Chess2u
Would you like to react to this message? Create an account in a few clicks or log in to continue.

Chess2uLog in

stockfish of the neural network

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: KJE-98
Date: Sun Apr 17 21:38:05 2022 +0200
Timestamp: 1650224285

Decrease LMR at PV nodes with low depth.

This patch lessens the Late Move Reduction at PV nodes with low depth. Previously the affect of depth on LMR was independant of nodeType. The idea behind this patch is that at PV nodes, LMR at low depth is will miss out on potential alpha-raising moves.

Passed STC:
https://tests.stockfishchess.org/tests/view/625aa867d3367522c4b8965c
LLR: 2.93 (-2.94,2.94) <0.00,2.50>
Total: 19360 W: 5252 L: 5006 D: 9102 Elo +4.41
Ptnml(0-2): 79, 2113, 5069, 2321, 98

Passed LTC:
https://tests.stockfishchess.org/tests/view/625ae844d3367522c4b8a009
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 39264 W: 10636 L: 10357 D: 18271 Elo +2.47
Ptnml(0-2): 18, 3928, 11473, 4183, 30

closes https://github.com/official-stockfish/Stockfish/pull/3985

bench: 8129754

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Stockfish 15

Official release version of Stockfish 15

Bench: 8129754

---

A new major release of Stockfish is now available at https://stockfishchess.org

Stockfish 15 continues to push the boundaries of chess, providing unrivalled
analysis and playing strength. In our testing, Stockfish 15 is ahead of
Stockfish 14 by 36 Elo points and wins nine times more game pairs than it
loses[1].

Improvements to the engine have made it possible for Stockfish to end up
victorious in tournaments at all sorts of time controls ranging from bullet to
classical and even at Fischer random chess[2]. At CCC, Stockfish won all of
the latest tournaments: CCC 16 Bullet, Blitz and Rapid, CCC 960 championship,
and the CCC 17 Rapid. At TCEC, Stockfish won the Season 21, Cup 9, FRC 4 and
in the current Season 22 superfinal, at the time of writing, has won 16 game
pairs and not yet lost a single one.

This progress is the result of a dedicated team of developers that comes up
with new ideas and improvements. For Stockfish 15, we tested nearly 13000
different changes and retained the best 200. These include the fourth
generation of our NNUE network architecture, as well as various search
improvements. To perform these tests, contributors provide CPU time for
testing, and in the last year, they have collectively played roughly a
billion chess games. In the last few years, our distributed testing
framework, Fishtest, has been operated superbly and has been developed and
improved extensively. This work by Pasquale Pigazzini, Tom Vijlbrief, Michel
Van den Bergh, and various other developers[3] is an essential part of the
success of the Stockfish project.

Indeed, the Stockfish project builds on a thriving community of enthusiasts
to offer a free and open-source chess engine that is robust, widely
available, and very strong. We invite our chess fans to join the Fishtest
testing framework and programmers to contribute to the project[4].

The Stockfish team

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
SF-PB-15_x64.
Engines https://pixeldrain.com/u/zTk1pQiv

Network https://tests.stockfishchess.org/api/nn/nn-6877cd24400e.nnue

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
thank u clap

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: Joost VandeVondele
Date: Tue Apr 19 19:59:04 2022 +0200
Timestamp: 1650391144

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 Elo +3.85
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 Elo +2.64
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
see source

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
SF-PB-190422_x64 "Update default net to nn-d0b74ce1e5eb.nnue"
Engines https://pixeldrain.com/u/PA6L2SPD

Network https://tests.stockfishchess.org/api/nn/nn-d0b74ce1e5eb.nnue

virustotal https://www.virustotal.com/gui/file/4156cef5f694867fa6585261fdc150c305f8cc237d6cad90289afeef654aad35?nocache=1

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: Michael Chaly
Date: Fri Apr 22 08:09:40 2022 +0200
Timestamp: 1650607780

Simplify away best move count logic

the only place where it was used it was true with >99% probability so it seemed to not be doing much any more.

