-
Notifications
You must be signed in to change notification settings - Fork 680
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
大佬好,我用两张3090去使用你所提供的那个100w的数据集训练,可是很快loss稳定在3.0就不降低了 #101
Comments
batch_size设置的128 |
我也有同样的问题,怎么解决阿? |
batch设置的是64 |
我的都已经过了好31个epoch了,从27个epoch开始 就在3左右徘徊,是不是遇到了局部最优? |
同3090我在13个epoch就开始在3降不下去了,可能数据质量不好。 |
请问你们loss到3左右降低不下去了的时候,batch_acc大概多少呢 我只有3060训练,我减少了语料 batch_size为32 训练了40的Epoch batch_acc只有0.3左右 |
请问数据集可以再分享一下吗,链接失效了,谢谢 |
大佬们 谁发一下数据集链接 作者的不可用了 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
可是很快loss稳定在3.0就不降低了,大概也就十几个epoch吧,请问最好的效果是这样吗
或者说还有没有什么训练方法可以让模型得到更好的效果呢
The text was updated successfully, but these errors were encountered: