The macOS version requirements might have something to do with the fact that it was written in SwiftUI.

Ya you got it. SwiftUI wasn't viable before Big Sur.

I'm really curious if this training process is optimized for the new 8-core neural engine on the M1 SoC. I'd like to see a comparison between the performance on M1 vs Intel macs.

I supposed this might serve as a good demonstration of how the neural engine performs?

edit: Perhaps running inference in the iOS simulator on the macs would also be a comparison point?

We're actually running a benchmark of that very thing this week! I'll follow up with what we find.