Update default net to nn-3678835b1d3d.nnue
New net trained with nnue-pytorch, started from the master net on a data set of Leela
(T60.binpack+T74.binpck) and Stockfish data (wrongIsRight_nodes5000pv2.binpack),
available as a single interleaved binpack:
https://drive.google.com/file/d/12uWZIA3F2cNbraAzQNb1jgf3tq_6HkTr/view?usp=sharing
The nnue-pytorch branch used is https://github.com/vondele/nnue-pytorch/tree/wdl, which
has the new feature to filter positions based on the likelihood of the current evaluation
leading to the game outcome. It should make it less likely to try to learn from
misevaluated positions. Standard options have been used, starting from the master net:
--gpus 1 --threads 4 --num-workers 4 --batch-size 16384 --progress_bar_refresh_rate 300
--smart-fen-skipping --random-fen-skipping 12 --features=HalfKAv2_hm^ --lambda=1.0
Testing with games shows neutral Elo at STC, and good performance at LTC:
STC:
https://tests.stockfishchess.org/tests/view/619eb597c0a4ea18ba95a4dc
ELO: -0.44 +-1.8 (95%) LOS: 31.2%
Total: 40000 W: 10447 L: 10498 D: 19055
Ptnml(0-2): 254, 4576, 10260, 4787, 123
LTC:
https://tests.stockfishchess.org/tests/view/619f6e87c0a4ea18ba95a53f
ELO: 3.30 +-1.8 (95%) LOS: 100.0%
Total: 33062 W: 8560 L: 8246 D: 16256
Ptnml(0-2): 54, 3358, 9352, 3754, 13
passed LTC SPRT:
https://tests.stockfishchess.org/tests/view/61a0864e8967bbf894416e65
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 29376 W: 7663 L: 7396 D: 14317
Ptnml(0-2): 67, 3017, 8205, 3380, 19
closes https://github.com/official-stockfish/Stockfish/pull/3808
Bench: 7011501