Better GAP logging during training

lab-cosmo / metatrain

Training and evaluating machine learning models for atomistic systems.

https://lab-cosmo.github.io/metatrain/

BSD 3-Clause "New" or "Revised" License

13 stars 3 forks source link

Better GAP logging during training #244

Closed frostedoyster closed 3 weeks ago

frostedoyster commented 3 weeks ago

We should log the different stages of fitting a GAP model (sparse points, features and kernel, solve). This is because large datasets can seemingly hang while in reality GAP is fitting fine.