Stockfish

mirror of https://github.com/opelly27/Stockfish.git synced 2026-05-20 16:47:37 +00:00

Author	SHA1	Message	Date
Linmiao Xu	41f50b2c83	Update default net to nn-e1fb1ade4432.nnue Created by retraining nn-dabb1ed23026.nnue with a dataset composed of: * The previous best dataset (nn-1ceb1a57d117.nnue dataset) * Adding de-duplicated T80 data from feb2023 and the last 10 days of jan2023, filtered with v6-dd Initially trained with the same options as the recent master net (nn-1ceb1a57d117.nnue). Around epoch 890, training was manually stopped and max epoch increased to 1000. ``` python3 easy_train.py \ --experiment-name leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovjanfebT79aprmayT78jantosepT77dec-v6dd \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes \ --start-from-engine-test-net True \ --early-fen-skipping 30 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 900 \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --gpus "0," \ --seed $RANDOM ``` The same v6-dd filtering and binpack minimizer was used for preparing the recent nn-1ceb1a57d117.nnue dataset. ``` python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-filt-v2.binpack \ T60-nov2021-12tb7p-eval-filt-v2.binpack \ T60-dec2021-12tb7p-eval-filt-v2.binpack \ filt-v6/test80-aug2022-16tb7p-filter-v6.min-mar2023.binpack \ filt-v6/test80-sep2022-16tb7p-filter-v6.min-mar2023.binpack \ filt-v6-dd/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test80-jul2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-oct2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-nov2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-jan2022-3of3-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test79-apr2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test79-may2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test78-juntosep2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test77-dec2021-16tb7p-filter-v6-dd.binpack \ /data/leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack ``` Links for downloading the training data components can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch919.nnue : 2.6 +/- 2.8 Passed STC vs. nn-dabb1ed23026.nnue https://tests.stockfishchess.org/tests/view/644420df94ff3db5625f2af5 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 125960 W: 33898 L: 33464 D: 58598 Ptnml(0-2): 351, 13920, 34021, 14320, 368 Passed LTC vs. nn-1ceb1a57d117.nnue https://tests.stockfishchess.org/tests/view/64469f128d30316529b3dc46 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 24544 W: 6817 L: 6542 D: 11185 Ptnml(0-2): 8, 2252, 7488, 2505, 19 closes https://github.com/official-stockfish/Stockfish/pull/4546 bench 3714847	2023-04-25 08:19:00 +02:00
Linmiao Xu	c3ce220408	Created by retraining the master net with these changes to the dataset: * Extending v6 filtering to data from T77 dec2021, T79 may2022, and T80 nov2022 * Reducing the number of duplicate positions, prioritizing position scores seen later in time * Using a binpack minimizer to reduce the overall data size Trained the same way as the previous master net, aside from the dataset changes: ``` python3 easy_train.py \ --experiment-name leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovT79aprmayT78jantosepT77dec-v6dd \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovT79aprmayT78jantosepT77dec-v6dd.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes \ --start-from-engine-test-net True \ --early-fen-skipping 30 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 900 \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --gpus "0," \ --seed $RANDOM ``` The new v6-dd filtering reduces duplicate positions by iterating over hourly data files within leela test runs, starting with the most recent, then keeping positions the first time they're seen and ignoring positions that are seen again. This ordering was done with the assumption that position scores seen later in time are generally more accurate than scores seen earlier in the test run. Positions are de-duplicated based on piece orientations, the first token in fen strings. The binpack minimizer was run with default settings after first merging monthly data into single binpacks. ``` python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-filt-v2.binpack \ T60-nov2021-12tb7p-eval-filt-v2.binpack \ T60-dec2021-12tb7p-eval-filt-v2.binpack \ filt-v6/test80-aug2022-16tb7p-filter-v6.min-mar2023.binpack \ filt-v6/test80-sep2022-16tb7p-filter-v6.min-mar2023.binpack \ filt-v6-dd/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test80-jul2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-oct2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test80-nov2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test79-apr2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test79-may2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.binpack \ filt-v6-dd/test78-juntosep2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test77-dec2021-16tb7p-filter-v6-dd.binpack \ /data/leela96-dfrc99-T60novdec-v2-T80augsep-v6-T80junjuloctnovT79aprmayT78jantosepT77dec-v6dd.binpack ``` The code for v6-dd filtering is available along with training data preparation scripts at: https://github.com/linrock/nnue-data Links for downloading the training data components: https://robotmoon.com/nnue-training-data/ The binpack minimizer is from: #4447 Local elo at 25k nodes per move: nn-epoch859.nnue : 1.2 +/- 2.6 Passed STC: https://tests.stockfishchess.org/tests/view/643aad7db08900ff1bc5a832 LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 565040 W: 150225 L: 149162 D: 265653 Ptnml(0-2): 1875, 62137, 153229, 63608, 1671 Passed LTC: https://tests.stockfishchess.org/tests/view/643ecf2fa43cf30e719d2042 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 1014840 W: 274645 L: 272456 D: 467739 Ptnml(0-2): 515, 98565, 306970, 100956, 414 closes https://github.com/official-stockfish/Stockfish/pull/4545 bench 3476305	2023-04-25 08:17:22 +02:00
Muzhen Gaming	c90dd38903	Simplify away complexity in evaluation Simplification STC: https://tests.stockfishchess.org/tests/view/64394bc0605991a801b4f6f0 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 72360 W: 19313 L: 19138 D: 33909 Ptnml(0-2): 206, 7883, 19800, 8112, 179 Simplification LTC: https://tests.stockfishchess.org/tests/view/6439e788c233ce943b6bdac1 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 224992 W: 60665 L: 60654 D: 103673 Ptnml(0-2): 96, 21875, 68526, 21920, 79 closes https://github.com/official-stockfish/Stockfish/pull/4530 Bench: 3709369	2023-04-22 10:43:29 +02:00
Linmiao Xu	37160c4b16	Update default net to nn-dabb1ed23026.nnue Created by retraining the master net with these modifications: * New filtering methods for existing data from T80 sep+oct2022, T79 apr2022, T78 jun+jul+aug+sep2022, T77 dec2021 * Adding new filtered data from T80 aug2022 and T78 apr+may2022 * Increasing early-fen-skipping from 28 to 30 ``` python3 easy_train.py \ --experiment-name leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3-sk30 \ --training-dataset /data/leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes \ --start-from-engine-test-net True \ --early-fen-skipping 30 \ --max_epoch 900 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --gpus "0," \ --seed $RANDOM ``` The v3 filtering used for data from T77dec 2021 differs from v2 filtering in that: * To improve binpack compression, positions after ply 28 were skipped during training by setting position scores to VALUE_NONE (32002) instead of removing them entirely * All early-game positions with ply <= 28 were removed to maximize binpack compression * Only bestmove captures at d6pv2 search were skipped, not 2nd bestmove captures * Binpack compression was repaired for the remaining positions by effectively replacing bestmoves with "played moves" to maintain contiguous sequences of positions in the training game data After improving binpack compression, The T77 dec2021 data size was reduced from 95G to 19G. The v6 filtering used for data from T80augsepoctT79aprT78aprtosep 2022 differs from v2 in that: * All positions with only one legal move were removed * Tighter score differences at d6pv2 search were used to remove more positions with only one good move than before * d6pv2 search was not used to remove positions where the best 2 moves were captures ``` python3 interleave_binpacks.py \ nn-547-dataset/leela96-eval-filt-v2.binpack \ nn-547-dataset/dfrc99-eval-filt-v2.binpack \ nn-547-dataset/test80-nov2022-12tb7p-eval-filt-v2-d6.binpack \ nn-547-dataset/T79-may2022-12tb7p-eval-filt-v2.binpack \ nn-547-dataset/T60-nov2021-12tb7p-eval-filt-v2.binpack \ nn-547-dataset/T60-dec2021-12tb7p-eval-filt-v2.binpack \ filt-v6/test80-aug2022-16tb7p-filter-v6.binpack \ filt-v6/test80-sep2022-16tb7p-filter-v6.binpack \ filt-v6/test80-oct2022-16tb7p-filter-v6.binpack \ filt-v6/test79-apr2022-16tb7p-filter-v6.binpack \ filt-v6/test78-aprmay2022-16tb7p-filter-v6.binpack \ filt-v6/test78-junjulaug2022-16tb7p-filter-v6.binpack \ filt-v6/test78-sep2022-16tb7p-filter-v6.binpack \ filt-v3/test77-dec2021-16tb7p-filt-v3.binpack \ /data/leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3.binpack ``` The code for the new data filtering methods is available at: https://github.com/linrock/Stockfish/tree/nnue-data-v3/nnue-data The code for giving hexword names to .nnue files is at: https://github.com/linrock/nnue-namer Links for downloading the training data components can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch779.nnue : 0.6 +/- 3.1 Passed STC: https://tests.stockfishchess.org/tests/view/64212412db43ab2ba6f8efb0 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 82256 W: 22185 L: 21809 D: 38262 Ptnml(0-2): 286, 9065, 22067, 9407, 303 Passed LTC: https://tests.stockfishchess.org/tests/view/64223726db43ab2ba6f91d6c LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 30840 W: 8437 L: 8149 D: 14254 Ptnml(0-2): 14, 2891, 9323, 3177, 15 closes https://github.com/official-stockfish/Stockfish/pull/4465 bench 5101970	2023-03-29 21:37:52 +02:00
disservin	af4b62a593	NNUE namespace cleanup This patch moves the nnue namespace in the appropiate header that correspondes with the definition. It also makes navigation a bit easier. closes https://github.com/official-stockfish/Stockfish/pull/4445 No functional change	2023-03-19 11:27:15 +01:00
Linmiao Xu	876906965b	Update default net to nn-52471d67216a.nnue Created by retraining the master net with modifications to the previous best dataset: * Improving T80 oct+nov 2022 endgame lambda accuracy by rescoring with 12-16tb of syzygy 7p tablebases * Filtering T78 jun+jul+aug 2022 with d6pv2 search to remove positions with bestmove captures or one good move * Adding T80 sep 2022 data, rescored with 16tb of 7p tablebases, unfiltered Trained with max-epoch 900, end-lambda 0.7, and early-fen-skipping 28. ``` python3 easy_train.py \ --experiment-name leela96-dfrc99-T80octnovT79aprmayT78junjulaugT60novdec-filt-v2-T78sep12tb7p-T77decT80sep16tb7p-lambda7-sk28 \ --training-dataset /data/leela96-dfrc99-T80octnovT79aprmayT78junjulaugT60novdec-filt-v2-T78sep12tb7p-T77decT80sep16tb7p.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/easy-train-early-fen-skipping \ --early-fen-skipping 28 \ --start-from-engine-test-net True \ --gpus "0," \ --max_epoch 900 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --gamma 0.995 \ --lr 4.375e-4 \ --tui False \ --seed $RANDOM ``` Training data was rescored and d6pv2 filtered in the same way as recent best datasets. For preparing the merged training dataset: ``` python3 interleave_binpacks.py \ leela96-eval-filt-v2.binpack \ dfrc99-eval-filt-v2.binpack \ test80-oct2022-16tb7p-eval-filt-v2-d6.binpack \ test80-nov2022-12tb7p-eval-filt-v2-d6.binpack \ T79-apr2022-12tb7p-eval-filt-v2.binpack \ T79-may2022-12tb7p-eval-filt-v2.binpack \ test78-junjulaug2022-16tb7p-eval-filt-v2-d6.binpack \ T60-nov2021-12tb7p-eval-filt-v2.binpack \ T60-dec2021-12tb7p-eval-filt-v2.binpack \ T78-sep2022-12tb7p.binpack \ test77-dec2021-16gb7p.binpack \ test80-sep2022-16tb7p.binpack \ /data/leela96-dfrc99-T80octnovT79aprmayT78junjulaugT60novdec-filt-v2-T78sep12tb7p-T77decT80sep16tb7p.binpack ``` Links for downloading the training data components can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch839.nnue : 0.6 +/- 1.4 Passed STC: https://tests.stockfishchess.org/tests/view/63f9ab4be74a12625bcdf02e LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 84656 W: 22681 L: 22302 D: 39673 Ptnml(0-2): 271, 9343, 22734, 9696, 284 Passed LTC: https://tests.stockfishchess.org/tests/view/63fa3833e74a12625bce0c0e LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 184664 W: 49933 L: 49344 D: 85387 Ptnml(0-2): 111, 17977, 55561, 18578, 105 closes https://github.com/official-stockfish/Stockfish/pull/4416 bench: 4814343	2023-02-27 22:07:52 +01:00
Joost VandeVondele	08385527dd	Introduce a function to compute NNUE accumulator This patch introduces `hint_common_parent_position()` to signal that potentially several child nodes will require an NNUE eval. By populating explicitly the accumulator, these subsequent evaluations can be performed more efficiently. This was based on the observation that calculating the evaluation in an excluded move position yielded a significant Elo gain, even though the evaluation itself was already available (work by pb00067). Sopel wrote the code to perform just the accumulator update. This PR is based on cleaned up code that passed STC: https://tests.stockfishchess.org/tests/view/63f62f9be74a12625bcd4aa0 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 110368 W: 29607 L: 29167 D: 51594 Ptnml(0-2): 41, 10551, 33572, 10967, 53 and in an the earlier (equivalent) version passed STC: https://tests.stockfishchess.org/tests/view/63f3c3fee74a12625bcce2a6 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 47552 W: 12786 L: 12467 D: 22299 Ptnml(0-2): 120, 5107, 12997, 5438, 114 passed LTC: https://tests.stockfishchess.org/tests/view/63f45cc2e74a12625bccfa63 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 110368 W: 29607 L: 29167 D: 51594 Ptnml(0-2): 41, 10551, 33572, 10967, 53 closes https://github.com/official-stockfish/Stockfish/pull/4402 Bench: 3726250	2023-02-23 13:25:35 +01:00
Linmiao Xu	05dea2ca46	Update default net to nn-1337b1adec5b.nnue Created by retraining the master net on a dataset composed of: * Most of the previous best dataset filtered to remove positions likely having only one good move * Adding training data from Leela T77 dec2021 rescored with 16tb of 7-piece tablebases Trained with end lambda 0.7 and max epoch 900. Positions with ply <= 28 were removed from most of the previous best dataset before training began. A new nnue-pytorch trainer param for skipping early plies was used to skip plies <= 24 in the unfiltered and additional Leela T77 parts of the dataset. ``` python easy_train.py \ --experiment-name leela96-dfrc99-T80octnovT79aprmayT60novdec-eval-filt-v2-T78augsep-12tb-T77dec-16tb-lambda7-sk24 \ --training-dataset /data/leela96-dfrc99-T80octnovT79aprmayT60novdec-eval-filt-v2-T78augsep-12tb-T77dec-16tb.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/easy-train-early-fen-skipping \ --early-fen-skipping 24 \ --gpus "0," \ --start-from-engine-test-net True \ --start-lambda 1.0 \ --end-lambda 0.7 \ --gamma 0.995 \ --lr 4.375e-4 \ --tui False \ --seed $RANDOM \ --max_epoch 900 ``` The depth6 multipv2 search filtering method is the same as the one used for filtering recent best datasets, with a lower eval difference threshold to remove slightly more positions than before. These parts of the dataset were filtered: * 96% of T60T70wIsRightFarseerT60T74T75T76.binpack * 99% of dfrc_n5000.binpack * T80 oct + nov 2022 data, no positions with castling flags, rescored with ~600gb 7p tablebases * T79 apr + may 2022 data, rescored with 12tb 7p tablebases * T60 nov + dec 2021 data, rescored with 12tb 7p tablebases These parts of the dataset were not filtered. Positions with ply <= 24 were skipped during training: * T78 aug + sep 2022 data, rescored with 12tb 7p tablebases * 84% of T77 dec 2021 data, rescored with 16tb 7p tablebases The code and exact evaluation thresholds used for data filtering can be found at: https://github.com/linrock/Stockfish/tree/tools-filter-multipv2-eval-diff-t2/src/filter The exact training data used can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch859.nnue : 3.5 +/ 1.2 Passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.00> https://tests.stockfishchess.org/tests/view/63dfeefc73223e7f52ad769f Total: 219744 W: 58572 L: 58002 D: 103170 Ptnml(0-2): 609, 24446, 59284, 24832, 701 Passed LTC: https://tests.stockfishchess.org/tests/view/63e268fc73223e7f52ade7b6 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 91256 W: 24528 L: 24121 D: 42607 Ptnml(0-2): 48, 8863, 27390, 9288, 39 closes https://github.com/official-stockfish/Stockfish/pull/4387 bench 3841998	2023-02-09 07:50:27 +01:00
Linmiao Xu	596a528c6a	Update default net to nn-bc24c101ada0.nnue Created by retraining the master net with Leela T78 data from Aug+Sep 2022 added to the previous best dataset. Trained with end lambda 0.7 and started with max epoch 800. All positions with ply <= 28 were skipped: ``` python easy_train.py \ --experiment-name leela95-dfrc96-filt-only-T80octnov-T60novdecT78augsepT79aprmay-12tb7p-sk28-lambda7 \ --training-dataset /data/leela95-dfrc96-filt-only-T80octnov-T60novdecT78augsepT79aprmay-12tb7p.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-skip-ply-lteq-28 \ --start-from-engine-test-net True \ --gpus "0," \ --start-lambda 1.0 \ --end-lambda 0.7 \ --gamma 0.995 \ --lr 4.375e-4 \ --tui False \ --seed $RANDOM \ --max_epoch 800 ``` Around epoch 750, training was manually paused and max epoch increased to 950 before resuming. The additional Leela training data from T78 was prepared in the same way as the previous best dataset. The exact training data used can be found at: https://robotmoon.com/nnue-training-data/ While the local elo ratings during this experiment were much lower than in recent master nets, several later epochs had a consistent elo above zero, and this was hypothesized to represent potential strength at slower time controls. Local elo at 25k nodes per move leela95-dfrc96-filt-only-T80octnov-T60novdecT78augsepT79aprmay-12tb7p-sk28-lambda7 nn-epoch819.nnue : 0.4 +/- 1.1 (nn-bc24c101ada0.nnue) nn-epoch799.nnue : 0.3 +/- 1.2 nn-epoch759.nnue : 0.3 +/- 1.1 nn-epoch839.nnue : 0.2 +/- 1.4 Passed STC https://tests.stockfishchess.org/tests/view/63cabf6f0eefe8694a0c6013 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 41608 W: 11161 L: 10848 D: 19599 Ptnml(0-2): 116, 4496, 11281, 4781, 130 Passed LTC https://tests.stockfishchess.org/tests/view/63cb1856344bb01c191af263 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 76760 W: 20517 L: 20137 D: 36106 Ptnml(0-2): 34, 7435, 23070, 7799, 42 closes https://github.com/official-stockfish/Stockfish/pull/4351 bench 3941848	2023-01-23 07:01:32 +01:00
Linmiao Xu	3d2381d76d	Update default net to nn-1e7ca356472e.nnue Created by retraining the master net on a dataset composed of: * The Leela-dfrc_n5000.binpack dataset filtered with depth6 multipv2 search to remove positions with only one good move, in addition to removing positions where either of the two best moves are captures * The same Leela T80 oct+nov 2022 training data used in recent best datasets * Additional Leela training data from T60 nov+dec 2021 and T79 apr+may 2022 Trained with end lambda 0.7 and started with max epoch 800. All positions with ply <= 28 were skipped: ``` python easy_train.py \ --experiment-name leela95-dfrc96-mpv-eval-fonly-T80octnov-T79aprmayT60novdec-12tb7p-sk28-lambda7 \ --training-dataset /data/leela95-dfrc96-mpv-eval-fonly-T80octnov-T79aprmayT60novdec-12tb7p.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-skip-ply-lteq-28 \ --start-from-engine-test-net True \ --gpus "0," \ --start-lambda 1.0 \ --end-lambda 0.7 \ --gamma 0.995 \ --lr 4.375e-4 \ --tui False \ --seed $RANDOM \ --max_epoch 800 ``` Around epoch 780, training was manually paused and max epoch increased to 920 before resuming. During depth6 multipv2 data filtering, positions were considered to have only one good move if the score of the best move was significantly better than the 2nd best move in a way that changes the outcome of the game: * the best move leads to a significant advantage while the 2nd best move equalizes or loses * the best move is about equal while the 2nd best move loses The modified stockfish branch and exact score thresholds used for filtering are at: https://github.com/linrock/Stockfish/tree/tools-filter-multipv2-eval-diff/src/filter About 95% of the Leela portion and 96% of the DFRC portion of the Leela-dfrc_n5000.binpack dataset was filtered. Unfiltered parts of the dataset were left out. The additional Leela training data from T60 nov+dec 2021 and T79 apr+may 2022 was WDL-rescored with about 12TB of syzygy 7-piece tablebases where the material difference is less than around 6 pawns. Best moves were exported to .plain data files during data conversion with the lc0 rescorer. The exact training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move experiment_leela95-dfrc96-mpv-eval-fonly-T80octnov-T79aprmayT60novdec-12tb7p-sk28-lambda7 run_0/nn-epoch899.nnue : 3.8 +/- 1.6 Passed STC https://tests.stockfishchess.org/tests/view/63bed1f540aa064159b9c89b LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 103344 W: 27392 L: 26991 D: 48961 Ptnml(0-2): 333, 11223, 28099, 11744, 273 Passed LTC https://tests.stockfishchess.org/tests/view/63c010415705810de2deb3ec LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 21712 W: 5891 L: 5619 D: 10202 Ptnml(0-2): 12, 2022, 6511, 2304, 7 closes https://github.com/official-stockfish/Stockfish/pull/4338 bench 4106793	2023-01-14 08:12:11 +01:00
Linmiao Xu	a6fa683418	Update default net to nn-a3dc078bafc7.nnue This is a later epoch (epoch 859) from the same experiment run that trained yesterday's master net nn-60fa44e376d9.nnue (epoch 779). The experiment was manually paused around epoch 790 and unpaused with max epoch increased to 900 mainly to get more local elo data without letting the GPU idle. nn-60fa44e376d9.nnue is from #4314 nn-335a9b2d8a80.nnue is from #4295 Local elo vs. nn-335a9b2d8a80.nnue at 25k nodes per move: experiment_leela93-dfrc99-filt-only-T80-oct-nov-skip28 run_0/nn-epoch779.nnue (nn-60fa44e376d9.nnue) : 5.0 +/- 1.2 run_0/nn-epoch859.nnue (nn-a3dc078bafc7.nnue) : 5.6 +/- 1.6 Passed STC vs. nn-335a9b2d8a80.nnue https://tests.stockfishchess.org/tests/view/63ae10495bd1e5f27f13d94f LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 37536 W: 10088 L: 9781 D: 17667 Ptnml(0-2): 110, 4006, 10223, 4325, 104 An LTC test vs. nn-335a9b2d8a80.nnue was paused due to nn-60fa44e376d9.nnue passing LTC first: https://tests.stockfishchess.org/tests/view/63ae5d34331d5fca5113703b Passed LTC vs. nn-60fa44e376d9.nnue https://tests.stockfishchess.org/tests/view/63af1e41465d2b022dbce4e7 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 148704 W: 39672 L: 39155 D: 69877 Ptnml(0-2): 59, 14443, 44843, 14936, 71 closes https://github.com/official-stockfish/Stockfish/pull/4319 bench 3984365	2023-01-02 19:10:14 +01:00
Sebastian Buchwald	b60f9cc451	Update copyright years Happy New Year! closes https://github.com/official-stockfish/Stockfish/pull/4315 No functional change	2023-01-02 19:07:38 +01:00
Linmiao Xu	be9bc420af	Update default net to nn-60fa44e376d9.nnue Created by retraining the master net on the previous best dataset with additional filtering. No new data was added. More of the Leela-dfrc_n5000.binpack part of the dataset was pre-filtered with depth6 multipv2 search to remove bestmove captures. About 93% of the previous Leela/SF data and 99% of the SF dfrc data was filtered. Unfiltered parts of the dataset were left out. The new Leela T80 oct+nov data is the same as before. All early game positions with ply count <= 28 were skipped during training by modifying the training data loader in nnue-pytorch. Trained in a similar way as recent master nets, with a different nnue-pytorch branch for early ply skipping: python3 easy_train.py \ --experiment-name=leela93-dfrc99-filt-only-T80-oct-nov-skip28 \ --training-dataset=/data/leela93-dfrc99-filt-only-T80-oct-nov.binpack \ --start-from-engine-test-net True \ --nnue-pytorch-branch=linrock/nnue-pytorch/misc-fixes-skip-ply-lteq-28 \ --gpus="0," \ --start-lambda=1.0 \ --end-lambda=0.75 \ --gamma=0.995 \ --lr=4.375e-4 \ --tui=False \ --seed=$RANDOM \ --max_epoch=800 \ --network-testing-threads 20 \ --num-workers 6 For the exact training data used: https://robotmoon.com/nnue-training-data/ Details about the previous best dataset: #4295 Local testing at a fixed 25k nodes: experiment_leela93-dfrc99-filt-only-T80-oct-nov-skip28 Local Elo: run_0/nn-epoch779.nnue : 5.1 +/- 1.5 Passed STC https://tests.stockfishchess.org/tests/view/63adb3acae97a464904fd4e8 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 36504 W: 9847 L: 9538 D: 17119 Ptnml(0-2): 108, 3981, 9784, 4252, 127 Passed LTC https://tests.stockfishchess.org/tests/view/63ae0ae25bd1e5f27f13d884 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 36592 W: 10017 L: 9717 D: 16858 Ptnml(0-2): 17, 3461, 11037, 3767, 14 closes https://github.com/official-stockfish/Stockfish/pull/4314 bench 4015511	2023-01-01 12:28:51 +01:00
Linmiao Xu	c620886181	Update default net to nn-335a9b2d8a80.nnue Created by retraining the master net with a combination of: the previous best dataset (Leela-dfrc_n5000.binpack), with about half the dataset filtered using depth6 multipv2 search to throw away positions where either of the 2 best moves are captures Leela T80 Oct and Nov training data rescored with best moves, adding ~9.5 billion positions Trained effectively the same way as the previous master net: python3 easy_train.py \ --experiment-name=leela-dfrc-filtered-T80-oct-nov \ --training-dataset=/data/leela-dfrc-filtered-T80-oct-nov.binpack \ --start-from-engine-test-net True \ --gpus="0," \ --start-lambda=1.0 \ --end-lambda=0.75 \ --gamma=0.995 \ --lr=4.375e-4 \ --tui=False \ --seed=$RANDOM \ --max_epoch=800 \ --auto-exit-timeout-on-training-finished=900 \ --network-testing-threads 20 \ --num-workers 6 Local testing at a fixed 25k nodes: experiments/experiment_leela-dfrc-filtered-T80-oct-nov/training/run_0/nn-epoch779.nnue localElo: run_0/nn-epoch779.nnue : 4.7 +/- 3.1 The new Leela T80 part of the dataset was prepared by downloading test80 training data from all of Oct 2022 and Nov 2022, rescoring with syzygy 6-piece tablebases and ~600 GB of 7-piece tablebases, saving best moves to exported .plain files, removing all positions with castling flags, then converting to binpacks and using interleave_binpacks.py to merge them together. Scripts used in this data conversion process are available at: https://github.com/linrock/lc0-data-converter Filtering binpack data using depth6 multipv2 search was done by modifying transform.cpp in the tools branch: https://github.com/linrock/Stockfish/tree/tools-filter-multipv2-no-rescore Links for downloading the training data (total size: 338 GB) are available at: https://robotmoon.com/nnue-training-data/ Passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 30544 W: 8244 L: 7947 D: 14353 Ptnml(0-2): 93, 3243, 8302, 3542, 92 https://tests.stockfishchess.org/tests/view/63a0d377264a0cf18f86f82b Passed LTC: LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 32464 W: 8866 L: 8573 D: 15025 Ptnml(0-2): 19, 3054, 9794, 3345, 20 https://tests.stockfishchess.org/tests/view/63a10bc9fb452d3c44b1e016 closes https://github.com/official-stockfish/Stockfish/pull/4295 Bench 3554904	2022-12-21 07:14:58 +01:00
Joost VandeVondele	4b4b7d1209	Update default net to nn-ad9b42354671.nnue using trainer branch https://github.com/glinscott/nnue-pytorch/pull/208 with a slightly tweaked loss function (power 2.5 instead of 2.6), otherwise same training as in the previous net update https://github.com/official-stockfish/Stockfish/pull/4100 passed STC: LLR: 2.97 (-2.94,2.94) <0.00,2.50> Total: 367536 W: 99465 L: 98573 D: 169498 Ptnml(0-2): 1820, 40994, 97117, 42148, 1689 https://tests.stockfishchess.org/tests/view/62cc43fe50dcbecf5fc1c5b8 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 25032 W: 6802 L: 6553 D: 11677 Ptnml(0-2): 40, 2424, 7341, 2669, 42 https://tests.stockfishchess.org/tests/view/62ce5f421dacb46e4d5fd277 closes https://github.com/official-stockfish/Stockfish/pull/4107 Bench: 5905619	2022-07-13 18:01:20 +02:00
Joost VandeVondele	85f8ee6199	Update default net to nn-3c0054ea9860.nnu First things first... this PR is being made from court. Today, Tord and Stéphane, with broad support of the developer community are defending their complaint, filed in Munich, against ChessBase. With their products Houdini 6 and Fat Fritz 2, both Stockfish derivatives, ChessBase violated repeatedly the Stockfish GPLv3 license. Tord and Stéphane have terminated their license with ChessBase permanently. Today we have the opportunity to present our evidence to the judge and enforce that termination. To read up, have a look at our blog post https://stockfishchess.org/blog/2022/public-court-hearing-soon/ and https://stockfishchess.org/blog/2021/our-lawsuit-against-chessbase/ This PR introduces a net trained with an enhanced data set and a modified loss function in the trainer. A slight adjustment for the scaling was needed to get a pass on standard chess. passed STC: https://tests.stockfishchess.org/tests/view/62c0527a49b62510394bd610 LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 135008 W: 36614 L: 36152 D: 62242 Ptnml(0-2): 640, 15184, 35407, 15620, 653 passed LTC: https://tests.stockfishchess.org/tests/view/62c17e459e7d9997a12d458e LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 28864 W: 8007 L: 7749 D: 13108 Ptnml(0-2): 47, 2810, 8466, 3056, 53 Local testing at a fixed 25k nodes resulted in Test run1026/easy_train_data/experiments/experiment_2/training/run_0/nn-epoch799.nnue localElo: 4.2 +- 1.6 The real strength of the net is in FRC and DFRC chess where it gains significantly. Tested at STC with slightly different scaling: FRC: https://tests.stockfishchess.org/tests/view/62c13a4002ba5d0a774d20d4 Elo: 29.78 +-3.4 (95%) LOS: 100.0% Total: 10000 W: 2007 L: 1152 D: 6841 Ptnml(0-2): 31, 686, 2804, 1355, 124 nElo: 59.24 +-6.9 (95%) PairsRatio: 2.06 DFRC: https://tests.stockfishchess.org/tests/view/62c13a5702ba5d0a774d20d9 Elo: 55.25 +-3.9 (95%) LOS: 100.0% Total: 10000 W: 2984 L: 1407 D: 5609 Ptnml(0-2): 51, 636, 2266, 1779, 268 nElo: 96.95 +-7.2 (95%) PairsRatio: 2.98 Tested at LTC with identical scaling: FRC: https://tests.stockfishchess.org/tests/view/62c26a3c9e7d9997a12d6caf Elo: 16.20 +-2.5 (95%) LOS: 100.0% Total: 10000 W: 1192 L: 726 D: 8082 Ptnml(0-2): 10, 403, 3727, 831, 29 nElo: 44.12 +-6.7 (95%) PairsRatio: 2.08 DFRC: https://tests.stockfishchess.org/tests/view/62c26a539e7d9997a12d6cb2 Elo: 40.94 +-3.0 (95%) LOS: 100.0% Total: 10000 W: 2215 L: 1042 D: 6743 Ptnml(0-2): 10, 410, 3053, 1451, 76 nElo: 92.77 +-6.9 (95%) PairsRatio: 3.64 This is due to the mixing in a significant fraction of DFRC training data in the final training round. The net is trained using the easy_train.py script in the following way: ``` python easy_train.py \ --training-dataset=../Leela-dfrc_n5000.binpack \ --experiment-name=2 \ --nnue-pytorch-branch=vondele/nnue-pytorch/lossScan4 \ --additional-training-arg=--param-index=2 \ --start-lambda=1.0 \ --end-lambda=0.75 \ --gamma=0.995 \ --lr=4.375e-4 \ --start-from-engine-test-net True \ --tui=False \ --seed=$RANDOM \ --max_epoch=800 \ --auto-exit-timeout-on-training-finished=900 \ --network-testing-threads 8 \ --num-workers 12 ``` where the data set used (Leela-dfrc_n5000.binpack) is a combination of our previous best data set (mix of Leela and some SF data) and DFRC data, interleaved to form: The data is available in https://drive.google.com/drive/folders/1S9-ZiQa_3ApmjBtl2e8SyHxj4zG4V8gG?usp=sharing Leela mix: https://drive.google.com/file/d/1JUkMhHSfgIYCjfDNKZUMYZt6L5I7Ra6G/view?usp=sharing DFRC: https://drive.google.com/file/d/17vDaff9LAsVo_1OfsgWAIYqJtqR8aHlm/view?usp=sharing The training branch used is https://github.com/vondele/nnue-pytorch/commits/lossScan4 A PR to the main trainer repo will be made later. This contains a revised loss function, now computing the loss from the score based on the win rate model, which is a more accurate representation than what we had before. Scaling constants are tweaked there as well. closes https://github.com/official-stockfish/Stockfish/pull/4100 Bench: 5186781	2022-07-04 15:42:34 +02:00
Dubslow	442c40b43d	Use NNUE complexity in search, retune related parameters This builds on ideas of xoto10 and mstembera to use more output from NNUE in the search algorithm. passed STC: https://tests.stockfishchess.org/tests/view/62ae454fe7ee5525ef88a957 LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 89208 W: 24127 L: 23753 D: 41328 Ptnml(0-2): 400, 9886, 23642, 10292, 384 passed LTC: https://tests.stockfishchess.org/tests/view/62acc6ddd89eb6cf1e0750a1 LLR: 2.93 (-2.94,2.94) <0.50,3.00> Total: 56352 W: 15430 L: 15115 D: 25807 Ptnml(0-2): 44, 5501, 16782, 5794, 55 closes https://github.com/official-stockfish/Stockfish/pull/4088 bench 5332964	2022-06-20 08:30:57 +02:00
xoto10	7f1333ccf8	Blend nnue complexity with classical. Following mstembera's test of the complexity value derived from nnue values, this change blends that idea with the old complexity calculation. STC 10+0.1: LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 42320 W: 11436 L: 11148 D: 19736 Ptnml(0-2): 209, 4585, 11263, 4915, 188 https://tests.stockfishchess.org/tests/live_elo/6295c9239c8c2fcb2bad7fd9 LTC 60+0.6: LLR: 2.98 (-2.94,2.94) <0.50,3.00> Total: 34600 W: 9393 L: 9125 D: 16082 Ptnml(0-2): 32, 3323, 10319, 3597, 29 https://tests.stockfishchess.org/tests/view/6295fd5d9c8c2fcb2bad88cf closes https://github.com/official-stockfish/Stockfish/pull/4046 Bench 6078140	2022-06-02 07:47:23 +02:00
Tomasz Sobczyk	c079acc26f	Update NNUE architecture to SFNNv5. Update network to nn-3c0aa92af1da.nnue. Architecture changes: Duplicated activation after the 1024->15 layer with squared crelu (so 15->15*2). As proposed by vondele. Trainer changes: Added bias to L1 factorization, which was previously missing (no measurable improvement but at least neutral in principle) For retraining linearly reduce lambda parameter from 1.0 at epoch 0 to 0.75 at epoch 800. reduce max_skipping_rate from 15 to 10 (compared to vondele's outstanding PR) Note: This network was trained with a ~0.8% error in quantization regarding the newly added activation function. This will be fixed in the released trainer version. Expect a trainer PR tomorrow. Note: The inference implementation cuts a corner to merge results from two activation functions. This could possibly be resolved nicer in the future. AVX2 implementation likely not necessary, but NEON is missing. First training session invocation: python3 train.py \ ../nnue-pytorch-training/data/nodes5000pv2_UHO.binpack \ ../nnue-pytorch-training/data/nodes5000pv2_UHO.binpack \ --gpus "$3," \ --threads 4 \ --num-workers 8 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=1.0 \ --max_epochs=400 \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$2 Second training session invocation: python3 train.py \ ../nnue-pytorch-training/data/T60T70wIsRightFarseerT60T74T75T76.binpack \ ../nnue-pytorch-training/data/T60T70wIsRightFarseerT60T74T75T76.binpack \ --gpus "$3," \ --threads 4 \ --num-workers 8 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --start-lambda=1.0 \ --end-lambda=0.75 \ --gamma=0.995 \ --lr=4.375e-4 \ --max_epochs=800 \ --resume-from-model /data/sopel/nnue/nnue-pytorch-training/data/exp367/nn-exp367-run3-epoch399.pt \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$2 Passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 27288 W: 7445 L: 7178 D: 12665 Ptnml(0-2): 159, 3002, 7054, 3271, 158 https://tests.stockfishchess.org/tests/view/627e8c001919125939623644 Passed LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.00> Total: 21792 W: 5969 L: 5727 D: 10096 Ptnml(0-2): 25, 2152, 6294, 2406, 19 https://tests.stockfishchess.org/tests/view/627f2a855734b18b2e2ece47 closes https://github.com/official-stockfish/Stockfish/pull/4020 Bench: 6481017	2022-05-14 12:47:22 +02:00
Joost VandeVondele	6e0680efa0	Update default net to nn-d0b74ce1e5eb.nnue train a net using training data with a heavier weight on positions having 16 pieces on the board. More specifically, with a relative weight of `i * (32-i)/(16 * 16)+1` (where i is the number of pieces on the board). This is done with the trainer branch https://github.com/glinscott/nnue-pytorch/pull/173 The command used is: ``` python train.py $datafile $datafile $restarttype $restartfile --gpus 1 --threads 4 --num-workers 12 --random-fen-skipping=3 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --features=HalfKAv2_hm^ --lambda=1.00 --max_epochs=$epochs --seed $RANDOM --default_root_dir exp/run_$i ``` The datafile is T60T70wIsRightFarseerT60T74T75T76.binpack, the restart is from the master net. passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 22728 W: 6197 L: 5945 D: 10586 Ptnml(0-2): 105, 2453, 6001, 2695, 110 https://tests.stockfishchess.org/tests/view/625cf944ff677a888877cd90 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 35664 W: 9535 L: 9264 D: 16865 Ptnml(0-2): 30, 3524, 10455, 3791, 32 https://tests.stockfishchess.org/tests/view/625d3c32ff677a888877d7ca closes https://github.com/official-stockfish/Stockfish/pull/3989 Bench: 7269563	2022-04-19 19:59:04 +02:00
Tomasz Sobczyk	cb9c2594fc	Update architecture to "SFNNv4". Update network to nn-6877cd24400e.nnue. Architecture: The diagram of the "SFNNv4" architecture: https://user-images.githubusercontent.com/8037982/153455685-cbe3a038-e158-4481-844d-9d5fccf5c33a.png The most important architectural changes are the following: * 1024x2 [activated] neurons are pairwise, elementwise multiplied (not quite pairwise due to implementation details, see diagram), which introduces a non-linearity that exhibits similar benefits to previously tested sigmoid activation (quantmoid4), while being slightly faster. * The following layer has therefore 2x less inputs, which we compensate by having 2 more outputs. It is possible that reducing the number of outputs might be beneficial (as we had it as low as 8 before). The layer is now 1024->16. * The 16 outputs are split into 15 and 1. The 1-wide output is added to the network output (after some necessary scaling due to quantization differences). The 15-wide is activated and follows the usual path through a set of linear layers. The additional 1-wide output is at least neutral, but has shown a slightly positive trend in training compared to networks without it (all 16 outputs through the usual path), and allows possibly an additional stage of lazy evaluation to be introduced in the future. Additionally, the inference code was rewritten and no longer uses a recursive implementation. This was necessitated by the splitting of the 16-wide intermediate result into two, which was impossible to do with the old implementation with ugly hacks. This is hopefully overall for the better. First session: The first session was training a network from scratch (random initialization). The exact trainer used was slightly different (older) from the one used in the second session, but it should not have a measurable effect. The purpose of this session is to establish a strong network base for the second session. Small deviations in strength do not harm the learnability in the second session. The training was done using the following command: python3 train.py \ /home/sopel/nnue/nnue-pytorch-training/data/nodes5000pv2_UHO.binpack \ /home/sopel/nnue/nnue-pytorch-training/data/nodes5000pv2_UHO.binpack \ --gpus "$3," \ --threads 4 \ --num-workers 4 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=1.0 \ --gamma=0.992 \ --lr=8.75e-4 \ --max_epochs=400 \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$2 Every 20th net was saved and its playing strength measured against some baseline at 25k nodes per move with pure NNUE evaluation (modified binary). The exact setup is not important as long as it's consistent. The purpose is to sift good candidates from bad ones. The dataset can be found https://drive.google.com/file/d/1UQdZN_LWQ265spwTBwDKo0t1WjSJKvWY/view Second session: The second training session was done starting from the best network (as determined by strength testing) from the first session. It is important that it's