From f8c779dbe538315aa6f65556d0acf11640558504 Mon Sep 17 00:00:00 2001 From: JWmer Date: Sun, 13 Jun 2021 23:48:32 +0200 Subject: [PATCH] Update default net to nn-8e47cf062333.nnue MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit This net is the result of training on data used by the Leela project. More precisely, we shuffled T60 and T74 data kindly provided by borg (for different Tnn, the data is a result of Leela selfplay with differently sized Leela nets). The data is available at vondele's google drive: https://drive.google.com/drive/folders/1mftuzYdl9o6tBaceR3d_VBQIrgKJsFpl. The Leela data comes in small chunks of .binpack files. To shuffle them, we simply used a small python script to randomly rename the files, and then concatenated them using `cat`. As validation data we picked a file of T60 data. We will further investigate T74 data. The training for the NNUE architecture used 200 epochs with the Python trainer from the Stockfish project. Unlike the previous run we tried with this data, this run does not have adjusted scaling — not because we didn't want to, but because we forgot. However, this training randomly skips 40% more positions than previous run. The loss was very spiky and decreased slower than it does usually. Training loss: https://github.com/official-stockfish/images/blob/main/training-loss-8e47cf062333.png Validation loss: https://github.com/official-stockfish/images/blob/main/validation-loss-8e47cf062333.png This is the exact training command: python train.py --smart-fen-skipping --random-fen-skipping 14 --batch-size 16384 --threads 4 --num-workers 4 --gpus 1 trainingdata\training_data.binpack validationdata\val.binpack --- 10k STC result: ELO: 3.61 +-3.3 (95%) LOS: 98.4% Total: 10000 W: 1241 L: 1137 D: 7622 Ptnml(0-2): 68, 841, 3086, 929, 76 https://tests.stockfishchess.org/tests/view/60c67e50457376eb8bcaae70 10k LTC result: ELO: 2.71 +-2.4 (95%) LOS: 98.8% Total: 10000 W: 659 L: 581 D: 8760 Ptnml(0-2): 22, 485, 3900, 579, 14 https://tests.stockfishchess.org/tests/view/60c69deb457376eb8bcaae98 Passed LTC: LLR: 2.93 (-2.94,2.94) <0.50,3.50> Total: 9648 W: 685 L: 545 D: 8418 Ptnml(0-2): 22, 448, 3740, 596, 18 https://tests.stockfishchess.org/tests/view/60c6d41c457376eb8bcaaecf --- closes https://github.com/official-stockfish/Stockfish/pull/3550 Bench: 4877339 --- AUTHORS | 3 ++- src/evaluate.h | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/AUTHORS b/AUTHORS index 7165363f..7e63591a 100644 --- a/AUTHORS +++ b/AUTHORS @@ -1,4 +1,4 @@ -# List of authors for Stockfish, as of May 17, 2021 +# List of authors for Stockfish, as of June 14, 2021 # Founders of the Stockfish project and fishtest infrastructure Tord Romstad (romstad) @@ -96,6 +96,7 @@ Joost VandeVondele (vondele) Jörg Oster (joergoster) Joseph Ellis (jhellis3) Joseph R. Prostko +Julian Willemer (NightlyKing) jundery Justin Blanchard (UncombedCoconut) Kelly Wilson diff --git a/src/evaluate.h b/src/evaluate.h index 725d5a78..c19b14ba 100644 --- a/src/evaluate.h +++ b/src/evaluate.h @@ -39,7 +39,7 @@ namespace Eval { // The default net name MUST follow the format nn-[SHA256 first 12 digits].nnue // for the build process (profile-build and fishtest) to work. Do not change the // name of the macro, as it is used in the Makefile. - #define EvalFileDefaultName "nn-7e66505906a6.nnue" + #define EvalFileDefaultName "nn-8e47cf062333.nnue" namespace NNUE { -- 2.39.2