Skip to content
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

NSMC (Binary Classification) Data issue #2

Closed
pminhyung opened this issue Apr 27, 2022 · 3 comments · Fixed by #3
Closed

NSMC (Binary Classification) Data issue #2

pminhyung opened this issue Apr 27, 2022 · 3 comments · Fixed by #3

Comments

@pminhyung
Copy link
Collaborator

[현상]
동일한 하이퍼파라미터 사용에도, KoELECTRA-Base-v3 (monologg/KoELECTRA) 과의 NSMC Accuracy 차이 발생 (0.884, 약 2.2%)

[원인]
현재 master branch의 NSMC 데이터 (train_binary.csv, test_binary.csv) 와 실제 NSMC 밴치마크 데이터 간 차이 확인

  • 현재 NSMC 데이터 개수 : 20,000 : 2000 (train : test)
  • KoELECTRA repository의 NSMC 데이터 개수 : 150,000: 50,000 (train : test)

issue1
issue2
@DaehanKim
Copy link
Collaborator

아 어쩐지~ 데이터가 간소화된 버전이였군요

@pminhyung
Copy link
Collaborator Author

네네 대한님의 kobart 쪽도 ynat은 성능이 잘 나왔는데 nsmc 는 차이가 좀 있었던 이유가 데이터 차이 때문이 아닐까 싶습니다 ㅎㅎ

@DaehanKim
Copy link
Collaborator

예리한 분석이었습니다 👍

@pminhyung pminhyung linked a pull request Apr 27, 2022 that will close this issue
New version of NSMC data #3
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

New version of NSMC data Pseudo-Lab/nlp_open_cookbook
2 participants
@DaehanKim @pminhyung