-
Notifications
You must be signed in to change notification settings - Fork 5
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
added architecture #374
added architecture #374
Conversation
Hi @PicoCentauri @frostedoyster @ppegolo, so the problem of this PR was, as said in #372, that the So I changed the The code passes all tests. I hope this was the only place where the absence of The new docs for the default hypers are shown in the attached file. I also corrected some typos when I saw them. |
So my comment in the issue was correct and this is more of a user experience issue. We could improve the documentation or write a comment at the top of each of these files, but I also see the point for providing the I would leave the decision to @PicoCentauri who is the designer of this code |
Yes, I probably did not understand what you meant in the issue and I did not know it was used in the code. Anyway what ever you want to do is not much work |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's okay for me. This helps the usability and is just a minor change in one function.
""" | ||
check_architecture_name(name) | ||
default_hypers = OmegaConf.load(get_architecture_path(name) / "default-hypers.yaml") | ||
return OmegaConf.to_container(default_hypers) | ||
return OmegaConf.to_container(default_hypers)["architecture"] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would maybe add a comment here that for a better UX we store the default-hypers.yaml
of each architecture indented by one level (architecture:
).
USE_SHIFT_AGNOSTIC_LOSS: False # only used when fitting general target. Primary use case: EDOS | ||
ENERGIES_LOSS: per_structure # per_structure or per_atom | ||
CHECKPOINT_INTERVAL: 100 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe add a new line just for my personal linter peace
well, I have to say I was very good at implementing the suggestions 😂 |
hahaha |
fixes #372
📚 Documentation preview 📚: https://metatrain--374.org.readthedocs.build/en/374/