resumed from a .pt model and NOT a .ckpt model. The conversion can be performed directly using serialize.py The LR schedule was modified to use gamma=0.995 instead of gamma=0.992 and LR=4.375e-4 instead of LR=8.75e-4 to flatten the LR curve and allow for longer training. The training was then running for 800 epochs instead of 400 (though it's possibly mostly noise after around epoch 600). The training was done using the following command: The training was done using the following command: python3 train.py \ /data/sopel/nnue/nnue-pytorch-training/data/T60T70wIsRightFarseerT60T74T75T76.binpack \ /data/sopel/nnue/nnue-pytorch-training/data/T60T70wIsRightFarseerT60T74T75T76.binpack \ --gpus "$3," \ --threads 4 \ --num-workers 4 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=1.0 \ --gamma=0.995 \ --lr=4.375e-4 \ --max_epochs=800 \ --resume-from-model /data/sopel/nnue/nnue-pytorch-training/data/exp295/nn-epoch399.pt \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$run_id In particular note that we now use lambda=1.0 instead of lambda=0.8 (previous nets), because tests show that WDL-skipping introduced by vondele performs better with lambda=1.0. Nets were being saved every 20th epoch. In total 16 runs were made with these settings and the best nets chosen according to playing strength at 25k nodes per move with pure NNUE evaluation - these are the 4 nets that have been put on fishtest. The dataset can be found either at ftp://ftp.chessdb.cn/pub/sopel/data_sf/T60T70wIsRightFarseerT60T74T75T76.binpack in its entirety (download might be painfully slow because hosted in China) or can be assembled in the following way: Get the https://github.com/official-stockfish/Stockfish/blob/5640ad48ae5881223b868362c1cbeb042947f7b4/script/interleave_binpacks.py script. Download T60T70wIsRightFarseer.binpack https://drive.google.com/file/d/1_sQoWBl31WAxNXma2v45004CIVltytP8/view Download farseerT74.binpack http://trainingdata.farseer.org/T74-May13-End.7z Download farseerT75.binpack http://trainingdata.farseer.org/T75-June3rd-End.7z Download farseerT76.binpack http://trainingdata.farseer.org/T76-Nov10th-End.7z Run python3 interleave_binpacks.py T60T70wIsRightFarseer.binpack farseerT74.binpack farseerT75.binpack farseerT76.binpack T60T70wIsRightFarseerT60T74T75T76.binpack Tests: STC: https://tests.stockfishchess.org/tests/view/6203fb85d71106ed12a407b7 LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 16952 W: 4775 L: 4521 D: 7656 Ptnml(0-2): 133, 1818, 4318, 2076, 131 LTC: https://tests.stockfishchess.org/tests/view/62041e68d71106ed12a40e85 LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 14944 W: 4138 L: 3907 D: 6899 Ptnml(0-2): 21, 1499, 4202, 1728, 22 closes https://github.com/official-stockfish/Stockfish/pull/3927 Bench: 4919707	2022-02-10 19:54:31 +01:00
Brad Knox	ad926d34c0	Update copyright years Happy New Year! closes https://github.com/official-stockfish/Stockfish/pull/3881 No functional change	2022-01-06 15:45:45 +01:00
Joost VandeVondele	7d82f0d1f4	Update default net to nn-ac07bd334b62.nnue Trained with essentially the same data as provided and used by Farseer (mbabigian) for the previous master net. T60T70wIsRightFarseerT60T74T75T76.binpack (99GB): ['T60T70wIsRightFarseer.binpack', 'farseerT74.binpack', 'farseerT75.binpack', 'farseerT76.binpack'] using the trainer branch tweakLR1PR (https://github.com/glinscott/nnue-pytorch/pull/158) and `--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=1.00` options passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 108280 W: 28042 L: 27636 D: 52602 Ptnml(0-2): 328, 12382, 28401, 12614, 415 https://tests.stockfishchess.org/tests/view/61bcd8c257a0d0f327c34fbd passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 259296 W: 66974 L: 66175 D: 126147 Ptnml(0-2): 146, 27096, 74452, 27721, 233 https://tests.stockfishchess.org/tests/view/61bda70957a0d0f327c37817 closes https://github.com/official-stockfish/Stockfish/pull/3870 Bench: 4633875	2021-12-22 11:02:34 +01:00
farseer	3bea736a2a	Update default net to nn-4401e826ebcc.nnue Using data T60 12/1/20 to 11/2/2021, T74 4/22/21 to 7/27/21, T75 6/3/21 to 10/16/21, T76 (half of the randomly interleaved dataset due to a mistake merging) 11/10/21 to 11/21/21, wrongIsRight_nodes5000pv2.binpack, and WrongIsRight-Reloaded.binpack combined and shuffled position by position. Trained with LR=4.375e-4 and WDL filtering enabled: python train.py --smart-fen-skipping --random-fen-skipping 0 --features=HalfKAv2_hm^ --lambda=1.0 --max_epochs=800 --seed 910688689 --batch-size 16384 --progress_bar_refresh_rate 30 --threads 4 --num-workers 4 --gpus 1 --resume-from-model C:\msys64\home\Mike\nnue-pytorch\9b3d.pt E:\trainingdata\T60-T74-T75-T76-WiR-WiRR-PbyP.binpack E:\trainingdata\T60-T74-T75-T76-WiR-WiRR-PbyP.binpack Passed STC LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 41848 W: 10962 L: 10676 D: 20210 Elo +2.16 Ptnml(0-2): 142, 4699, 11016, 4865, 202 https://tests.stockfishchess.org/tests/view/61ba886857a0d0f327c2cfd6 Passed LTC LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 27776 W: 7208 L: 6953 D: 13615 Elo + 3.00 Ptnml(0-2): 14, 2808, 8007, 3027, 32 https://tests.stockfishchess.org/tests/view/61baae4d57a0d0f327c2d96f closes https://github.com/official-stockfish/Stockfish/pull/3856 Bench: 4667591	2021-12-17 18:12:47 +01:00
Joost VandeVondele	ea1ddb6aef	Update default net to nn-d93927199b3d.nnue Using the same dataset as before but slightly reduced initial LR as in https://github.com/vondele/nnue-pytorch/tree/tweakLR1 passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 51368 W: 13492 L: 13191 D: 24685 Ptnml(0-2): 168, 5767, 13526, 6042, 181 https://tests.stockfishchess.org/tests/view/61b61f43dffbe89a3580b529 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 45128 W: 11763 L: 11469 D: 21896 Ptnml(0-2): 24, 4583, 13063, 4863, 31 https://tests.stockfishchess.org/tests/view/61b6612edffbe89a3580c447 closes https://github.com/official-stockfish/Stockfish/pull/3848 Bench: 5121336	2021-12-13 07:17:25 +01:00
Joost VandeVondele	b82d93ece4	Update default net to nn-63376713ba63.nnue. same data set as previous trained nets, tuned the wdl model slightly for training. https://github.com/vondele/nnue-pytorch/tree/wdlTweak1 passed STC: https://tests.stockfishchess.org/tests/view/61abe9e456fcf33bce7d2834 LLR: 2.93 (-2.94,2.94) <0.00,2.50> Total: 31720 W: 8385 L: 8119 D: 15216 Ptnml(0-2): 117, 3534, 8273, 3838, 98 passed LTC: https://tests.stockfishchess.org/tests/view/61ac293756fcf33bce7d36cf LLR: 2.96 (-2.94,2.94) <0.50,3.00> Total: 136136 W: 35255 L: 34741 D: 66140 Ptnml(0-2): 114, 14217, 38894, 14727, 116 closes https://github.com/official-stockfish/Stockfish/pull/3836 Bench: 4667742	2021-12-07 12:40:48 +01:00
Joost VandeVondele	327060232a	Update default net to nn-cdf1785602d6.nnue Same process as in https://github.com/official-stockfish/Stockfish/commit/e4a0c6c75950bf27b6dc32490a1102499643126b with the training started from the current master net. passed STC: LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 38224 W: 10023 L: 9742 D: 18459 Ptnml(0-2): 133, 4328, 9940, 4547, 164 https://tests.stockfishchess.org/tests/view/61a8611e4ed77d629d4e836e passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 115176 W: 29783 L: 29321 D: 56072 Ptnml(0-2): 68, 12039, 32936, 12453, 92 https://tests.stockfishchess.org/tests/view/61a8963e4ed77d629d4e8d9b closes https://github.com/official-stockfish/Stockfish/pull/3830 Bench: 4829419	2021-12-04 10:31:22 +01:00
Joost VandeVondele	e4a0c6c759	Update default net to nn-4f56ecfca5b7.nnue New net trained with nnue-pytorch, started from a master net on a data set of Leela (T60.binpack+T74.binpck) Stockfish data (wrongIsRight_nodes5000pv2.binpack), and Michael Babigian's conversion of T60 Leela data (including TB7 rescoring) (farseer.binpack) available as a single interleaved binpack: https://drive.google.com/file/d/1_sQoWBl31WAxNXma2v45004CIVltytP8/view?usp=sharing The nnue-pytorch branch used is https://github.com/vondele/nnue-pytorch/tree/wdl passed STC: https://tests.stockfishchess.org/tests/view/61a3cc729f0c43dae1c71f1b LLR: 2.95 (-2.94,2.94) <0.00,2.50> Total: 49152 W: 12842 L: 12544 D: 23766 Ptnml(0-2): 154, 5542, 12904, 5804, 172 passed LTC: https://tests.stockfishchess.org/tests/view/61a43c6260afd064f2d724f1 LLR: 2.96 (-2.94,2.94) <0.50,3.00> Total: 25528 W: 6676 L: 6425 D: 12427 Ptnml(0-2): 9, 2593, 7315, 2832, 15 closes https://github.com/official-stockfish/Stockfish/pull/3816 Bench: 6885242	2021-11-29 12:56:01 +01:00
Joost VandeVondele	9ee58dc7a7	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	2021-11-26 18:16:04 +01:00
xoto10	f21a66f70d	Small clean-up, Sept 2021 Closes https://github.com/official-stockfish/Stockfish/pull/3485 No functional change	2021-10-07 09:41:57 +02:00
SFisGOD	723f48dec0	Update default net to nn-13406b1dcbe0.nnue SPSA 1: https://tests.stockfishchess.org/tests/view/6134abc425b9b35584838572 Parameters: A total of 64 net biases were tuned (hidden layer 1) Base net: nn-6762d36ad265.nnue New net: nn-c9fdeea14cb2.nnue SPSA 2: https://tests.stockfishchess.org/tests/view/61355b7e25b9b3558483860e Parameters: 256 net weights and 8 net biases (output layer) Base net: nn-c9fdeea14cb2.nnue New net: nn-0ddc28184f4c.nnue SPSA 3: https://tests.stockfishchess.org/tests/view/613737be0cd98ab40c0c9e4e Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-0ddc28184f4c.nnue New net: nn-2419828bb394.nnue SPSA 4: https://tests.stockfishchess.org/tests/view/613966ff689039fce12e0fe7 Parameters: A total of 64 net biases were tuned (hidden layer 1) Base net: nn-2419828bb394.nnue New net: nn-05d9b1ee3037.nnue SPSA 5: https://tests.stockfishchess.org/tests/view/613b4a38689039fce12e1209 Parameters: 256 net weights and 8 net biases (output layer) Base net: nn-05d9b1ee3037.nnue New net: nn-98c6ce0fc15f.nnue SPSA 6: https://tests.stockfishchess.org/tests/view/613e331515591e7c9ebc3fe9 Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-98c6ce0fc15f.nnue New net: nn-13406b1dcbe0.nnue STC: LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 82008 W: 21044 L: 20752 D: 40212 Ptnml(0-2): 264, 9341, 21525, 9587, 287 https://tests.stockfishchess.org/tests/view/613f7c6cf29dda16fcca870c LTC: LLR: 2.96 (-2.94,2.94) <0.50,3.50> Total: 182928 W: 46258 L: 45602 D: 91068 Ptnml(0-2): 107, 19448, 51712, 20076, 121 https://tests.stockfishchess.org/tests/view/613fccb97315e7c73204a48c Closes #3703 Bench: 6658747	2021-09-15 17:50:20 +02:00
