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

关于id_loss在训练过程中不收敛的问题 #9

Closed

Zplusdragon opened this issue Apr 4, 2023 · 1 comment

Zplusdragon commented Apr 4, 2023

您好，我按照您所提供的代码在单张3090跑了训练，但是在logging日志中发现id_loss并没有收敛，最终一直维持在7.847左右，请问这是什么原因呢？

Owner

anosorae commented Apr 4, 2023

如果你想要让id_loss继续下降，可以在这里的代码：

IRRA/solver/build.py

Line 23 in 91a6856

if "classifier" in key or "mlm_head" in key:

对classifier的学习率进行调整，如果你调大学习率的话，id_loss会下降得更快且能收敛到你想要的值，但是会对最终检索结果造成一定的影响，这需要你自己进行实验来找出更合适的学习率设置。

anosorae closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment