Update default net to nn-3c0054ea9860.nnu #4100
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 Stephane 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. Bench: 5186781
|
You Stockfish people are heroes. We're all with you in this struggle for justice. |
|
merged via 85f8ee6, congrats :-) :-) |
vondele
added a commit
to vondele/nnue-pytorch
that referenced
this pull request
Jul 5, 2022
this refines the loss function to the form used for the new master net in official-stockfish/Stockfish#4100 The new loss function uses the expect game score to learn, making the the learning more sensitive to those scores between loss and draw, draw and win. Most visible for smaller values of the scaling parameter, but the current ones have been optimized. it also introduces param_index for simpler explorations of paramers, i.e. simple parameter scans.
vondele
added a commit
to vondele/nnue-pytorch
that referenced
this pull request
Jul 5, 2022
this refines the loss function to the form used for the new master net in official-stockfish/Stockfish#4100 The new loss function uses the expect game score to learn, making the the learning more sensitive to those scores between loss and draw, draw and win. Most visible for smaller values of the scaling parameter, but the current ones have been optimized. it also introduces param_index for simpler explorations of paramers, i.e. simple parameter scans.
vondele
added a commit
to vondele/Stockfish
that referenced
this pull request
Jul 13, 2022
using trainer branch official-stockfish/nnue-pytorch#208 with a slightly tweaked loss function (power 2.5 instead of 2.6), otherwise same training as in the previous net update official-stockfish#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 Bench: 5905619
vondele
added a commit
to vondele/Stockfish
that referenced
this pull request
Jul 13, 2022
using trainer branch official-stockfish/nnue-pytorch#208 with a slightly tweaked loss function (power 2.5 instead of 2.6), otherwise same training as in the previous net update official-stockfish#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 official-stockfish#4107 Bench: 5905619
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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 Stephane 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:
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.
Bench: 5186781