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

About the difference between val loss and test loss #11

Open
SkyKingL opened this issue Nov 21, 2024 · 4 comments
Open

About the difference between val loss and test loss #11

SkyKingL opened this issue Nov 21, 2024 · 4 comments

Comments

@SkyKingL
Copy link

Hello! I would like to ask, when I reproduced the effect on the EPF dataset, I found that the val loss and test loss were quite different. Logically, the distribution of the val dataset and the test dataset should be similar, and the loss of the two should not be so different.

image

@UP-programmer
Copy link

Hello! I would like to ask, when I reproduced the effect on the EPF dataset, I found that the val loss and test loss were quite different. Logically, the distribution of the val dataset and the test dataset should be similar, and the loss of the two should not be so different.

image

where is the log?

@SkyKingL
Copy link
Author

I included a picture of the log information in my question...

@UP-programmer
Copy link

I included a picture of the log information in my question...

Can we have a talk? I have some questions in how to run the code.

@XiiiTang
Copy link

I also noticed the same issue, the loss on the test set is much higher than on the training set. Can you tell me what the reason might be?

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

3 participants