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

ZBL follow-up #355

Open
frostedoyster opened this issue Oct 9, 2024 · 2 comments · May be fixed by #427
Open

ZBL follow-up #355

frostedoyster opened this issue Oct 9, 2024 · 2 comments · May be fixed by #427
Assignees
Labels
Infrastructure: Miscellaneous General infrastructure issues Priority: Medium Important issues to address after high priority.

Comments

@frostedoyster
Copy link
Collaborator

#335 leaves a few problems open for ZBL:

  • units
  • should the composition model be fit before or after removing ZBL? At the moment, it's "before" for the native models and "after" for PET
  • the current version breaks distributed training by working on CPU (DistributedDataParallel doesn't like it)
@frostedoyster frostedoyster added Priority: Medium Important issues to address after high priority. Infrastructure: Miscellaneous General infrastructure issues labels Oct 9, 2024
@frostedoyster frostedoyster self-assigned this Oct 9, 2024
@frostedoyster
Copy link
Collaborator Author

A PR will be opened soon. Regarding the 3 points above:

  • units: it's too early to have an internal unit system in metatrain. For now, users that want ZBL will have to work with eV and A
  • the composition model will always be fitted after ZBL is removed
  • will be fixed

@frostedoyster frostedoyster linked a pull request Dec 14, 2024 that will close this issue
2 tasks
@Luthaf
Copy link
Member

Luthaf commented Dec 16, 2024

units: it's too early to have an internal unit system in metatrain. For now, users that want ZBL will have to work with eV and A

Do we send an error if the users has his dataset using different units?

Also, I don't think this would require having a full internal units systems in metatrain. Instead we could use metatensor.torch.atomistic.unit_conversion_factor("energy", "eV", "user-unit") when initializing the ZBL module to convert between the data stored in the code and what the user wants to use.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Infrastructure: Miscellaneous General infrastructure issues Priority: Medium Important issues to address after high priority.
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants