mirror of
https://github.com/official-stockfish/Stockfish.git
synced 2026-07-22 12:47:08 +00:00
4f53560d248195b172ac97d7c74e6bcfc65fe6fd
56
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Linmiao XuandJoost VandeVondele
|
c17d73c554 |
Simplify statScore divisor into a constant
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/665b392ff4a1fd0c208ea864 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 114752 W: 29628 L: 29495 D: 55629 Ptnml(0-2): 293, 13694, 29269, 13827, 293 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/665b588c11645bd3d3fac467 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 65322 W: 16549 L: 16373 D: 32400 Ptnml(0-2): 30, 7146, 18133, 7322, 30 closes https://github.com/official-stockfish/Stockfish/pull/5337 bench 1241443 |
||
|
Linmiao XuandJoost VandeVondele
|
cb4a623119 |
Update default smallnet to nn-37f18f62d772.nnue
Created by training L1-128 from scratch with:
- skipping based on simple eval in the trainer, for compatibility with
regular binpacks without requiring pre-filtering all binpacks
- minimum simple eval of 950, lower than 1000 previously
- usage of some hse-v1 binpacks with minimum simple eval 1000
- addition of hse-v6 binpacks with minimum simple eval 500
- permuting the FT with 10k positions from fishpack32.binpack
- torch.compile to speed up smallnet training
Training is significantly slower when using non-pre-filtered binpacks due to
the increased skipping required.
This net was reached at epoch 339.
```
experiment-name: 128--S1-hse-1k-T80-v6-unfilt-less-sf--se-gt950-no-wld-skip
training-dataset:
/data/:
- dfrc99-16tb7p.v2.min.binpack
/data/hse-v1/:
- leela96-filt-v2.min.high-simple-eval-1k.min-v2.binpack
- test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test77-nov2021-2tb7p.no-db.min.high-simple-eval-1k.min-v2.binpack
- test77-dec2021-16tb7p.no-db.min.high-simple-eval-1k.min-v2.binpack
- test77-jan2022-2tb7p.high-simple-eval-1k.min-v2.binpack
- test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test79-apr2022-16tb7p.min.high-simple-eval-1k.min-v2.binpack
- test79-may2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test80-apr2022-16tb7p.min.high-simple-eval-1k.min-v2.binpack
- test80-may2022-16tb7p.high-simple-eval-1k.min-v2.binpack
- test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test80-jul2022-16tb7p.v6-dd.min.high-simple-eval-1k.min-v2.binpack
- test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.min-v2.binpack
- test80-nov2022-16tb7p-v6-dd.min.high-simple-eval-1k.min-v2.binpack
/data/S11-mar2024/:
- test80-2022-08-aug-16tb7p.v6-dd.min.binpack
- test80-2022-10-oct-16tb7p.v6-dd.binpack
- test80-2022-12-dec-16tb7p.min.binpack
- test80-2023-01-jan-16tb7p.v6-sk20.min.binpack
- test80-2023-02-feb-16tb7p.v6-sk20.min.binpack
- test80-2023-03-mar-2tb7p.v6-sk16.min.binpack
- test80-2023-04-apr-2tb7p.v6-sk16.min.binpack
- test80-2023-05-may-2tb7p.v6.min.binpack
- test80-2023-06-jun-2tb7p.binpack.min-v2.binpack
- test80-2023-07-jul-2tb7p.binpack.min-v2.binpack
- test80-2023-08-aug-2tb7p.v6.min.binpack
- test80-2023-09-sep-2tb7p.binpack.hse-v6.binpack
- test80-2023-10-oct-2tb7p.binpack.hse-v6.binpack
- test80-2023-11-nov-2tb7p.binpack.hse-v6.binpack
- test80-2023-12-dec-2tb7p.binpack.hse-v6.binpack
- test80-2024-01-jan-2tb7p.binpack.hse-v6.binpack
- test80-2024-02-feb-2tb7p.binpack.hse-v6.binpack
- test80-2024-03-mar-2tb7p.binpack
wld-fen-skipping: False
nnue-pytorch-branch: linrock/nnue-pytorch/128-skipSimpleEval-lt950-torch-compile
engine-test-branch: linrock/Stockfish/L1-128-nolazy
engine-base-branch: linrock/Stockfish/L1-128
start-from-engine-test-net: False
num-epochs: 500
start-lambda: 1.0
end-lambda: 1.0
```
Training data can be found at:
https://robotmoon.com/nnue-training-data/
Passed STC:
https://tests.stockfishchess.org/tests/view/66549c16a86388d5e27daff5
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 196608 W: 51254 L: 50697 D: 94657
Ptnml(0-2): 722, 23244, 49796, 23839, 703
Passed LTC:
https://tests.stockfishchess.org/tests/view/6658d1aa6b0e318cefa90122
LLR: 2.96 (-2.94,2.94) <0.50,2.50>
Total: 122538 W: 31332 L: 30835 D: 60371
Ptnml(0-2): 69, 13407, 33811, 13922, 60
closes https://github.com/official-stockfish/Stockfish/pull/5333
bench
|
||
|
Linmiao XuandJoost VandeVondele
|
0ef809ac71 |
Quadratic smallnet threshold with re-evaluation
The threshold now decreases more quickly as pawn count decreases, using the smallnet more compared to before. Combo of two eval patches: https://tests.stockfishchess.org/tests/view/66576c5f6b0e318cefa8d26e https://tests.stockfishchess.org/tests/view/664ced40830eb9f886616a77 Passed STC: https://tests.stockfishchess.org/tests/view/66588c136b0e318cefa8ff21 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 112608 W: 29336 L: 28908 D: 54364 Ptnml(0-2): 344, 13223, 28718, 13699, 320 Passed LTC: https://tests.stockfishchess.org/tests/view/6658c8786b0e318cefa900f5 LLR: 2.96 (-2.94,2.94) <0.50,2.50> Total: 108288 W: 27493 L: 27026 D: 53769 Ptnml(0-2): 54, 11821, 29930, 12282, 57 closes https://github.com/official-stockfish/Stockfish/pull/5323 bench 1728074 |
||
|
Linmiao XuandJoost VandeVondele
|
35aff79843 |
Update default main net to nn-ddcfb9224cdb.nnue
Created by further tuning the spsa-tuned main net `nn-c721dfca8cd3.nnue` with the same methods described in https://github.com/official-stockfish/Stockfish/pull/5254 This net was reached at 61k / 120k spsa games at 70+0.7 th 7: https://tests.stockfishchess.org/tests/view/665639d0a86388d5e27dd259 Passed STC: https://tests.stockfishchess.org/tests/view/6657d44e6b0e318cefa8d771 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 114688 W: 29775 L: 29344 D: 55569 Ptnml(0-2): 274, 13633, 29149, 13964, 324 Passed LTC: https://tests.stockfishchess.org/tests/view/6657e1e46b0e318cefa8d7a6 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 88152 W: 22412 L: 21988 D: 43752 Ptnml(0-2): 56, 9560, 24409, 10006, 45 closes https://github.com/official-stockfish/Stockfish/pull/5308 Bench: 1434678 |
||
|
Linmiao XuandJoost VandeVondele
|
5ab3fe6db8 |
Simplify blending eval with nnue complexity
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/66567377a86388d5e27dd89c LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 144000 W: 37443 L: 37338 D: 69219 Ptnml(0-2): 587, 17260, 36208, 17351, 594 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/66567f29a86388d5e27dd924 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 112326 W: 28550 L: 28421 D: 55355 Ptnml(0-2): 66, 12732, 30434, 12869, 62 closes https://github.com/official-stockfish/Stockfish/pull/5305 bench 1554486 |
||
|
Linmiao XuandDisservin
|
8bc3fd3871 |
Lower smallnet threshold with tuned eval params
The smallnet threshold is now below the training data range of the current smallnet (simple eval diff > 1k, nn-baff1edelf90.nnue) when no pawns are on the board. Params found with spsa at 93k / 120k games at 60+06: https://tests.stockfishchess.org/tests/view/664fa166a86388d5e27d7d6b Tuned on top of: https://github.com/official-stockfish/Stockfish/pull/5287 Passed STC: https://tests.stockfishchess.org/tests/view/664fc8b7a86388d5e27d8dac LLR: 2.96 (-2.94,2.94) <0.00,2.00> Total: 64672 W: 16731 L: 16371 D: 31570 Ptnml(0-2): 239, 7463, 16517, 7933, 184 Passed LTC: https://tests.stockfishchess.org/tests/view/664fd5f9a86388d5e27d8dfe LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 210648 W: 53489 L: 52813 D: 104346 Ptnml(0-2): 102, 23129, 58164, 23849, 80 closes https://github.com/official-stockfish/Stockfish/pull/5288 Bench: 1717838 |
||
|
Linmiao XuandDisservin
|
365aa85dce |
Remove material imbalance param when adjusting optimism
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/664d033d830eb9f886616aff LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 102144 W: 26283 L: 26135 D: 49726 Ptnml(0-2): 292, 12201, 25991, 12243, 345 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/664d5c00830eb9f886616cb3 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 250032 W: 63022 L: 63036 D: 123974 Ptnml(0-2): 103, 27941, 68970, 27871, 131 closes https://github.com/official-stockfish/Stockfish/pull/5284 Bench: 1330940 |
||
|
Linmiao XuandDisservin
|
1dcffa6210 |
Comment about re-evaluating positions
While the smallNet bool is no longer used as of now, setting it to false upon re-evaluation represents the correct eval state. closes https://github.com/official-stockfish/Stockfish/pull/5279 No functional change |
||
|
Linmiao XuandJoost VandeVondele
|
c14b69790a |
Lower smallnet threshold with updated eval divisors
Params found after 30k spsa games at 60+0.6, with initial values from 64k spsa games at 45+0.45 First spsa with 64k / 120k games at 45+0.45: https://tests.stockfishchess.org/tests/view/664a561b5fc7b70b8817c663 https://tests.stockfishchess.org/tests/view/664ae88e830eb9f8866146f9 Second spsa with 30k / 120k games at 60+0.6: https://tests.stockfishchess.org/tests/view/664be227830eb9f886615a36 Values found at 10k games at 60+0.6 also passed STC and LTC: https://tests.stockfishchess.org/tests/view/664bf4bd830eb9f886615a72 https://tests.stockfishchess.org/tests/view/664c0905830eb9f886615abf Passed STC: https://tests.stockfishchess.org/tests/view/664c139e830eb9f886615af2 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 69408 W: 18216 L: 17842 D: 33350 Ptnml(0-2): 257, 8275, 17401, 8379, 392 Passed LTC: https://tests.stockfishchess.org/tests/view/664cdaf7830eb9f886616a24 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 35466 W: 9075 L: 8758 D: 17633 Ptnml(0-2): 27, 3783, 9794, 4104, 25 closes https://github.com/official-stockfish/Stockfish/pull/5280 bench 1301287 |
||
|
Linmiao XuandJoost VandeVondele
|
4d88a63e60 |
Re-eval only if smallnet output flips from simple eval
Recent attempts to change the smallnet nnue re-eval threshold did not show much elo difference: https://tests.stockfishchess.org/tests/view/664a29bb25a9058c4d21d53c https://tests.stockfishchess.org/tests/view/664a299925a9058c4d21d53a Passed non-regression STC: https://tests.stockfishchess.org/tests/view/664a3ea95fc7b70b8817aee2 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 22304 W: 5905 L: 5664 D: 10735 Ptnml(0-2): 67, 2602, 5603, 2783, 97 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/664a43d35fc7b70b8817aef4 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 37536 W: 9667 L: 9460 D: 18409 Ptnml(0-2): 25, 4090, 10321, 4317, 15 closes https://github.com/official-stockfish/Stockfish/pull/5271 bench 1287409 |
||
|
Linmiao XuandJoost VandeVondele
|
2694fce928 |
Simplify away adjustEval lambda
Now that only the shuffling constant differs between nets, a lambda for adjusting eval is no longer needed. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/664806ca6dcff0d1d6b05f34 LLR: 2.99 (-2.94,2.94) <-1.75,0.25> Total: 31552 W: 8175 L: 7959 D: 15418 Ptnml(0-2): 76, 3180, 9065, 3362, 93 closes https://github.com/official-stockfish/Stockfish/pull/5260 No functional change |
||
|
Linmiao XuandJoost VandeVondele
|
99dfc63e03 |
Use one nnue pawn count multiplier
Switch to the value used by the main net. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6647e8096dcff0d1d6b05e96 LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 51040 W: 13249 L: 13044 D: 24747 Ptnml(0-2): 139, 6029, 13016, 6160, 176 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6647f4a46dcff0d1d6b05eea LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 20460 W: 5195 L: 4972 D: 10293 Ptnml(0-2): 8, 2178, 5637, 2397, 10 https://github.com/official-stockfish/Stockfish/pull/5258 bench 1887462 |
||
|
Linmiao XuandJoost VandeVondele
|
d92d1f3180 |
Move smallnet threshold logic into a function
Now that the smallnet threshold is no longer a constant, use a function to organize it with other eval code. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/66459fa093ce6da3e93b5ba2 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 217600 W: 56281 L: 56260 D: 105059 Ptnml(0-2): 756, 23787, 59729, 23736, 792 closes https://github.com/official-stockfish/Stockfish/pull/5255 No functional change |
||
|
Linmiao XuandJoost VandeVondele
|
1b7dea3f85 |
Update default main net to nn-c721dfca8cd3.nnue
Created by first retraining the spsa-tuned main net `nn-ae6a388e4a1a.nnue` with: - using v6-dd data without bestmove captures removed - addition of T80 mar2024 data - increasing loss by 20% when Q is too high - torch.compile changes for marginal training speed gains And then SPSA tuning weights of epoch 899 following methods described in: https://github.com/official-stockfish/Stockfish/pull/5149 This net was reached at 92k out of 120k steps in this 70+0.7 th 7 SPSA tuning run: https://tests.stockfishchess.org/tests/view/66413b7df9f4e8fc783c9bbb Thanks to @Viren6 for suggesting usage of: - c value 4 for the weights - c value 128 for the biases Scripts for automating applying fishtest spsa params to exporting tuned .nnue are in: https://github.com/linrock/nnue-tools/tree/master/spsa Before spsa tuning, epoch 899 was nn-f85738aefa84.nnue https://tests.stockfishchess.org/tests/view/663e5c893a2f9702074bc167 After initially training with max-epoch 800, training was resumed with max-epoch 1000. ``` experiment-name: 3072--S11--more-data-v6-dd-t80-mar2024--see-ge0-20p-more-loss-high-q-sk28-l8 nnue-pytorch-branch: linrock/nnue-pytorch/3072-r21-skip-more-wdl-see-ge0-20p-more-loss-high-q-torch-compile-more start-from-engine-test-net: False start-from-model: /data/config/apr2024-3072/nn-ae6a388e4a1a.nnue early-fen-skipping: 28 training-dataset: /data/S11-mar2024/: - leela96.v2.min.binpack - test60-2021-11-12-novdec-12tb7p.v6-dd.min.binpack - test78-2022-01-to-05-jantomay-16tb7p.v6-dd.min.binpack - test80-2022-06-jun-16tb7p.v6-dd.min.binpack - test80-2022-08-aug-16tb7p.v6-dd.min.binpack - test80-2022-09-sep-16tb7p.v6-dd.min.binpack - test80-2023-01-jan-16tb7p.v6-sk20.min.binpack - test80-2023-02-feb-16tb7p.v6-sk20.min.binpack - test80-2023-03-mar-2tb7p.v6-sk16.min.binpack - test80-2023-04-apr-2tb7p.v6-sk16.min.binpack - test80-2023-05-may-2tb7p.v6.min.binpack # https://github.com/official-stockfish/Stockfish/pull/4782 - test80-2023-06-jun-2tb7p.binpack - test80-2023-07-jul-2tb7p.binpack # https://github.com/official-stockfish/Stockfish/pull/4972 - test80-2023-08-aug-2tb7p.v6.min.binpack - test80-2023-09-sep-2tb7p.binpack - test80-2023-10-oct-2tb7p.binpack # S9 new data: https://github.com/official-stockfish/Stockfish/pull/5056 - test80-2023-11-nov-2tb7p.binpack - test80-2023-12-dec-2tb7p.binpack # S10 new data: https://github.com/official-stockfish/Stockfish/pull/5149 - test80-2024-01-jan-2tb7p.binpack - test80-2024-02-feb-2tb7p.binpack # S11 new data - test80-2024-03-mar-2tb7p.binpack /data/filt-v6-dd/: - test77-dec2021-16tb7p-filter-v6-dd.binpack - test78-juntosep2022-16tb7p-filter-v6-dd.binpack - test79-apr2022-16tb7p-filter-v6-dd.binpack - test79-may2022-16tb7p-filter-v6-dd.binpack - test80-jul2022-16tb7p-filter-v6-dd.binpack - test80-oct2022-16tb7p-filter-v6-dd.binpack - test80-nov2022-16tb7p-filter-v6-dd.binpack num-epochs: 1000 lr: 4.375e-4 gamma: 0.995 start-lambda: 0.8 end-lambda: 0.7 ``` Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch899.nnue : 4.6 +/- 1.4 Passed STC: https://tests.stockfishchess.org/tests/view/6645454893ce6da3e93b31ae LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 95232 W: 24598 L: 24194 D: 46440 Ptnml(0-2): 294, 11215, 24180, 11647, 280 Passed LTC: https://tests.stockfishchess.org/tests/view/6645522d93ce6da3e93b31df LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 320544 W: 81432 L: 80524 D: 158588 Ptnml(0-2): 164, 35659, 87696, 36611, 142 closes https://github.com/official-stockfish/Stockfish/pull/5254 bench 1995552 |
||
|
Linmiao XuandDisservin
|
47597641dc |
Lower smallnet threshold linearly as pawn count decreases
Passed STC: https://tests.stockfishchess.org/tests/view/6644f677324e96f42f89d894 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 377920 W: 97135 L: 96322 D: 184463 Ptnml(0-2): 1044, 44259, 97588, 44978, 1091 Passed LTC: https://tests.stockfishchess.org/tests/view/664548af93ce6da3e93b31b3 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 169056 W: 42901 L: 42312 D: 83843 Ptnml(0-2): 58, 18538, 46753, 19115, 64 closes https://github.com/official-stockfish/Stockfish/pull/5252 Bench: 1991750 |
||
|
Linmiao XuandDisservin
|
541406ab91 |
Use same nnue divisor for both nets
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6643ceeabc537f56194506f6 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 224800 W: 57910 L: 57896 D: 108994 Ptnml(0-2): 673, 26790, 57519, 26686, 732 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6643ff15bc537f5619451719 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 347658 W: 87574 L: 87688 D: 172396 Ptnml(0-2): 207, 39004, 95488, 38956, 174 closes https://github.com/official-stockfish/Stockfish/pull/5250 Bench: 1804704 |
||
|
Linmiao XuandDisservin
|
1f3a0fda2e |
Use same eval divisor for both nets
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/66428f146577e9d2c8a29cf8 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 241024 W: 62173 L: 62177 D: 116674 Ptnml(0-2): 904, 28648, 61407, 28654, 899 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6643ae6f1f32a966da74977b LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 193710 W: 48762 L: 48717 D: 96231 Ptnml(0-2): 70, 21599, 53481, 21626, 79 closes https://github.com/official-stockfish/Stockfish/pull/5246 Bench: 1700680 |
||
|
|
0b08953174 |
Re-evaluate some small net positions for more accurate evals
Use main net evals when small net evals hint that higher eval accuracy may be worth the slower eval speeds. With Finny caches, re-evals with the main net are less expensive than before. Original idea by mstembera who I've added as co-author to this PR. Based on reEval tests by mstembera: https://tests.stockfishchess.org/tests/view/65e69187b6345c1b934866e5 https://tests.stockfishchess.org/tests/view/65e863aa0ec64f0526c3e991 A few variants of this patch also passed LTC: https://tests.stockfishchess.org/tests/view/663d2108507ebe1c0e91f407 https://tests.stockfishchess.org/tests/view/663e388c3a2f9702074bc152 Passed STC: https://tests.stockfishchess.org/tests/view/663dadbd1a61d6377f190e2c LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 92320 W: 23941 L: 23531 D: 44848 Ptnml(0-2): 430, 10993, 22931, 11349, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/663ef48b2948bf9aa698690c LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 98934 W: 24907 L: 24457 D: 49570 Ptnml(0-2): 48, 10952, 27027, 11382, 58 closes https://github.com/official-stockfish/Stockfish/pull/5238 bench 1876282 Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com> |
||
|
Linmiao XuandJoost VandeVondele
|
53f363041c |
Simplify npm constants when adjusting eval
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/663d0c4f507ebe1c0e91ec8d LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 162784 W: 41987 L: 41906 D: 78891 Ptnml(0-2): 520, 19338, 41591, 19427, 516 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/663d20fd507ebe1c0e91f405 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 457242 W: 115022 L: 115250 D: 226970 Ptnml(0-2): 271, 51566, 125179, 51330, 275 closes https://github.com/official-stockfish/Stockfish/pull/5237 Bench: 2238216 |
||
|
Linmiao XuandDisservin
|
bd579ab5d1 |
Update default main net to nn-1ceb1ade0001.nnue
Created by retraining the previous main net `nn-b1a57edbea57.nnue` with: - some of the same options as before: - ranger21, more WDL skipping, 15% more loss when Q is too high - removal of the huge 514G pre-interleaved binpack - removal of SF-generated dfrc data (dfrc99-16tb7p-filt-v2.min.binpack) - interleaving many binpacks at training time - training with some bestmove capture positions where SEE < 0 - increased usage of torch.compile to speed up training by up to 40% ```yaml experiment-name: 2560--S10-dfrc0-to-dec2023-skip-more-wdl-15p-more-loss-high-q-see-ge0-sk28 nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip-15p-more-loss-high-q-skip-see-ge0-torch-compile-more start-from-engine-test-net: True early-fen-skipping: 28 training-dataset: # similar, not the exact same as: # https://github.com/official-stockfish/Stockfish/pull/4635 - /data/S5-5af/leela96.v2.min.binpack - /data/S5-5af/test60-2021-11-12-novdec-12tb7p.v6-dd.min.binpack - /data/S5-5af/test77-2021-12-dec-16tb7p.v6-dd.min.binpack - /data/S5-5af/test78-2022-01-to-05-jantomay-16tb7p.v6-dd.min.binpack - /data/S5-5af/test78-2022-06-to-09-juntosep-16tb7p.v6-dd.min.binpack - /data/S5-5af/test79-2022-04-apr-16tb7p.v6-dd.min.binpack - /data/S5-5af/test79-2022-05-may-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2022-06-jun-16tb7p.v6-dd.min.unmin.binpack - /data/S5-5af/test80-2022-07-jul-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2022-08-aug-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2022-09-sep-16tb7p.v6-dd.min.unmin.binpack - /data/S5-5af/test80-2022-10-oct-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2022-11-nov-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2023-01-jan-16tb7p.v6-sk20.min.binpack - /data/S5-5af/test80-2023-02-feb-16tb7p.v6-dd.min.binpack - /data/S5-5af/test80-2023-03-mar-2tb7p.min.unmin.binpack - /data/S5-5af/test80-2023-04-apr-2tb7p.binpack - /data/S5-5af/test80-2023-05-may-2tb7p.min.dd.binpack # https://github.com/official-stockfish/Stockfish/pull/4782 - /data/S6-1ee1aba5ed/test80-2023-06-jun-2tb7p.binpack - /data/S6-1ee1aba5ed/test80-2023-07-jul-2tb7p.min.binpack # https://github.com/official-stockfish/Stockfish/pull/4972 - /data/S8-baff1edbea57/test80-2023-08-aug-2tb7p.v6.min.binpack - /data/S8-baff1edbea57/test80-2023-09-sep-2tb7p.binpack - /data/S8-baff1edbea57/test80-2023-10-oct-2tb7p.binpack # https://github.com/official-stockfish/Stockfish/pull/5056 - /data/S9-b1a57edbea57/test80-2023-11-nov-2tb7p.binpack - /data/S9-b1a57edbea57/test80-2023-12-dec-2tb7p.binpack num-epochs: 800 lr: 4.375e-4 gamma: 0.995 start-lambda: 1.0 end-lambda: 0.7 ``` This particular net was reached at epoch 759. Use of more torch.compile decorators in nnue-pytorch model.py than in the previous main net training run sped up training by up to 40% on Tesla gpus when using recent pytorch compiled with cuda 12: https://github.com/linrock/nnue-tools/blob/7fb9831/Dockerfile Skipping positions with bestmove captures where static exchange evaluation is >= 0 is based on the implementation from Sopel's NNUE training & experimentation log: https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY Experiment 293 - only skip captures with see>=0 Positions with bestmove captures where score == 0 are always skipped for compatibility with minimized binpacks, since the original minimizer sets scores to 0 for slight improvements in compression. The trainer branch used was: https://github.com/linrock/nnue-pytorch/tree/r21-more-wdl-skip-15p-more-loss-high-q-skip-see-ge0-torch-compile-more Binpacks were renamed to be sorted chronologically by default when sorted by name. The binpack data are otherwise the same as binpacks with similar names in the prior naming convention. Training data can be found at: https://robotmoon.com/nnue-training-data/ Passed STC: https://tests.stockfishchess.org/tests/view/65e3ddd1f2ef6c733362ae5c LLR: 2.92 (-2.94,2.94) <0.00,2.00> Total: 149792 W: 39153 L: 38661 D: 71978 Ptnml(0-2): 675, 17586, 37905, 18032, 698 Passed LTC: https://tests.stockfishchess.org/tests/view/65e4d91c416ecd92c162a69b LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 64416 W: 16517 L: 16135 D: 31764 Ptnml(0-2): 38, 7218, 17313, 7602, 37 closes https://github.com/official-stockfish/Stockfish/pull/5090 Bench: 1373183 |
||
|
Linmiao XuandDisservin
|
8e75548f2a |
Update default main net to nn-b1a57edbea57.nnue
Created by retraining the previous main net `nn-baff1edbea57.nnue` with: - some of the same options as before: ranger21, more WDL skipping - the addition of T80 nov+dec 2023 data - increasing loss by 15% when prediction is too high, up from 10% - use of torch.compile to speed up training by over 25% ```yaml experiment-name: 2560--S9-514G-T80-augtodec2023-more-wdl-skip-15p-more-loss-high-q-sk28 training-dataset: # https://github.com/official-stockfish/Stockfish/pull/4782 - /data/S6-514G-1ee1aba5ed.binpack - /data/test80-aug2023-2tb7p.v6.min.binpack - /data/test80-sep2023-2tb7p.binpack - /data/test80-oct2023-2tb7p.binpack - /data/test80-nov2023-2tb7p.binpack - /data/test80-dec2023-2tb7p.binpack early-fen-skipping: 28 start-from-engine-test-net: True nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip-15p-more-loss-high-q-torch-compile num-epochs: 1000 lr: 4.375e-4 gamma: 0.995 start-lambda: 1.0 end-lambda: 0.7 ``` Epoch 819 trained with the above config led to this PR. Use of torch.compile decorators in nnue-pytorch model.py was found to speed up training by at least 25% on Ampere gpus when using recent pytorch compiled with cuda 12: https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch See recent main net PRs for more info on - ranger21 and more WDL skipping: https://github.com/official-stockfish/Stockfish/pull/4942 - increasing loss when Q is too high: https://github.com/official-stockfish/Stockfish/pull/4972 Training data can be found at: https://robotmoon.com/nnue-training-data/ Passed STC: https://tests.stockfishchess.org/tests/view/65cd76151d8e83c78bfd2f52 LLR: 2.98 (-2.94,2.94) <0.00,2.00> Total: 78336 W: 20504 L: 20115 D: 37717 Ptnml(0-2): 317, 9225, 19721, 9562, 343 Passed LTC: https://tests.stockfishchess.org/tests/view/65ce5be61d8e83c78bfd43e9 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 41016 W: 10492 L: 10159 D: 20365 Ptnml(0-2): 22, 4533, 11071, 4854, 28 closes https://github.com/official-stockfish/Stockfish/pull/5056 Bench: 1351997 |
||
|
Linmiao XuandDisservin
|
6deb88728f |
Update default main net to nn-baff1edbea57.nnue
Created by retraining the previous main net nn-b1e55edbea57.nnue with: - some of the same options as before: ranger21 optimizer, more WDL skipping - adding T80 aug filter-v6, sep, and oct 2023 data to the previous best dataset - increasing training loss for positions where predicted win rates were higher than estimated match results from training data position scores ```yaml experiment-name: 2560--S8-r21-more-wdl-skip-10p-more-loss-high-q-sk28 training-dataset: # https://github.com/official-stockfish/Stockfish/pull/4782 - /data/S6-1ee1aba5ed.binpack - /data/test80-aug2023-2tb7p.v6.min.binpack - /data/test80-sep2023-2tb7p.binpack - /data/test80-oct2023-2tb7p.binpack early-fen-skipping: 28 start-from-engine-test-net: True nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip-10p-more-loss-high-q num-epochs: 1000 lr: 4.375e-4 gamma: 0.995 start-lambda: 1.0 end-lambda: 0.7 ``` Training data can be found at: https://robotmoon.com/nnue-training-data/ Training loss was increased by 10% for positions where predicted win rates were higher than suggested by the win rate model based on the training data, by multiplying with: ((qf > pt) * 0.1 + 1). This was a variant of experiments from Sopel's NNUE training & experimentation log: https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY Experiment 302 - increase loss when prediction too high, vondele’s idea Experiment 309 - increase loss when prediction too high, normalize in a batch Passed STC: https://tests.stockfishchess.org/tests/view/6597a21c79aa8af82b95fd5c LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 148320 W: 37960 L: 37475 D: 72885 Ptnml(0-2): 542, 17565, 37383, 18206, 464 Passed LTC: https://tests.stockfishchess.org/tests/view/659834a679aa8af82b960845 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 55188 W: 13955 L: 13592 D: 27641 Ptnml(0-2): 34, 6162, 14834, 6535, 29 closes https://github.com/official-stockfish/Stockfish/pull/4972 Bench: 1219824 |
||
|
Linmiao XuandDisservin
|
f09adaa4a4 |
Update smallnet to nn-baff1ede1f90.nnue with wider eval range
Created by training an L1-128 net from scratch with a wider range of
evals in the training data and wld-fen-skipping disabled during
training. The differences in this training data compared to the first
dual nnue PR are:
- removal of all positions with 3 pieces
- when piece count >= 16, keep positions with simple eval above 750
- when piece count < 16, remove positions with simple eval above 3000
The asymmetric data filtering was meant to flatten the training data
piece count distribution, which was previously heavily skewed towards
positions with low piece counts.
Additionally, the simple eval range where the smallnet is used was
widened to cover more positions previously evaluated by the big net and
simple eval.
```yaml
experiment-name: 128--S1-hse-S7-v4-S3-v1-no-wld-skip
training-dataset:
- /data/hse/S3/leela96-filt-v2.min.high-simple-eval-1k.binpack
- /data/hse/S3/dfrc99-16tb7p-eval-filt-v2.min.high-simple-eval-1k.binpack
- /data/hse/S3/test80-apr2022-16tb7p.min.high-simple-eval-1k.binpack
- /data/hse/S7/test60-2020-2tb7p.v6-3072.high-simple-eval-v4.binpack
- /data/hse/S7/test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test77-nov2021-2tb7p.v6-3072.min.high-simple-eval-v4.binpack
- /data/hse/S7/test77-dec2021-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test77-jan2022-2tb7p.high-simple-eval-v4.binpack
- /data/hse/S7/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test79-apr2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test79-may2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-may2022-16tb7p.high-simple-eval-v4.binpack
- /data/hse/S7/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-jul2022-16tb7p.v6-dd.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-aug2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-oct2022-16tb7p.v6-dd.high-simple-eval-v4.binpack
- /data/hse/S7/test80-nov2022-16tb7p-v6-dd.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack
- /data/hse/S7/test80-mar2023-2tb7p.v6-sk16.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-apr2023-2tb7p-filter-v6-sk16.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-may2023-2tb7p.v6.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-jun2023-2tb7p.v6-3072.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-jul2023-2tb7p.v6-3072.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-aug2023-2tb7p.v6.min.high-simple-eval-v4.binpack
- /data/hse/S7/test80-sep2023-2tb7p.high-simple-eval-v4.binpack
- /data/hse/S7/test80-oct2023-2tb7p.high-simple-eval-v4.binpack
wld-fen-skipping: False
start-from-engine-test-net: False
nnue-pytorch-branch: linrock/nnue-pytorch/L1-128
engine-test-branch: linrock/Stockfish/L1-128-nolazy
engine-base-branch: linrock/Stockfish/L1-128
num-epochs: 500
start-lambda: 1.0
end-lambda: 1.0
```
Experiment yaml configs converted to easy_train.sh commands with:
https://github.com/linrock/nnue-tools/blob/4339954/yaml_easy_train.py
Binpacks interleaved at training time with:
https://github.com/official-stockfish/nnue-pytorch/pull/259
FT weights permuted with 10k positions from fishpack32.binpack with:
https://github.com/official-stockfish/nnue-pytorch/pull/254
Data filtered for high simple eval positions (v4) with:
https://github.com/linrock/Stockfish/blob/b9c8440/src/tools/transform.cpp#L640-L675
Training data can be found at:
https://robotmoon.com/nnue-training-data/
Local elo at 25k nodes per move of
L1-128 smallnet (nnue-only eval) vs. L1-128 trained on standard S1 data:
nn-epoch319.nnue : -241.7 +/- 3.2
Passed STC vs.
|
||
|
|
584d9efedc |
Dual NNUE with L1-128 smallnet
Credit goes to @mstembera for: - writing the code enabling dual NNUE: https://github.com/official-stockfish/Stockfish/pull/4898 - the idea of trying L1-128 trained exclusively on high simple eval positions The L1-128 smallnet is: - epoch 399 of a single-stage training from scratch - trained only on positions from filtered data with high material difference - defined by abs(simple_eval) > 1000 ```yaml experiment-name: 128--S1-only-hse-v2 training-dataset: - /data/hse/S3/dfrc99-16tb7p-eval-filt-v2.min.high-simple-eval-1k.binpack - /data/hse/S3/leela96-filt-v2.min.high-simple-eval-1k.binpack - /data/hse/S3/test80-apr2022-16tb7p.min.high-simple-eval-1k.binpack - /data/hse/S7/test60-2020-2tb7p.v6-3072.high-simple-eval-1k.binpack - /data/hse/S7/test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test77-nov2021-2tb7p.v6-3072.min.high-simple-eval-1k.binpack - /data/hse/S7/test77-dec2021-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test77-jan2022-2tb7p.high-simple-eval-1k.binpack - /data/hse/S7/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test79-apr2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test79-may2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack # T80 2022 - /data/hse/S7/test80-may2022-16tb7p.high-simple-eval-1k.binpack - /data/hse/S7/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test80-jul2022-16tb7p.v6-dd.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-aug2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test80-oct2022-16tb7p.v6-dd.high-simple-eval-1k.binpack - /data/hse/S7/test80-nov2022-16tb7p-v6-dd.min.high-simple-eval-1k.binpack # T80 2023 - /data/hse/S7/test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-1k.binpack - /data/hse/S7/test80-mar2023-2tb7p.v6-sk16.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-apr2023-2tb7p-filter-v6-sk16.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-may2023-2tb7p.v6.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-jun2023-2tb7p.v6-3072.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-jul2023-2tb7p.v6-3072.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-aug2023-2tb7p.v6.min.high-simple-eval-1k.binpack - /data/hse/S7/test80-sep2023-2tb7p.high-simple-eval-1k.binpack - /data/hse/S7/test80-oct2023-2tb7p.high-simple-eval-1k.binpack start-from-engine-test-net: False nnue-pytorch-branch: linrock/nnue-pytorch/L1-128 engine-test-branch: linrock/Stockfish/L1-128-nolazy engine-base-branch: linrock/Stockfish/L1-128 num-epochs: 500 lambda: 1.0 ``` Experiment yaml configs converted to easy_train.sh commands with: https://github.com/linrock/nnue-tools/blob/4339954/yaml_easy_train.py Binpacks interleaved at training time with: https://github.com/official-stockfish/nnue-pytorch/pull/259 Data filtered for high simple eval positions with: https://github.com/linrock/nnue-data/blob/32d6a68/filter_high_simple_eval_plain.py https://github.com/linrock/Stockfish/blob/61dbfe/src/tools/transform.cpp#L626-L655 Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move of L1-128 smallnet (nnue-only eval) vs. L1-128 trained on standard S1 data: nn-epoch399.nnue : -318.1 +/- 2.1 Passed STC: https://tests.stockfishchess.org/tests/view/6574cb9d95ea6ba1fcd49e3b LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 62432 W: 15875 L: 15521 D: 31036 Ptnml(0-2): 177, 7331, 15872, 7633, 203 Passed LTC: https://tests.stockfishchess.org/tests/view/6575da2d4d789acf40aaac6e LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 64830 W: 16118 L: 15738 D: 32974 Ptnml(0-2): 43, 7129, 17697, 7497, 49 closes https://github.com/official-stockfish/Stockfish/pulls Bench: 1330050 Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com> |
||
|
Linmiao XuandDisservin
|
f12035c88c |
Update default net to nn-b1e55edbea57.nnue
Created by retraining the master big net `nn-0000000000a0.nnue` on the same dataset with the ranger21 optimizer and more WDL skipping at training time. More WDL skipping is meant to increase lambda accuracy and train on fewer misevaluated positions where position scores are unlikely to correlate with game outcomes. Inspired by: - repeated reports in discord #events-discuss about SF misplaying due to wrong endgame evals, possibly due to Leela's endgame weaknesses reflected in training data - an attempt to reduce the skewed dataset piece count distribution where there are much more positions with less than 16 pieces, since the target piece count distribution in the trainer is symmetric around 16 The faster convergence seen with ranger21 is meant to: - prune experiment ideas more quickly since fewer epochs are needed to reach elo maxima - research faster potential trainings by shortening each run ```yaml experiment-name: 2560-S7-Re-514G-ranger21-more-wdl-skip training-dataset: /data/S6-514G.binpack early-fen-skipping: 28 start-from-engine-test-net: True nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip num-epochs: 1200 lr: 4.375e-4 gamma: 0.995 start-lambda: 1.0 end-lambda: 0.7 ``` Experiment yaml configs converted to easy_train.sh commands with: https://github.com/linrock/nnue-tools/blob/4339954/yaml_easy_train.py Implementations based off of Sopel's NNUE training & experimentation log: https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY - Experiment 336 - ranger21 https://github.com/Sopel97/nnue-pytorch/tree/experiment_336 - Experiment 351 - more WDL skipping The version of the ranger21 optimizer used is: https://github.com/lessw2020/Ranger21/blob/b507df6/ranger21/ranger21.py The dataset is the exact same as in: https://github.com/official-stockfish/Stockfish/pull/4782 Local elo at 25k nodes per move: nn-epoch619.nnue : 6.2 +/- 4.2 Passed STC: https://tests.stockfishchess.org/tests/view/658a029779aa8af82b94fbe6 LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 46528 W: 11985 L: 11650 D: 22893 Ptnml(0-2): 154, 5489, 11688, 5734, 199 Passed LTC: https://tests.stockfishchess.org/tests/view/658a448979aa8af82b95010f LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 265326 W: 66378 L: 65574 D: 133374 Ptnml(0-2): 153, 30175, 71254, 30877, 204 This was additionally tested with the latest DualNNUE and passed SPRTs: Passed STC vs. https://github.com/official-stockfish/Stockfish/pull/4919 https://tests.stockfishchess.org/tests/view/658bcd5c79aa8af82b951846 LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 296128 W: 76273 L: 75554 D: 144301 Ptnml(0-2): 1223, 35768, 73617, 35979, 1477 Passed LTC vs. https://github.com/official-stockfish/Stockfish/pull/4919 https://tests.stockfishchess.org/tests/view/658c988d79aa8af82b95240f LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 75618 W: 19085 L: 18680 D: 37853 Ptnml(0-2): 45, 8420, 20497, 8779, 68 closes https://github.com/official-stockfish/Stockfish/pull/4942 Bench: 1304666 |
||
|
Linmiao XuandJoost VandeVondele
|
fbc6b27505 |
Simplify away optimism average score offset params
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/654abf6b136acbc57352ac4b LLR: 2.97 (-2.94,2.94) <-1.75,0.25> Total: 49664 W: 12687 L: 12477 D: 24500 Ptnml(0-2): 138, 5840, 12703, 5976, 175 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/654b638e136acbc57352b961 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 347166 W: 85561 L: 85676 D: 175929 Ptnml(0-2): 206, 39569, 94150, 39450, 208 closes https://github.com/official-stockfish/Stockfish/pull/4871 bench 1257641 |
||
|
Linmiao XuandJoost VandeVondele
|
0024133b08 |
Update 5 search params for pruning at shallow depth
Found by spsa tuning at 45+0.45 with: ``` int fpcEvalOffset = 188; int fpcLmrDepthMult = 206; int histDepthMult = -3232; int histDenom = 5793; int fpEvalOffset = 115; int negSeeDepthMultSq = -27; TUNE(SetRange(0, 394), fpcEvalOffset); TUNE(SetRange(0, 412), fpcLmrDepthMult); TUNE(SetRange(-6464, -1616), histDepthMult); TUNE(SetRange(2896, 11586), histDenom); TUNE(SetRange(0, 230), fpEvalOffset); TUNE(SetRange(-54, 0), negSeeDepthMultSq); ``` Passed STC: https://tests.stockfishchess.org/tests/view/6535551de746e058e6c0165d LLR: 2.98 (-2.94,2.94) <0.00,2.00> Total: 109056 W: 28025 L: 27599 D: 53432 Ptnml(0-2): 357, 12669, 28038, 13119, 345 Passed LTC: https://tests.stockfishchess.org/tests/view/65364c6ff127f3553505175d LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 61290 W: 15316 L: 14941 D: 31033 Ptnml(0-2): 34, 6849, 16498, 7236, 28 closes https://github.com/official-stockfish/Stockfish/pull/4847 bench 1167412 |
||
|
Linmiao XuandDisservin
|
afe7f4d9b0 |
Update default net to nn-0000000000a0.nnue
This is a later epoch from the same experiment that led to the previous master net. In training stage 6, max-epoch was raised to 1,200 near the end of the first 1,000 epochs. For more details, see https://github.com/official-stockfish/Stockfish/pull/4795 Local elo at 25k nodes per move (vs. L1-2048 nn-1ee1aba5ed4c.nnue) ep1079 : 15.6 +/- 1.2 Passed STC: https://tests.stockfishchess.org/tests/view/651503b3b3e74811c8af1e2a LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 29408 W: 7607 L: 7304 D: 14497 Ptnml(0-2): 97, 3277, 7650, 3586, 94 Passed LTC: https://tests.stockfishchess.org/tests/view/651585ceb3e74811c8af2a5f LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 73164 W: 18828 L: 18440 D: 35896 Ptnml(0-2): 30, 7749, 20644, 8121, 38 closes https://github.com/official-stockfish/Stockfish/pull/4810 Bench: 1453057 |
||
|
Linmiao XuandJoost VandeVondele
|
70ba9de85c |
Update NNUE architecture to SFNNv8: L1-2560 nn-ac1dbea57aa3.nnue
Creating this net involved: - a 6-stage training process from scratch. The datasets used in stages 1-5 were fully minimized. - permuting L1 weights with https://github.com/official-stockfish/nnue-pytorch/pull/254 A strong epoch after each training stage was chosen for the next. The 6 stages were: ``` 1. 400 epochs, lambda 1.0, default LR and gamma UHOx2-wIsRight-multinet-dfrc-n5000 (135G) nodes5000pv2_UHO.binpack data_pv-2_diff-100_nodes-5000.binpack wrongIsRight_nodes5000pv2.binpack multinet_pv-2_diff-100_nodes-5000.binpack dfrc_n5000.binpack 2. 800 epochs, end-lambda 0.75, LR 4.375e-4, gamma 0.995, skip 12 LeelaFarseer-T78juntoaugT79marT80dec.binpack (141G) T60T70wIsRightFarseerT60T74T75T76.binpack test78-junjulaug2022-16tb7p.no-db.min.binpack test79-mar2022-16tb7p.no-db.min.binpack test80-dec2022-16tb7p.no-db.min.binpack 3. 800 epochs, end-lambda 0.725, LR 4.375e-4, gamma 0.995, skip 20 leela93-v1-dfrc99-v2-T78juntosepT80jan-v6dd-T78janfebT79aprT80aprmay.min.binpack leela93-filt-v1.min.binpack dfrc99-16tb7p-filt-v2.min.binpack test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.binpack test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.binpack test78-janfeb2022-16tb7p.min.binpack test79-apr2022-16tb7p.min.binpack test80-apr2022-16tb7p.min.binpack test80-may2022-16tb7p.min.binpack 4. 800 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 24 leela96-dfrc99-v2-T78juntosepT79mayT80junsepnovjan-v6dd-T80mar23-v6-T60novdecT77decT78aprmayT79aprT80may23.min.binpack leela96-filt-v2.min.binpack dfrc99-16tb7p-filt-v2.min.binpack test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.binpack test79-may2022-16tb7p.filter-v6-dd.min.binpack test80-jun2022-16tb7p.filter-v6-dd.min.binpack test80-sep2022-16tb7p.filter-v6-dd.min.binpack test80-nov2022-16tb7p.filter-v6-dd.min.binpack test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.binpack test80-mar2023-2tb7p.v6-sk16.min.binpack test60-novdec2021-16tb7p.min.binpack test77-dec2021-16tb7p.min.binpack test78-aprmay2022-16tb7p.min.binpack test79-apr2022-16tb7p.min.binpack test80-may2023-2tb7p.min.binpack 5. 960 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 28 Increased max-epoch to 960 near the end of the first 800 epochs 5af11540bbfe dataset: https://github.com/official-stockfish/Stockfish/pull/4635 6. 1000 epochs, end-lambda 0.7, LR 4.375e-4, gamma 0.995, skip 28 Increased max-epoch to 1000 near the end of the first 800 epochs 1ee1aba5ed dataset: https://github.com/official-stockfish/Stockfish/pull/4782 ``` L1 weights permuted with: ```bash python3 serialize.py $nnue $nnue_permuted \ --features=HalfKAv2_hm \ --ft_optimize \ --ft_optimize_data=/data/fishpack32.binpack \ --ft_optimize_count=10000 ``` Speed measurements from 100 bench runs at depth 13 with profile-build x86-64-avx2: ``` sf_base = 1329051 +/- 2224 (95%) sf_test = 1163344 +/- 2992 (95%) diff = -165706 +/- 4913 (95%) speedup = -12.46807% +/- 0.370% (95%) ``` Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move (vs. L1-2048 nn-1ee1aba5ed4c.nnue) ep959 : 16.2 +/- 2.3 Failed 10+0.1 STC: https://tests.stockfishchess.org/tests/view/6501beee2cd016da89abab21 LLR: -2.92 (-2.94,2.94) <0.00,2.00> Total: 13184 W: 3285 L: 3535 D: 6364 Ptnml(0-2): 85, 1662, 3334, 1440, 71 Failed 180+1.8 VLTC: https://tests.stockfishchess.org/tests/view/6505cf9a72620bc881ea908e LLR: -2.94 (-2.94,2.94) <0.00,2.00> Total: 64248 W: 16224 L: 16374 D: 31650 Ptnml(0-2): 26, 6788, 18640, 6650, 20 Passed 60+0.6 th 8 VLTC SMP (STC bounds): https://tests.stockfishchess.org/tests/view/65084a4618698b74c2e541dc LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 90630 W: 23372 L: 23033 D: 44225 Ptnml(0-2): 13, 8490, 27968, 8833, 11 Passed 60+0.6 th 8 VLTC SMP: https://tests.stockfishchess.org/tests/view/6501d45d2cd016da89abacdb LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 137804 W: 35764 L: 35276 D: 66764 Ptnml(0-2): 31, 13006, 42326, 13522, 17 closes https://github.com/official-stockfish/Stockfish/pull/4795 bench 1246812 |