SFisGOD	be63ce1bb5	Update default net to nn-6762d36ad265.nnue SPSA 1: https://tests.stockfishchess.org/tests/view/612cdb1fbb4956d8b78eb5ab Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-fe433fd8c7f6.nnue New net: nn-5f134823db04.nnue SPSA 2: https://tests.stockfishchess.org/tests/view/612fcde645091e810014af19 Parameters: A total of 64 net biases were tuned (hidden layer 1) Base net: nn-5f134823db04.nnue New net: nn-8eca5dd4e3f7.nnue SPSA 3: https://tests.stockfishchess.org/tests/view/6130822345091e810014af61 Parameters: 256 net weights and 8 net biases (output layer) Base net: nn-8eca5dd4e3f7.nnue New net: nn-4556108e4f00.nnue SPSA 4: https://tests.stockfishchess.org/tests/view/613287652ffb3c36aceb923c Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-4556108e4f00.nnue New net: nn-6762d36ad265.nnue STC: LLR: 2.96 (-2.94,2.94) <-0.50,2.50> Total: 162776 W: 41220 L: 40807 D: 80749 Ptnml(0-2): 517, 18800, 42359, 19177, 535 https://tests.stockfishchess.org/tests/view/6134107125b9b35584838559 LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.50> Total: 41056 W: 10428 L: 10156 D: 20472 Ptnml(0-2): 30, 4288, 11618, 4564, 28 https://tests.stockfishchess.org/tests/view/6134ad6525b9b3558483857a closes https://github.com/official-stockfish/Stockfish/pull/3691 Bench: 5812158	2021-09-06 14:08:22 +02:00
SFisGOD	2807dcfab6	Update default net to nn-735bba95dec0.nnue SPSA 1: https://tests.stockfishchess.org/tests/view/61286d8b62d20cf82b5ad1bd Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-33495fe25081.nnue New net: nn-83e3cf2af92b.nnue SPSA 2: https://tests.stockfishchess.org/tests/view/6129cf2162d20cf82b5ad25f Parameters: A total of 64 net biases were tuned (hidden layer 1) Base net: nn-83e3cf2af92b.nnue New net: nn-69a528eaef35.nnue SPSA 3: https://tests.stockfishchess.org/tests/view/612a0dcb62d20cf82b5ad2a0 Parameters: 256 net weights and 8 net biases (output layer) Base net: nn-69a528eaef35.nnue New net: nn-735bba95dec0.nnue STC: LLR: 2.94 (-2.94,2.94) <-0.50,2.50> Total: 95144 W: 24310 L: 23999 D: 46835 Ptnml(0-2): 232, 11059, 24748, 11232, 301 https://tests.stockfishchess.org/tests/view/612bb3be0fdf40644b4b9996 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 33632 W: 8522 L: 8271 D: 16839 Ptnml(0-2): 18, 3511, 9516, 3744, 27 https://tests.stockfishchess.org/tests/view/612ce5b9bb4956d8b78eb5b3 Closes https://github.com/official-stockfish/Stockfish/pull/3685 Bench: 5600615	2021-08-31 12:56:19 +02:00
SFisGOD	69eede7d08	Update default net to nn-33495fe25081.nnue STC: LLR: 2.95 (-2.94,2.94) <-0.50,2.50> Total: 37368 W: 9621 L: 9391 D: 18356 Ptnml(0-2): 117, 4287, 9664, 4481, 135 https://tests.stockfishchess.org/tests/view/612768165318138ee1204977 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 13328 W: 3446 L: 3246 D: 6636 Ptnml(0-2): 11, 1383, 3682, 1571, 17 https://tests.stockfishchess.org/tests/view/6127dc8d62d20cf82b5ad196 Closes https://github.com/official-stockfish/Stockfish/pull/3679 Bench: 5179347	2021-08-27 07:51:26 +02:00
SFisGOD	590447d7a1	Update default net to nn-517c4f68b5df.nnue SPSA: https://tests.stockfishchess.org/tests/view/611cf0da4977aa1525c9ca03 Parameters: 256 net weights and 8 net biases (output layer) Base net: nn-ac5605a608d6.nnue New net: nn-517c4f68b5df.nnue STC: LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 11600 W: 998 L: 851 D: 9751 Ptnml(0-2): 30, 705, 4186, 846, 33 https://tests.stockfishchess.org/tests/view/611f84524977aa1525c9cb5b LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.50> Total: 9360 W: 338 L: 243 D: 8779 Ptnml(0-2): 0, 220, 4151, 303, 6 https://tests.stockfishchess.org/tests/view/611f8c5b4977aa1525c9cb64 closes https://github.com/official-stockfish/Stockfish/pull/3667 Bench: 4844618	2021-08-22 09:09:58 +02:00
Torsten Hellwig	1946a67567	Update default net to nn-ac5605a608d6.nnue This net was created with the nnue-pytorch trainer, it used the previous master net as a starting point. The training data includes all T60 data (https://drive.google.com/drive/folders/1rzZkgIgw7G5vQMLr2hZNiUXOp7z80613), all T74 data (https://drive.google.com/drive/folders/1aFUv3Ih3-A8Vxw9064Kw_FU4sNhMHZU-) and the wrongNNUE_02_d9.binpack (https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq). The Leela data were randomly named and then concatenated. All data was merged into one binpack using interleave_binpacks.py. python3 train.py \ ../data/t60_t74_wrong.binpack \ ../data/t60_t74_wrong.binpack \ --resume-from-model ../data/nn-e8321e467bf6.pt \ --gpus 1 \ --threads 4 \ --num-workers 1 \ --batch-size 16384 \ --progress_bar_refresh_rate 300 \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=1.0 \ --max_epochs=600 \ --seed $RANDOM \ --default_root_dir ../output/exp_24 STC: LLR: 2.95 (-2.94,2.94) <-0.50,2.50> Total: 15320 W: 1415 L: 1257 D: 12648 Ptnml(0-2): 50, 1002, 5402, 1152, 54 https://tests.stockfishchess.org/tests/view/611c404a4977aa1525c9c97f LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 9440 W: 345 L: 248 D: 8847 Ptnml(0-2): 3, 222, 4175, 315, 5 https://tests.stockfishchess.org/tests/view/611c6c7d4977aa1525c9c996 LTC with UHO_XXL_+0.90_+1.19.epd: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 6232 W: 1638 L: 1459 D: 3135 Ptnml(0-2): 5, 592, 1744, 769, 6 https://tests.stockfishchess.org/tests/view/611c9b214977aa1525c9c9cb closes https://github.com/official-stockfish/Stockfish/pull/3664 Bench: 5375286	2021-08-18 09:17:22 +02:00
Tomasz Sobczyk	d61d38586e	New NNUE architecture and net Introduces a new NNUE network architecture and associated network parameters The summary of the changes: * Position for each perspective mirrored such that the king is on e..h files. Cuts the feature transformer size in half, while preserving enough knowledge to be good. See https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY/edit#heading=h.b40q4rb1w7on. * The number of neurons after the feature transformer increased two-fold, to 1024x2. This is possibly mostly due to the now very optimized feature transformer update code. * The number of neurons after the second layer is reduced from 16 to 8, to reduce the speed impact. This, perhaps surprisingly, doesn't harm the strength much. See https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY/edit#heading=h.6qkocr97fezq The AffineTransform code did not work out-of-the box with the smaller number of neurons after the second layer, so some temporary changes have been made to add a special case for InputDimensions == 8. Also additional 0 padding is added to the output for some archs that cannot process inputs by <=8 (SSE2, NEON). VNNI uses an implementation that can keep all outputs in the registers while reducing the number of loads by 3 for each 16 inputs, thanks to the reduced number of output neurons. However GCC is particularily bad at optimization here (and perhaps why the current way the affine transform is done even passed sprt) (see https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY/edit# for details) and more work will be done on this in the following days. I expect the current VNNI implementation to be improved and extended to other architectures. The network was trained with a slightly modified version of the pytorch trainer (https://github.com/glinscott/nnue-pytorch); the changes are in https://github.com/glinscott/nnue-pytorch/pull/143 The training utilized 2 datasets. dataset A - https://drive.google.com/file/d/1VlhnHL8f-20AXhGkILujnNXHwy9T-MQw/view?usp=sharing dataset B - as described in https://github.com/official-stockfish/Stockfish/commit/ba01f4b95448bcb324755f4dd2a632a57c6e67bc The training process was as following: train on dataset A for 350 epochs, take the best net in terms of elo at 20k nodes per move (it's fine to take anything from later stages of training). convert the .ckpt to .pt --resume-from-model from the .pt file, train on dataset B for <600 epochs, take the best net. Lambda=0.8, applied before the loss function. The first training command: python3 train.py \ ../nnue-pytorch-training/data/large_gensfen_multipvdiff_100_d9.binpack \ ../nnue-pytorch-training/data/large_gensfen_multipvdiff_100_d9.binpack \ --gpus "$3," \ --threads 1 \ --num-workers 1 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --smart-fen-skipping \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=1.0 \ --max_epochs=600 \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$2 The second training command: python3 serialize.py \ --features=HalfKAv2_hm^ \ ../nnue-pytorch-training/experiment_131/run_6/default/version_0/checkpoints/epoch-499.ckpt \ ../nnue-pytorch-training/experiment_$1/base/base.pt python3 train.py \ ../nnue-pytorch-training/data/michael_commit_b94a65.binpack \ ../nnue-pytorch-training/data/michael_commit_b94a65.binpack \ --gpus "$3," \ --threads 1 \ --num-workers 1 \ --batch-size 16384 \ --progress_bar_refresh_rate 20 \ --smart-fen-skipping \ --random-fen-skipping 3 \ --features=HalfKAv2_hm^ \ --lambda=0.8 \ --max_epochs=600 \ --resume-from-model ../nnue-pytorch-training/experiment_$1/base/base.pt \ --default_root_dir ../nnue-pytorch-training/experiment_$1/run_$2 STC: https://tests.stockfishchess.org/tests/view/611120b32a8a49ac5be798c4 LLR: 2.97 (-2.94,2.94) <-0.50,2.50> Total: 22480 W: 2434 L: 2251 D: 17795 Ptnml(0-2): 101, 1736, 7410, 1865, 128 LTC: https://tests.stockfishchess.org/tests/view/611152b32a8a49ac5be798ea LLR: 2.93 (-2.94,2.94) <0.50,3.50> Total: 9776 W: 442 L: 333 D: 9001 Ptnml(0-2): 5, 295, 4180, 402, 6 closes https://github.com/official-stockfish/Stockfish/pull/3646 bench: 5189338	2021-08-15 12:05:43 +02:00
