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

参数设置疑问 #2

Open

echo-valor opened this issue Dec 13, 2023 · 1 comment

echo-valor commented Dec 13, 2023

很有价值的工作，但还有两个问题想请教一下：

Q1：Weight Decay和Gradient Clip与其他开源模型似乎不一致，一般Weight Decay设置为0.01，梯度裁减设置为1，请问贵团队这样设计的理由及物理含义是什么？
Q2：贵团队有打算开源预训练数据集吗？

Thanks

Collaborator

SS-YuJJ commented Jan 19, 2024

你好，感谢提问。

Q1：我们使用的DecoupledAdamW优化器将learning rate和weight decay参数解绑了，所以weight decay需要设置更小的数值。请参考：https://github.com/mosaicml/composer/blob/dev/composer/optim/decoupled_weight_decay.py#L247

Q2：不好意思，我们目前没有打算开源训练数据集。

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