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

训练dual网络,为什么loss越来越大了? #101

Open
archwolf118 opened this issue May 25, 2023 · 1 comment
Open

训练dual网络,为什么loss越来越大了? #101

archwolf118 opened this issue May 25, 2023 · 1 comment

Comments

@archwolf118
Copy link

您好!感谢rocketQA的工作,我已经成功将rocketQA应用到我们的系统中。
为了能提高rocketQA的召回率,我尝试对zh_dureader_de_v2进行finetune,使用的是repo中自带的训练集,下面是训练代码:

import rocketqa
dual_encoder = rocketqa.load_model(model="zh_dureader_de_v2", use_cuda=True, device_id=0, batch_size=4)
dual_encoder.train('./examples/data/dual.train.tsv', 20, 'de_models', save_steps=500, learning_rate=1e-5, log_folder='log_de')

我发现loss是越来越大的,如下图所示,不知道为什么?
image
谢谢!

@zhangpeng-HEBUT
Copy link

您好,请问您是用几个GPU训练的呀?

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