SFisGOD	73ef5b8c4a	Update default net to nn-46832cfbead3.nnue SPSA 1: https://tests.stockfishchess.org/tests/view/6100e7f096b86d98abf6a832 Parameters: A total of 256 net weights and 8 net biases were tuned (output layer) Base net: nn-56a5f1c4173a.nnue New net: nn-ec3c8e029926.nnue SPSA 2: https://tests.stockfishchess.org/tests/view/610733caafad2da4f4ae3da7 Parameters: A total of 256 net biases were tuned (hidden layer 2) Base net: nn-ec3c8e029926.nnue New net: nn-46832cfbead3.nnue STC: LLR: 2.98 (-2.94,2.94) <-0.50,2.50> Total: 50520 W: 3953 L: 3765 D: 42802 Ptnml(0-2): 138, 3063, 18678, 3235, 146 https://tests.stockfishchess.org/tests/view/610a79692a8a49ac5be793f4 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 57256 W: 1723 L: 1566 D: 53967 Ptnml(0-2): 12, 1442, 25568, 1589, 17 https://tests.stockfishchess.org/tests/view/610ac5bb2a8a49ac5be79434 Closes https://github.com/official-stockfish/Stockfish/pull/3642 Bench: 5359314	2021-08-05 08:52:07 +02:00
SFisGOD	e973eee919	Update default net to nn-56a5f1c4173a.nnue SPSA 1: https://tests.stockfishchess.org/tests/view/60fd24efd8a6b65b2f3a796e Parameters: A total of 256 net biases were tuned (hidden layer 2) New best values: Half of the changes from the tuning run New net: nn-5992d3ba79f3.nnue SPSA 2: https://tests.stockfishchess.org/tests/view/60fec7d6d8a6b65b2f3a7aa2 Parameters: A total of 128 net biases were tuned (hidden layer 1) New best values: Half of the changes from the tuning run New net: nn-56a5f1c4173a.nnue STC: LLR: 2.94 (-2.94,2.94) <-0.50,2.50> Total: 140392 W: 10863 L: 10578 D: 118951 Ptnml(0-2): 347, 8754, 51718, 9021, 356 https://tests.stockfishchess.org/tests/view/610037e396b86d98abf6a79e LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.50> Total: 14216 W: 454 L: 355 D: 13407 Ptnml(0-2): 4, 323, 6356, 420, 5 https://tests.stockfishchess.org/tests/view/61019995afad2da4f4ae3a3c Closes #3633 Bench: 4801359	2021-07-29 07:35:13 +02:00
SFisGOD	237ed1ef8f	Update default net to nn-26abeed38351.nnue SPSA: https://tests.stockfishchess.org/tests/view/60fba335d8a6b65b2f3a7891 New best values: Half of the changes from the tuning run. Setting: nodestime=300 with 10+0.1 (approximate real TC is 2.5 seconds) The rest is the same as described in #3593 The change from nodestime=600 to 300 was suggested by gekkehenker to prevent time losses for some slow workers SFisGOD@94cd757#commitcomment-53324840 STC: LLR: 2.96 (-2.94,2.94) <-0.50,2.50> Total: 67448 W: 5241 L: 5036 D: 57171 Ptnml(0-2): 151, 4198, 24827, 4391, 157 https://tests.stockfishchess.org/tests/view/60fd50f2d8a6b65b2f3a798e LTC: LLR: 2.93 (-2.94,2.94) <0.50,3.50> Total: 48752 W: 1504 L: 1358 D: 45890 Ptnml(0-2): 13, 1226, 21754, 1368, 15 https://tests.stockfishchess.org/tests/view/60fd7bb2d8a6b65b2f3a79a9 Closes https://github.com/official-stockfish/Stockfish/pull/3630 Bench: 5124774	2021-07-26 07:52:59 +02:00
MichaelB7	b939c80513	Update the default net to nn-76a8a7ffb820.nnue. combined work by Serio Vieri, Michael Byrne, and Jonathan D (aka SFisGod) based on top of previous developments, by restarts from good nets. Sergio generated the net https://tests.stockfishchess.org/api/nn/nn-d8609abe8caf.nnue: The initial net nn-d8609abe8caf.nnue is trained by generating around 16B of training data from the last master net nn-9e3c6298299a.nnue, then trained, continuing from the master net, with lambda=0.2 and sampling ratio of 1. Starting with LR=2e-3, dropping LR with a factor of 0.5 until it reaches LR=5e-4. in_scaling is set to 361. No other significant changes made to the pytorch trainer. Training data gen command (generates in chunks of 200k positions): generate_training_data min_depth 9 max_depth 11 count 200000 random_move_count 10 random_move_max_ply 80 random_multi_pv 12 random_multi_pv_diff 100 random_multi_pv_depth 8 write_min_ply 10 eval_limit 1500 book noob_3moves.epd output_file_name gendata/$(date +"%Y%m%d-%H%M")_${HOSTNAME}.binpack PyTorch trainer command (Note that this only trains for 20 epochs, repeatedly train until convergence): python train.py --features "HalfKAv2^" --max_epochs 20 --smart-fen-skipping --random-fen-skipping 500 --batch-size 8192 --default_root_dir $dir --seed $RANDOM --threads 4 --num-workers 32 --gpus $gpuids --track_grad_norm 2 --gradient_clip_val 0.05 --lambda 0.2 --log_every_n_steps 50 $resumeopt $data $val See https://github.com/sergiovieri/Stockfish/tree/tools_mod/rl for the scripts used to generate data. Based on that Michael generated nn-76a8a7ffb820.nnue in the following way: The net being submitted was trained with the pytorch trainer: https://github.com/glinscott/nnue-pytorch python train.py i:/bin/all.binpack i:/bin/all.binpack --gpus 1 --threads 4 --num-workers 30 --batch-size 16384 --progress_bar_refresh_rate 30 --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --auto_lr_find True --lambda=1.0 --max_epochs=240 --seed %random%%random% --default_root_dir exp/run_109 --resume-from-model ./pt/nn-d8609abe8caf.pt This run is thus started from Segio Vieri's net nn-d8609abe8caf.nnue all.binpack equaled 4 parts Wrong_NNUE_2.binpack https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq/view?usp=sharing plus two parts of Training_Data.binpack https://drive.google.com/file/d/1RFkQES3DpsiJqsOtUshENtzPfFgUmEff/view?usp=sharing Each set was concatenated together - making one large Wrong_NNUE 2 binpack and one large Training so the were approximately equal in size. They were then interleaved together. The idea was to give Wrong_NNUE.binpack closer to equal weighting with the Training_Data binpack model.py modifications: loss = torch.pow(torch.abs(p - q), 2.6).mean() LR = 8.0e-5 calculated as follows: 1.5e-3*(.992^360) - the idea here was to take a highly trained net and just use all.binpack as a finishing micro refinement touch for the last 2 Elo or so. This net was discovered on the 59th epoch. optimizer = ranger.Ranger(train_params, betas=(.90, 0.999), eps=1.0e-7, gc_loc=False, use_gc=False) scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=1, gamma=0.992) For this micro optimization, I had set the period to "5" in train.py. This changes the checkpoint output so that every 5th checkpoint file is created The final touches were to adjust the NNUE scale, as was done by Jonathan in tests running at the same time. passed LTC https://tests.stockfishchess.org/tests/view/60fa45aed8a6b65b2f3a77a4 LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 53040 W: 1732 L: 1575 D: 49733 Ptnml(0-2): 14, 1432, 23474, 1583, 17 passed STC https://tests.stockfishchess.org/tests/view/60f9fee2d8a6b65b2f3a7775 LLR: 2.94 (-2.94,2.94) <-0.50,2.50> Total: 37928 W: 3178 L: 3001 D: 31749 Ptnml(0-2): 100, 2446, 13695, 2623, 100. closes https://github.com/official-stockfish/Stockfish/pull/3626 Bench: 5169957	2021-07-24 18:04:59 +02:00
SFisGOD	8fc297c506	Update default net to nn-9e3c6298299a.nnue Optimization of nn-956480d8378f.nnue using SPSA https://tests.stockfishchess.org/tests/view/60da2bf63beab81350ac9fe7 Same method as described in PR #3593 STC: LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 17792 W: 1525 L: 1372 D: 14895 Ptnml(0-2): 28, 1156, 6401, 1257, 54 https://tests.stockfishchess.org/tests/view/60deffc59ea99d7c2d693c19 LTC: LLR: 2.96 (-2.94,2.94) <0.50,3.50> Total: 36544 W: 1245 L: 1109 D: 34190 Ptnml(0-2): 12, 988, 16139, 1118, 15 https://tests.stockfishchess.org/tests/view/60df11339ea99d7c2d693c22 closes https://github.com/official-stockfish/Stockfish/pull/3601 Bench: 4687476	2021-07-03 10:03:32 +02:00
SFisGOD	49283d3a66	Update default net to nn-3475407dc199.nnue Optimization of eight subnetwork output layers of Michael's nn-190f102a22c3.nnue using SPSA https://tests.stockfishchess.org/tests/view/60d5510642a522cc50282ef3 Parameters: A total of 256 net weights and 8 net biases were tuned New best values: The raw values at the end of the tuning run were used (800k games, 5 seconds TC) Settings: default ck value and SPSA A is 30,000 (3.75% of the total number of games) STC: LLR: 2.94 (-2.94,2.94) <-0.50,2.50> Total: 29064 W: 2435 L: 2269 D: 24360 Ptnml(0-2): 72, 1857, 10505, 2029, 69 https://tests.stockfishchess.org/tests/view/60d8ea123beab81350ac9eb6 LTC: LLR: 2.93 (-2.94,2.94) <0.50,3.50> Total: 61848 W: 2055 L: 1884 D: 57909 Ptnml(0-2): 18, 1708, 27310, 1861, 27 https://tests.stockfishchess.org/tests/view/60d8f0393beab81350ac9ec6 closes https://github.com/official-stockfish/Stockfish/pull/3593 Bench: 4770936	2021-06-28 21:31:58 +02:00
MichaelB7	b94a651878	Make net nn-956480d8378f.nnue the default Trained with the pytorch trainer: https://github.com/glinscott/nnue-pytorch python train.py i:/bin/all.binpack i:/bin/all.binpack --gpus 1 --threads 4 --num-workers 30 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --lambda=1.0 --max_epochs=440 --seed %random%%random% --default_root_dir exp/run_18 --resume-from-model ./pt/nn-75980ca503c6.pt This run is thus started from a previous master net. all.binpack equaled 4 parts Wrong_NNUE_2.binpack https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq/view?usp=sharing plus two parts of Training_Data.binpack https://drive.google.com/file/d/1RFkQES3DpsiJqsOtUshENtzPfFgUmEff/view?usp=sharing Each set was concatenated together - making one large Wrong_NNUE 2 binpack and one large Training so the were approximately equal in size. They were then interleaved together. The idea was to give Wrong_NNUE.binpack closer to equal weighting with the Training_Data binpack passed STC: https://tests.stockfishchess.org/tests/view/60d0c0a7a8ec07dc34c072b2 LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 18440 W: 1693 L: 1531 D: 15216 Ptnml(0-2): 67, 1225, 6464, 1407, 57 passed LTC: https://tests.stockfishchess.org/tests/view/60d762793beab81350ac9d72 LLR: 2.98 (-2.94,2.94) <0.50,3.50> Total: 93120 W: 3152 L: 2933 D: 87035 Ptnml(0-2): 48, 2581, 41076, 2814, 41 passed LTC (rebased branch to current master): https://tests.stockfishchess.org/tests/view/60d85eeb3beab81350ac9e2b LLR: 2.96 (-2.94,2.94) <0.50,3.50> Total: 42688 W: 1347 L: 1206 D: 40135 Ptnml(0-2): 14, 1097, 18981, 1238, 14. closes https://github.com/official-stockfish/Stockfish/pull/3592 Bench: 4906727	2021-06-28 21:20:05 +02:00
