Open sgbaird opened 1 year ago
For me to address this error without forcing torch < 2.0, I will need to adjust CrabNet to use SWA from the official PyTorch implementation rather than the code that Anthony or Kaai copied (probably from a blog) when developing CrabNet.
Aside: I'm not sure how this will affect hyperparameters in the context of matsci-opt-benchmarks and crabnet-hyperparameter.
SWA
class)Maybe Lamb
is from https://github.com/cybertronai/pytorch-lamb/blob/master/pytorch_lamb/lamb.py?
Maybe Lookahead
is from https://github.com/lonePatient/lookahead_pytorch/blob/master/optimizer.py?
... or at least a double check. This might not be comprehensive, but it's a rough idea.
cc @anthony-wang @Kaaiian
What version of pytorch was usually used?
Probably just the latest version before 2.0. You shouldn't have to do anything fancy when you're installing locally on your computer, since it's already written into the latest requirements.
From https://github.com/sparks-baird/CrabNet/discussions/73#discussioncomment-7437336 by @DavidSiretMarques
I'm using pytorch for other things too, so that isn't an option...
That will make things tough. While not ideal, have you tried forcing installation of PyTorch < 2.0 and seeing if that breaks things in your other code?
Do you know the cause of the problem? I've dedicated some time to this, but only enough to identify the places that require refactoring and some potential solutions.
It was weird that in my old mac computer it worked and in my newer windows computer didn't..., they should have the exact same env with the same libraries... That's pretty interesting. I'm not sure why that would happen, though.
https://github.com/sparks-baird/matsci-opt-benchmarks/actions/runs/5193086890/jobs/9363184385