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

为什么我换了学习率,最终的结果都是0呢? batch_size设大一点就OOM? #386

Open
yohowitch opened this issue May 7, 2021 · 5 comments

Comments

@yohowitch
Copy link

  1. 将原本的1e-5学习率换为0.001,之后跑出的结果全为0

  2. batch_size 设为16可以跑,设为32就会有OOM报错

@1qingqing1
Copy link

请问你的gpu显存多大呢,我的8G显存,batch_size 设为16就会有OOM报错

@S0W0H0
Copy link

S0W0H0 commented May 6, 2022

  1. 将原本的1e-5学习率换为0.001,之后跑出的结果全为0

    1. batch_size 设为16可以跑,设为32就会有OOM报错

请问这个问题解决了吗我也遇到了更换学习率的问题

@1qingqing1
Copy link

bert层学习率要设置的小一些,可以试试2e-5、3e-5、5e-5,其他层可以设置大一些1e-4、1e-3

@S0W0H0
Copy link

S0W0H0 commented May 9, 2022

请问在哪设置呢,我只在train_helper.py中找到了一个有关learn_rate参数设置的地方

@Ingrid226
Copy link

想问问这个学习率在哪里设置呢,感谢

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

4 participants