I've released a new major version of Calvin, finally taking the jump into NNUE:
https://github.com/kelseyde/calvin-ches ... /tag/4.0.0
The net was trained on 250 million positions taken from the Leela dataset that I re-scored using Calvin's own search and HCE. For training I used the excellent bullet trainer.
In self-play Calvin 4.0.0 completely crushes his predecessor to the tune of +400 elo - although I guess that might be inflated somewhat compared to how he'd stack up against other engines:
Code: Select all
Score of Calvin_NNUE vs Calvin: 436 - 19 - 45 [0.917] 500
Elo difference: 417.3 +/- 47.1, LOS: 100.0 %, DrawRatio: 9.0 %