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

how many train step we need #35

Open
yuxiaoleipeng opened this issue Aug 3, 2019 · 2 comments
Open

how many train step we need #35

yuxiaoleipeng opened this issue Aug 3, 2019 · 2 comments

Comments

@yuxiaoleipeng
Copy link

when i train the model, it can run, but when the step meet 200000 loss drop to 6900 and it never go down, i train it for 370000 step and it still 6900, do you meet this question before?

@wenbingz
Copy link

wenbingz commented Aug 6, 2019

I met this problem, too. Does it relate to reproducibility?

@ogroth
Copy link
Owner

ogroth commented Aug 29, 2019

As I've explained here the loss seems to plateau because of the reconstruction term having reached the perfect means and the only thing which is optimized afterwards is the KL term which is, however, of a different order of magnitude. I admit that this loss setup is suboptimal and a bit confusing, so I'm happy about any suggestions.

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