Passed STC:
https://tests.stockfishchess.org/tests/view/625f4778d00da81c22dd4c93
LLR: 2.95 (-2.94,2.94) <-2.25,0.25>
Total: 85152 W: 22487 L: 22406 D: 40259 Elo +0.33
Ptnml(0-2): 313, 9035, 23818, 9078, 332

Passed LTC:
https://tests.stockfishchess.org/tests/view/625ff1f1b03f22647441a215
LLR: 2.94 (-2.94,2.94) <-2.25,0.25>
Total: 66776 W: 17768 L: 17673 D: 31335 Elo +0.49
Ptnml(0-2): 46, 6200, 20792, 6313, 37

close https://github.com/official-stockfish/Stockfish/pull/3993

bench 7280798

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: candirufish
Date: Fri Apr 22 08:17:22 2022 +0200
Timestamp: 1650608242

Negative extension for ttMove that is less than alpha and value

in the context of singular extensions

Passed STC:
https://tests.stockfishchess.org/tests/view/626047e8b03f22647441ade0
LLR: 2.97 (-2.94,2.94) <0.00,2.50>
Total: 50296 W: 13410 L: 13108 D: 23778 Elo +2.09
Ptnml(0-2): 196, 5548, 13370, 5826, 208

Passed LTC:
https://tests.stockfishchess.org/tests/view/6260a513b03f22647441b970
LLR: 2.96 (-2.94,2.94) <0.50,3.00>
Total: 83896 W: 22433 L: 22054 D: 39409 Elo +1.57
Ptnml(0-2): 49, 8273, 24938, 8626, 62

closes https://github.com/official-stockfish/Stockfish/pull/3995

bench: 7729968

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: candirufish
Date: Tue May 3 17:58:01 2022 +0200

Author: Stefan Geschwentner
Date: Tue May 3 17:54:23 2022 +0200

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Date: Wed May 04 , 2022
Author: Stéphane Nicolet   :music2:

Download : https://abrok.eu/stockfish/

Timestamp: 1651643276

Reduce depth after score improvement at PV nodes

STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 73760 W: 19590 L: 19244 D: 34926 Elo +1.63
Ptnml(0-2): 285, 8352, 19292, 8634, 317
https://tests.stockfishchess.org/tests/view/626eb2dc9116b52aa83b73da

LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 114400 W: 30561 L: 30111 D: 53728 Elo +1.37
Ptnml(0-2): 68, 11432, 33785, 11812, 103
https://tests.stockfishchess.org/tests/view/626f730859e9c431e0b10b21

closes https://github.com/official-stockfish/Stockfish/pull/4008

bench: 6174823

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
ChessFan1 wrote:
Date: Wed May 04 , 2022
Author: Stéphane Nicolet   :music2:

Download : https://abrok.eu/stockfish/

Timestamp: 1651643276

Reduce depth after score improvement at PV nodes

STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 73760 W: 19590 L: 19244 D: 34926 Elo +1.63
Ptnml(0-2): 285, 8352, 19292, 8634, 317
https://tests.stockfishchess.org/tests/view/626eb2dc9116b52aa83b73da

LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 114400 W: 30561 L: 30111 D: 53728 Elo +1.37
Ptnml(0-2): 68, 11432, 33785, 11812, 103
https://tests.stockfishchess.org/tests/view/626f730859e9c431e0b10b21

closes https://github.com/official-stockfish/Stockfish/pull/4008

bench: 6174823


Did U forget to attach Stockfish PB files?

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz

https://youtu.be/9GCz2dHc3lI

Alpha zero vs Stockfish 15

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
lisandr wrote:

https://youtu.be/9GCz2dHc3lI

Alpha zero vs Stockfish 15



It is interesting that Deep Mind did not boast about this game. I think Alpha Zero is Leela Chess Zero

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: Tomasz Sobczyk
Date: Sat May 14 12:47:22 2022 +0200
Timestamp: 1652525242

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 Elo +3.40
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 Elo +3.86
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
see source

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: disservin
Date: Sat May 14 13:17:35 2022 +0200
Timestamp: 1652527055

SE depth scaling using the previous depth

This patch makes the SE depth condition more robust and allows it to scale with completed depth
from a previous search.

