fix unnecessary eval

[Colin-Jay]

I tried to fix the issue #10, and now the code runs successfully on my local machine, though without additional validation or testing (e.g., on the QMOF dataset).

[facebook-github-bot]

Hi @Colin-Jay!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[chaitjo]

@Colin-Jay Can you describe in a bit more detail what this PR exactly does?

[Colin-Jay]

@Colin-Jay Can you describe in a bit more detail what this PR exactly does?

@chaitjo Sure! In the current code version, even if train on QM9 only (with MP20 and QMOF150's proportion explicitly set to 0), the model still attempts to validate and test them. This causes unnecessary issues and crashes the program, as described in issue #10. i attempted to fix this, and now the code runs properly on my local machine without performing any additional validation or testing.

[chaitjo]

And is your implemented fix robust to if the user only trained on MP20 or QMOF, too?

[Colin-Jay]

And is your implemented fix robust to if the user only trained on MP20 or QMOF, too?

Yes, I modified the Evaluator and val_metrics in the models module to dynamically update based on whether the proportion is greater than 0.

[chaitjo]

Will have to review in more detail in the coming days before merging. Please stay tuned.

[chaitjo]

Sorry for the delay - the fixes look mostly good to me. I still need to review it by testing if I can reproduce results on my end, after which I'd like to merge. Will keep you posted.