After starting training the model,it doesn't work and only see "learning rate 0.0002000 -> 0.0002000"

[KnightWin123]

I try to start training the model but it doesn't work and stay in the same position for a long time,may you tell me the reason? My GPU is RTX5000 16G batchsize 1

[KnightWin123]

[korjmorj]

You have a UserWarning, check it! There is a little mistake in the code, you need to fork it and put lr_scheduler.step() AFTER optimizer.step()

[simon-eda]

can you please provide a description on where and how to put lr_scheduler.step() AFTER optimizer.step()?

many thanks

[ApoorvaSuresh]

@simon-eda hey, did you find out what has to be changed to make it work? Please let me know :) Thank you!

[simon-eda]

@simon-eda hey, did you find out what has to be changed to make it work? Please let me know :) Thank you!

i switched to anaconda enviroment and the issues does not come up anymore

[Marco1402]

This issue persists for me, even with anaconda environment. How about you @ApoorvaSuresh ?

@simon-eda, would you be so kind to provide details about your environment and which package versions you used?

[junyanz]

We did provide an environment.yml, which should work.