At long TC this patch is almost equivalent to https://github.com/official-stockfish/Stockfish/pull/4016 which had

VLTC:
https://tests.stockfishchess.org/tests/view/626abd7e8707aa698c0093a8
Elo: 2.35 +-1.5 (95%) LOS: 99.9%
Total: 40000 W: 10991 L: 10720 D: 18289 Elo +2.35
Ptnml(0-2): 8, 3534, 12648, 3799, 11
nElo: 5.47 +-3.4 (95%) PairsRatio: 1.08

VLTC multicore:
https://tests.stockfishchess.org/tests/view/6272a6afc8f14123163c1997
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 86808 W: 24165 L: 23814 D: 38829 Elo +1.40
Ptnml(0-2): 11, 7253, 28524, 7606, 10

however, it is now also gaining at LTC:

LTC:
https://tests.stockfishchess.org/tests/view/627e7cb523c0c72a05b651a9
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 27064 W: 7285 L: 7046 D: 12733 Elo +3.07
Ptnml(0-2): 8, 2446, 8390, 2675, 13

and should have nearly no influence at STC as depth 27 is rarely reached.
It was noticed that initializing the threshold with MAX_PLY, had an adverse effect,
possibly because the first move is sensitive to this.

closes https://github.com/official-stockfish/Stockfish/pull/4021
closes https://github.com/official-stockfish/Stockfish/pull/4016

Bench: 6481017

https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: Tomasz Sobczyk
Date: Sat May 14 12:47:22 2022 +0200
Timestamp: 1652525242

molim uradi te SF-PB ove varijanet

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: Tomasz Sobczyk
Date: Sat May 14 12:47:22 2022 +0200
Timestamp: 165252524

please do you SF-PB this variant

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
thumb up

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
SF-PB-140522_x64 "SE depth scaling using the previous depth" https://github.com/official-stockfish/Stockfish/commit/5372f81cc81d5be3040db6f2dbfff108c460baf9

Engines https://pixeldrain.com/u/qTRDvqnJ

Network https://tests.stockfishchess.org/api/nn/nn-3c0aa92af1da.nnue

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Thanks . but the network does not work LINK FOR THE NETWORK DOES NOT WORK think

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
zoorb wrote:
Thanks . but the network does not work LINK FOR THE NETWORK DOES NOT WORK think

Try from here (same thing) https://tests.stockfishchess.org/nns?page=1

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Progession test of "SE depth scaling using the previous depth " vs SF15 of Mai 14th

Elo: 4.52 +-0.8 (95%) LOS: 100.0%
Total: 58112 W: 3311 L: 2555 D: 52246

Ptnml(0-2): 17, 1794, 24704, 2498, 43
nElo: 16.22 +-2.8 (95%) PairsRatio: 1.40

60000 @ 60+0.6 th 1

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Author: xoto10
Date: Sun May 15 20:20:37 2022 +0200
Timestamp: 1652638837

Tune scale and optimism.

Tune scale and optimism in effort to make stockfish play more aggressively.

STC @ 10+0.1 th 1:
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 27896 W: 7506 L: 7248 D: 13142 Elo +3.21
Ptnml(0-2): 103, 3047, 7388, 3309, 101
https://tests.stockfishchess.org/tests/live_elo/627fd0cfab44257388ab1f13

LTC @ 60+0.6 th 1:
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 65576 W: 17512 L: 17178 D: 30886 Elo +1.77
Ptnml(0-2): 37, 6397, 19587, 6729, 38
https://tests.stockfishchess.org/tests/live_elo/627ff666ab44257388ab256d

closes https://github.com/official-stockfish/Stockfish/pull/4025

Bench 6407734
https://abrok.eu/stockfish/

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
SF-PB-150522_x64 "Tune scale and optimism." https://github.com/official-stockfish/Stockfish/commit/22b7909809c731aea691184dd7c1a2b02c5946af
Engines https://pixeldrain.com/u/h2s7HzYQ

Network Network https://tests.stockfishchess.org/api/nn/nn-3c0aa92af1da.nnue

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
https://tests.stockfishchess.org/api/nn/nn-3c0aa92af1da.nnue


This DOES NOT WORK without everything is therefore useless think

descriptionstockfish of the neural network - Page 19 EmptyRe: stockfish of the neural network

more_horiz
Permissions in this forum:
You cannot reply to topics in this forum