-
Notifications
You must be signed in to change notification settings - Fork 161
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
Why is my eval_accuracy very low? #6
Comments
Me too. Any advice would be appreciated. |
me too |
Me too. Does anyone find the problem? |
Me too. Can anyone answer this question? |
I got the similar result after nearly 16 hours run on GPU. |
Me too!!!!anyone can help? Thanks!!! |
我的accuracy也是0.05,有谁知道怎么解决这个问题吗?是不是代码或者计算的问题啊 |
acc的计算不适用于多标签,低也是正常的,你可以自己写一个文件用来计算precision,recall,F1值 |
嗯嗯,好的,多谢您的回复,我也正在看多标签分类的一些指标的写法,谢谢您的解答,不然感觉自己可能在这个问题上饶好久,真的的太感谢了
|
我后面又找到一个计算每个标签的acc的代码了,然后试了一下是可以的,https://www.kaggle.com/javaidnabi/toxic-comment-classification-using-bert/ 就是这个项目。 |
eval_accuracy = 0.05
eval_loss = 0.1677554
global_step = 78750
loss = 0.16775554
The text was updated successfully, but these errors were encountered: