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

distill.py结果问题 #12

Open
letiantony opened this issue Mar 16, 2021 · 2 comments
Open

distill.py结果问题 #12

letiantony opened this issue Mar 16, 2021 · 2 comments

Comments

@letiantony
Copy link

首先感谢分享代码,我看distill.py有个疑问,最后输出的准确率是dev集上的结果,而默认teach_on_dev = True,这样相当于用dev集合在训练,这会导致测试效果虚高吧?

@letiantony
Copy link
Author

我明白用的dev集进行训练的时候没有过使用golden label,但是一般在真实场景下我们无法提前知道要预测的样本,我用distill.py在测试集上评估准确率,提升非常有限,不知道是不是我哪里用错了。

@paulxu1314
Copy link

也有同样疑惑,虽然没有使用label,但却使用验证集指标来衡量模型,总觉得有点不妥

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

No branches or pull requests

2 participants