
that referenced
this issue
Jun 4, 2022
eubinecto
added a commit
that referenced
this issue
Jun 4, 2022
eubinecto
added a commit
that referenced
this issue
Jun 6, 2022
…New singleton for kor2eng-translation: translator.py/Translator
eubinecto
added a commit
that referenced
this issue
Jun 6, 2022
eubinecto
added a commit
that referenced
this issue
Jun 6, 2022
eubinecto
added a commit
that referenced
this issue
Jun 6, 2022
eubinecto
added a commit
that referenced
this issue
Jun 7, 2022
eubinecto
added a commit
that referenced
this issue
Jun 7, 2022
eubinecto
added a commit
that referenced
this issue
Jun 7, 2022
eubinecto
added a commit
that referenced
this issue
Jun 7, 2022
eubinecto
added a commit
that referenced
this issue
Jun 7, 2022
eubinecto
added a commit
that referenced
this issue
Jun 8, 2022
eubinecto
added a commit
that referenced
this issue
Jun 8, 2022
…epoch to reduce computation overhead during training
eubinecto
added a commit
that referenced
this issue
Jun 8, 2022
eubinecto
added a commit
that referenced
this issue
Jun 10, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Why?
#21 에서 학습을 진행해보았을 때, 학습데이터조차 제대로 학습을 못함 (그리고 loss가 굉장히 튄다). 하지만 아주 조그마한 데이터셋에서는 오버피팅이 되는 것을 확인했었음. 이는 그렇다면.. 가중치 capacity의 문제이거나, learning rate를 제대로 지정하지 못했거나, tokenizer의 문제, 셋 중 하나일 것이다.
How?
The text was updated successfully, but these errors were encountered: