99M opening specialist (squares64)
Same 99M squares64 architecture as
avewright/chess-transformer-100m-squares64,
finetuned on ≥26-piece positions (one-hot best first move) from
Lichess/chess-position-evaluations
via avewright/lichess-opening-bestline.
This file is latest.pt at opening-FT step 8000 (2026-09-14 14:42 UTC).
Train loss ~1.7585. Frozen holdout hard CE ~1.4045.
Not the generalist incumbent, the puzzle expert, the Syzygy expert, or the endgame expert.
Training
- Warm start: public 99M
latest.pt(weights only), then full resume. - Split: position-hash 80/20 (seed 277). Frozen piece-stratified val 8192.
- One-hot PV1 (
soft_alpha=0). Pieces 26–32. - Polar-NorMuon, bs=528. Best disk ckpt at upload: step 8000.
Files
latest.ptstep_008000.ptmodel_config.jsontrain.logpack.json
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support