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

预训练阶段收敛问题 #65

Open
hanfeng0409 opened this issue Aug 28, 2024 · 2 comments
Open

预训练阶段收敛问题 #65

hanfeng0409 opened this issue Aug 28, 2024 · 2 comments

Comments

@hanfeng0409
Copy link

您好,我想请教一下,预训练阶段的loss一般会收敛到多少?我现在在自己的数据上跑预mae-b的预训练,发现loss基本在0.2左右就不再下降了。然后把重建的结果绘制在原图上,发现都比较模糊。

@XuecWu
Copy link

XuecWu commented Sep 1, 2024

@hanfeng0409 您好,请问您是在多大规模的数据集上跑了多少epoch后达到收敛呢

@hanfeng0409
Copy link
Author

@hanfeng0409 您好,请问您是在多大规模的数据集上跑了多少epoch后达到收敛呢
感谢您的回复。
大概3000个 数据上,现在是设置了1200个epoch,实际跑到了200个epoch,前30个epoch的loss很快从0.8降到了 0.2左右 后100个epoch loss在0.18附近震荡。

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