Pretty much all mainstream songs are of the same tempo (or slight variations), the same beat, the same scale, the same accents etc. I'm not surprised at all it can be regurgitated by an generative model.

What I would like to see is what happens if you ask it to do in 5/8, 5/4 or any of the 7/* variants and see how that goes (I have no idea, might actually work). There are some examples in common music but not a lot especially for the more obscure ones. Unless they also trained it on a lot of international folk songs.