About nan values in result

[yjyyyyyyyuuu]

Dear developers,

I would like to ask you about the reasons why "true loss value" and "loss value after loss minim" have a large number of nan values during the training process. Does this have anything to do with the range of parameters provided or some basic parameter Settings?

Thank you for your time!

[xxlliu]

I have the same question. Have you found the answer? Also look forward to the developer's answer.

Thank you for your time!

[cagrikymk]

Sorry for the delay, I was busy with my final defense for my phd and now I have more time with development.

I have a new branch that should remedy this issue as it is better tested.

https://github.com/cagrikymk/JAX-ReaxFF/tree/jax-reaxff-v0.2

[cagrikymk]

You can rerun the training with the updated code.

However, there is a chance that your starting parameters / training data are not so compatible which might result in high loss value.