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

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

Open
iniroc opened this issue Nov 26, 2022 · 8 comments

Comments

@iniroc
Copy link

iniroc commented Nov 26, 2022

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

@iniroc
Copy link
Author

iniroc commented Nov 26, 2022

batch_size设置的128

@cxhermagic
Copy link

我也有同样的问题,怎么解决阿?

@cxhermagic
Copy link

batch设置的是64

@cxhermagic
Copy link

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?

@Jehuty-ML
Copy link

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。

@Whylickspittle
Copy link

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

@Mylszd
Copy link

Mylszd commented Nov 7, 2023

请问数据集可以再分享一下吗,链接失效了,谢谢

@1dengguosong
Copy link

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
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants