Force loss function

[andrew_peterson]

If I'm reading the loss function code, the force residuals are being divided by the number of atoms. Since force is already a per-atom quantity, this should not be the case.

[Muammar El Khatib]

I think PR #36 should solve this.

[Muammar El Khatib]

Now that changes seem to be working, tests are broken.

[Alireza Khorshidi]

Here is a photo of our discussion today:

[andrew_peterson]

Thanks! That makes sense. But now I have another question: I can see where the code divides by the number of atoms here. But where does it divide by the number of images?

[andrew_peterson]

Nevermind -- we found it. I understand now that force_loss is the SSR and force_rmse is the RMSE, and the RMSE is only calculated within check_convergence, where the info is reported to the user.

[andrew_peterson]

Re-arrange loss function code.

Should be functionally identical, but a bit more efficient. (But probably wasn't rate-limiting.) Also makes code more logical to read in my opinion. Fixes Issue #218.

→ <<cset e5beac6ddbd4>>