MichaelB7	9b82414b67	Make net nn-190f102a22c3.nnue the default net. Trained with the pytorch trainer: https://github.com/glinscott/nnue-pytorch python train.py i:/bin/all.binpack i:/bin/all.binpack --gpus 1 --threads 4 --num-workers 30 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --lambda=1.0 --max_epochs=440 --seed %random%%random% --default_root_dir exp/run_17 --resume-from-model ./pt/nn-75980ca503c6.pt This run is thus started from the previous master net. all.binpack equaled 4 parts Wrong_NNUE_2.binpack https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq/view?usp=sharing plus two parts of Training_Data.binpack https://drive.google.com/file/d/1RFkQES3DpsiJqsOtUshENtzPfFgUmEff/view?usp=sharing Each set was concatenated together - making one large Wrong_NNUE 2 binpack and one large Training so the were approximately equal in size. They were then interleaved together. The idea was to give Wrong_NNUE.binpack closer to equal weighting with the Training_Data binpack passed LTC https://tests.stockfishchess.org/tests/view/60d09f52b4c17000d679517f LLR: 2.93 (-2.94,2.94) <0.50,3.50> Total: 32184 W: 1100 L: 970 D: 30114 Ptnml(0-2): 10, 878, 14193, 994, 17 passed STC https://tests.stockfishchess.org/tests/view/60d086c02114332881e7368e LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 11360 W: 1056 L: 906 D: 9398 Ptnml(0-2): 25, 735, 4026, 853, 41 closes https://github.com/official-stockfish/Stockfish/pull/3576 Bench: 4631244	2021-06-21 23:16:55 +02:00
MichaelB7	ba01f4b954	Make net nn-75980ca503c6.nnue the default. trained with the Python command c:\nnue>python train.py i:/bin/all.binpack i:/bin/all.binpack --gpus 1 --threads 4 --num-workers 30 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --lambda=1.0 --max_epochs=440 --seed %random%%random% --default_root_dir exp/run_10 --resume-from-model ./pt/nn-3b20abec10c1.pt ` all.binpack equaled 4 parts Wrong_NNUE_2.binpack https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq/view?usp=sharing plus two parts of Training_Data.binpack https://drive.google.com/file/d/1RFkQES3DpsiJqsOtUshENtzPfFgUmEff/view?usp=sharing Each set was concatenated together - making one large Wrong_NNUE 2 binpack and one large Training so the were approximately equal in size. They were then interleaved together. The idea was to give Wrong_NNUE.binpack closer to equal weighting with the Training_Data binpack . Net nn-3b20abec10c1.nnue was chosen as the --resume-from-model with the idea that through learning, the manually hex edited values will be learned and will not need to be manually adjusted going forward. They would also be fine tuned by the learning process. passed STC: https://tests.stockfishchess.org/tests/view/60cdf91e457376eb8bcab66f LLR: 2.95 (-2.94,2.94) <-0.50,2.50> Total: 18256 W: 1639 L: 1479 D: 15138 Ptnml(0-2): 59, 1179, 6505, 1313, 72 passed LTC: https://tests.stockfishchess.org/tests/view/60ce2166457376eb8bcab6e1 LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 18792 W: 654 L: 542 D: 17596 Ptnml(0-2): 9, 490, 8291, 592, 14 closes https://github.com/official-stockfish/Stockfish/pull/3570 Bench: 5020972	2021-06-19 23:24:35 +02:00
Tomasz Sobczyk	2e745956c0	Change trace with NNUE eval support This patch adds some more output to the `eval` command. It adds a board display with estimated piece values (method is remove-piece, evaluate, put-piece), and splits the NNUE evaluation with (psqt,layers) for each bucket for the NNUE net. Example: ``` ./stockfish position fen 3Qb1k1/1r2ppb1/pN1n2q1/Pp1Pp1Pr/4P2p/4BP2/4B1R1/1R5K b - - 11 40 eval Contributing terms for the classical eval: +------------+-------------+-------------+-------------+ \| Term \| White \| Black \| Total \| \| \| MG EG \| MG EG \| MG EG \| +------------+-------------+-------------+-------------+ \| Material \| ---- ---- \| ---- ---- \| -0.73 -1.55 \| \| Imbalance \| ---- ---- \| ---- ---- \| -0.21 -0.17 \| \| Pawns \| 0.35 -0.00 \| 0.19 -0.26 \| 0.16 0.25 \| \| Knights \| 0.04 -0.08 \| 0.12 -0.01 \| -0.08 -0.07 \| \| Bishops \| -0.34 -0.87 \| -0.17 -0.61 \| -0.17 -0.26 \| \| Rooks \| 0.12 0.00 \| 0.08 0.00 \| 0.04 0.00 \| \| Queens \| 0.00 0.00 \| -0.27 -0.07 \| 0.27 0.07 \| \| Mobility \| 0.84 1.76 \| 0.01 0.66 \| 0.83 1.10 \| \|King safety \| -0.99 -0.17 \| -0.72 -0.10 \| -0.27 -0.07 \| \| Threats \| 0.27 0.27 \| 0.73 0.86 \| -0.46 -0.59 \| \| Passed \| 0.00 0.00 \| 0.79 0.82 \| -0.79 -0.82 \| \| Space \| 0.61 0.00 \| 0.24 0.00 \| 0.37 0.00 \| \| Winnable \| ---- ---- \| ---- ---- \| 0.00 -0.03 \| +------------+-------------+-------------+-------------+ \| Total \| ---- ---- \| ---- ---- \| -1.03 -2.14 \| +------------+-------------+-------------+-------------+ NNUE derived piece values: +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| \| \| Q \| b \| \| k \| \| \| \| \| \| +12.4 \| -1.62 \| \| \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| r \| \| \| p \| p \| b \| \| \| \| -3.89 \| \| \| -0.84 \| -1.19 \| -3.32 \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| p \| N \| \| n \| \| \| q \| \| \| -1.81 \| +3.71 \| \| -4.82 \| \| \| -5.04 \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| P \| p \| \| P \| p \| \| P \| r \| \| +1.16 \| -0.91 \| \| +0.55 \| +0.12 \| \| +0.50 \| -4.02 \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| \| \| \| P \| \| \| p \| \| \| \| \| \| +2.33 \| \| \| +1.17 \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| \| \| \| B \| P \| \| \| \| \| \| \| \| +4.79 \| +1.54 \| \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| \| \| \| B \| \| R \| \| \| \| \| \| \| +4.54 \| \| +6.03 \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ \| \| R \| \| \| \| \| \| K \| \| \| +4.81 \| \| \| \| \| \| \| +-------+-------+-------+-------+-------+-------+-------+-------+ NNUE network contributions (Black to move) +------------+------------+------------+------------+ \| Bucket \| Material \| Positional \| Total \| \| \| (PSQT) \| (Layers) \| \| +------------+------------+------------+------------+ \| 0 \| + 0.32 \| - 1.46 \| - 1.13 \| \| 1 \| + 0.25 \| - 0.68 \| - 0.43 \| \| 2 \| + 0.46 \| - 1.72 \| - 1.25 \| \| 3 \| + 0.55 \| - 1.80 \| - 1.25 \| \| 4 \| + 0.48 \| - 1.77 \| - 1.29 \| \| 5 \| + 0.40 \| - 2.00 \| - 1.60 \| \| 6 \| + 0.57 \| - 2.12 \| - 1.54 \| <-- this bucket is used \| 7 \| + 3.38 \| - 2.00 \| + 1.37 \| +------------+------------+------------+------------+ Classical evaluation -1.00 (white side) NNUE evaluation +1.54 (white side) Final evaluation +2.38 (white side) [with scaled NNUE, hybrid, ...] ``` Also renames the export_net() function to save_eval() while there. closes https://github.com/official-stockfish/Stockfish/pull/3562 No functional change	2021-06-19 11:57:01 +02:00
Joost VandeVondele	adfb23c029	Make net nn-50144f835024.nnue the default trained with the Python command c:\nnue>python train.py i:/bin/all.binpack i:/bin/all.binpack --gpus 1 --threads 4 --num-workers 30 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --lambda=1.0 --max_epochs=440 --seed %random%%random% --default_root_dir exp/run_8 --resume-from-model ./pt/nn-6ad41a9207d0.pt ` all.binpack equaled 4 parts Wrong_NNUE_2.binpack https://drive.google.com/file/d/1seGNOqcVdvK_vPNq98j-zV3XPE5zWAeq/view?usp=sharing plus two parts of Training_Data.binpack https://drive.google.com/file/d/1RFkQES3DpsiJqsOtUshENtzPfFgUmEff/view?usp=sharing Each set was concatenated together - make one large Wrong_NNUE 2 binpack and one large Training_Data of approximate size. They were then interleaved together. The idea was to give Wrong_NNUE.binpack closer to equal weighting with the Training _Data binpack . nn-6ad41a9207d0.pt was derived from a net vondele ran which passed STC quickly, but faltered in LTC. https://tests.stockfishchess.org/tests/view/60cba666457376eb8bcab443 STC: LLR: 2.95 (-2.94,2.94) <-0.50,2.50> Total: 18792 W: 2068 L: 1889 D: 14835 Ptnml(0-2): 82, 1480, 6117, 1611, 106 https://tests.stockfishchess.org/tests/view/60ccda8b457376eb8bcab568 LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 11376 W: 574 L: 454 D: 10348 Ptnml(0-2): 4, 412, 4747, 510, 15 https://tests.stockfishchess.org/tests/view/60ccf952457376eb8bcab58d closes https://github.com/official-stockfish/Stockfish/pull/3568 Bench: 4900906	2021-06-18 23:50:26 +02:00
SFisGOD	86afb6a7cf	Update default net to nn-aa9d7eeb397e.nnue Optimization of vondele's nn-33c9d39e5eb6.nnue using SPSA https://tests.stockfishchess.org/tests/view/60ca68be457376eb8bcab28b Setting: ck values are default based on how large the parameters are The new values for this net are the raw values at the end of the tuning (80k games) The significant changes are in buckets 1 and 2 (5-12 pieces) so the main difference is in playing endgames if we compare it to nn-33c9. There is also change in bucket 7 (29-32 pieces) but not as substantial as the changes in buckets 1 and 2. If we interpret the changes based on an experiment a few months ago, this new net plays more optimistically during endgames and less optimistically during openings. STC: LLR: 2.93 (-2.94,2.94) <-0.50,2.50> Total: 49504 W: 4246 L: 4053 D: 41205 Ptnml(0-2): 140, 3282, 17749, 3407, 174 https://tests.stockfishchess.org/tests/view/60cbd752457376eb8bcab478 LTC: LLR: 2.95 (-2.94,2.94) <0.50,3.50> Total: 88720 W: 4926 L: 4651 D: 79143 Ptnml(0-2): 105, 4048, 35793, 4295, 119 https://tests.stockfishchess.org/tests/view/60cc7828457376eb8bcab4fa closes https://github.com/official-stockfish/Stockfish/pull/3566 Bench: 4758885	2021-06-18 21:29:14 +02:00
ap	14b673d90f	New default net nn-3b20abec10c1.nnue This net was created by @pleomati, who manually edited with an hex editor 10 values randomly chosen in the LCSFNet10 net (nn-6ad41a9207d0.nnue) to create this one. The LCSFNet10 net was trained by Joost VandeVondele from a dataset combining Stockfish games and Leela games (16x10^9 positions from SF self-play at depth 9, and 6.3x10^9 positions from Leela games, so overall 72% of Stockfish positions and 28% of Leela positions). passed STC 10+0.1: LLR: 2.94 (-2.94,2.94) <-0.50,2.50> Total: 50888 W: 5881 L: 5654 D: 39353 Ptnml(0-2): 281, 4290, 16085, 4497, 291 https://tests.stockfishchess.org/tests/view/60cbfa68457376eb8bcab49a passed LTC 60+0.6: LLR: 2.94 (-2.94,2.94) <0.50,3.50> Total: 25480 W: 1498 L: 1338 D: 22644 Ptnml(0-2): 36, 1155, 10193, 1325, 31 https://tests.stockfishchess.org/tests/view/60cc4af8457376eb8bcab4d4 closes https://github.com/official-stockfish/Stockfish/pull/3564 Bench: 4904930	2021-06-18 20:00:13 +02:00

1 2 3 4

196 Commits