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.

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

[KLUE-STS] MSE loss를 사용한 학습방법이 궁금합니다. #47

Open
dongju923 opened this issue Dec 19, 2024 · 1 comment
Open
Assignees
Labels

Comments

@dongju923
Copy link

Description

안녕하세요. 데이터셋 공유에 정말 감사드립니다.
논문에서 "The model is thus trained to map from the final hidden state of [CLS] to a real number, by minimizing the mean squared error (MSE)." 이렇게 나와 있는데, [CLS] 에 대한 hidden_state를 뽑아도 (batch_size, embedding_dim) 크기가 반환될텐데, labels랑 차원을 어떻게 맞추셨는지 궁금합니다. 감사합니다.

@dongju923
Copy link
Author

@DongjunLee @inmoonlight @SungjoonPark 시간 나실때 답변 부탁드립니다 ㅠㅠ

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

5 participants