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

关于优化器的问题 #7

Open
chenzean opened this issue Aug 7, 2024 · 1 comment
Open

关于优化器的问题 #7

chenzean opened this issue Aug 7, 2024 · 1 comment

Comments

@chenzean
Copy link

chenzean commented Aug 7, 2024

作者,你好!
我自己在使用RWKV模块的时候,使用torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.n_steps, gamma=args.gamma),在学习率更新后提升很小。我看您论文中是使用CosineAnnealingLR(optimizer_G, total_iteration, eta_min=1.0e-6),我想问一下total_iteration和总样本数有关吗?在你的任务中总样本数是多少呢?
谢谢!!!

@Yaziwel
Copy link
Owner

Yaziwel commented Aug 13, 2024

作者,你好! 我自己在使用RWKV模块的时候,使用torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.n_steps, gamma=args.gamma),在学习率更新后提升很小。我看您论文中是使用CosineAnnealingLR(optimizer_G, total_iteration, eta_min=1.0e-6),我想问一下total_iteration和总样本数有关吗?在你的任务中总样本数是多少呢? 谢谢!!!

total iteration是模型更新的次数,与样本数有关,我是通过观察验证集效果来决定的。

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