Some results from what I tested
Transformer overfit test: loss 0.014, confirming the training loop and model heads are correct.
Short training run (25.9M-param model, 6,000 steps, ~200M tokens): next-note top-1 accuracy 67.7% on clean input, 46.1% under timing jitter.
LightGBM next-chord baseline on the full 409,936-song corpus: 50.7% top-1 on next-bar chord, 46.8% on next-chord-change
Progress is ahead. Next week I hope to see if 80% goal is actually reasonable given the current scores. If i can get it up to ~65 i’ll keep trying for 80%