||
|
Linmiao XuandDisservin
|
3d1b067d85 |
Update default net to nn-1ee1aba5ed4c.nnue
Created by retraining the master net on a dataset composed by: - adding Leela data from T60 jul-dec 2020, T77 nov 2021, T80 jun-jul 2023 - deduplicating and unminimizing parts of the dataset before interleaving Trained initially with max epoch 800, then increased near the end of training twice. First to 960, then 1200. After training, post-processing involved: - greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620 - greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640 python3 easy_train.py \ --experiment-name 2048-retrain-S6-sk28 \ --training-dataset /data/S6.binpack \ --early-fen-skipping 28 \ --start-from-engine-test-net True \ --max_epoch 1200 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --tui False \ --seed $RANDOM \ --gpus 0 In the list of datasets below, periods in the filename represent the sequence of steps applied to arrive at the particular binpack. For example: test77-dec2021-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack 1. test77 dec2021 data rescored with 16 TB of syzygy tablebases during data conversion 2. filtered with csv_filter_v6_dd.py - v6 filtering and deduplication in one step 3. minimized with the original mar2023 implementation of `minimize_binpack` in the tools branch 4. unminimized by removing all positions with score == 32002 (`VALUE_NONE`) Binpacks were: - filtered with: https://github.com/linrock/nnue-data - unminimized with: https://github.com/linrock/Stockfish/tree/tools-unminify - deduplicated with: https://github.com/linrock/Stockfish/tree/tools-dd DATASETS=( leela96-filt-v2.min.unminimized.binpack dfrc99-16tb7p-eval-filt-v2.min.unminimized.binpack # most of the 0dd1cebea57 v6-dd dataset (without test80-jul2022) # https://github.com/official-stockfish/Stockfish/pull/4606 test60-novdec2021-12tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test77-dec2021-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test78-jantomay2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test78-juntosep2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test79-apr2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test79-may2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-jun2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-aug2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-sep2022-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-oct2022-16tb7p.filter-v6-dd.min.binpack test80-nov2022-16tb7p.filter-v6-dd.min.binpack test80-jan2023-3of3-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack test80-feb2023-16tb7p.filter-v6-dd.min-mar2023.unminimized.binpack # older Leela data, recently converted test60-octnovdec2020-2tb7p.min.unminimized.binpack test60-julaugsep2020-2tb7p.min.binpack test77-nov2021-2tb7p.min.dd.binpack # newer Leela data test80-mar2023-2tb7p.min.unminimized.binpack test80-apr2023-2tb7p.filter-v6-sk16.min.unminimized.binpack test80-may2023-2tb7p.min.dd.binpack test80-jun2023-2tb7p.min.binpack test80-jul2023-2tb7p.binpack ) python3 interleave_binpacks.py ${DATASETS[@]} /data/S6.binpack Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch1059 : 2.7 +/- 1.6 Passed STC: https://tests.stockfishchess.org/tests/view/64fc8d705dab775b5359db42 LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 168352 W: 43216 L: 42704 D: 82432 Ptnml(0-2): 599, 19672, 43134, 20160, 611 Passed LTC: https://tests.stockfishchess.org/tests/view/64fd44a75dab775b5359f065 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 154194 W: 39436 L: 38881 D: 75877 Ptnml(0-2): 78, 16577, 43238, 17120, 84 closes https://github.com/official-stockfish/Stockfish/pull/4782 Bench: 1603079 |
||
|
Linmiao XuandStéphane Nicolet
|
0ad9b51dea |
Remove classical psqt
Based on vondele's deletepsqt branch: https://github.com/vondele/Stockfish/commit/369f5b051 This huge simplification uses a weighted material differences instead of the positional piece square tables (psqt) in the semi-classical complexity calculation. Tuned weights using spsa at 45+0.45 with: int pawnMult = 100; int knightMult = 325; int bishopMult = 350; int rookMult = 500; int queenMult = 900; TUNE(SetRange(0, 200), pawnMult); TUNE(SetRange(0, 650), knightMult); TUNE(SetRange(0, 700), bishopMult); TUNE(SetRange(200, 800), rookMult); TUNE(SetRange(600, 1200), queenMult); The values obtained via this tuning session were for a model where the psqt replacement formula was always from the point of view of White, even if the side to move was Black. We re-used the same values for an implementation with a psqt replacement from the point of view of the side to move, testing the result both on our standard book on positions with a strong White bias, and an alternate book with positions with a strong Black bias. We note that with the patch the last use of the venerable "Score" type disappears in Stockfish codebase (the Score type was used in classical evaluation to get a tampered eval interpolating values smoothly from the early midgame stage to the endgame stage). We leave it to another commit to clean all occurrences of Score in the code and the comments. ------- Passed non-regression LTC: LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 142542 W: 36264 L: 36168 D: 70110 Ptnml(0-2): 76, 15578, 39856, 15696, 65 https://tests.stockfishchess.org/tests/view/64c8cb495b17f7c21c0cf9f8 Passed non-regression LTC (with a book with Black bias): https://tests.stockfishchess.org/tests/view/64c8f9295b17f7c21c0cfdaf LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 494814 W: 125565 L: 125827 D: 243422 Ptnml(0-2): 244, 53926, 139346, 53630, 261 ------ closes https://github.com/official-stockfish/Stockfish/pull/4713 Bench: 1655985 |
||
|
Linmiao XuandJoost VandeVondele
|
ee53f8ed2f |
Reintroduce nnue eval pawn count multipliers again
With separate multipliers for nnue eval and optimism scaling. This patch used 4 out of 7 params tuned with spsa at 30+0.3 using this tuning config: Value LazyThreshold1 = Value(3622); Value LazyThreshold2 = Value(1962); int psqThresh = 2048; int nnueNpmBase = 945; int nnuePcMult = 0; int optNpmBase = 150; int optPcMult = 0; TUNE(SetRange(3322, 3922), LazyThreshold1); TUNE(SetRange(1662, 2262), LazyThreshold2); TUNE(SetRange(1748, 2348), psqThresh); TUNE(SetRange(745, 1145), nnueNpmBase); TUNE(SetRange(-16, 16), nnuePcMult); TUNE(SetRange(0, 300), optNpmBase); TUNE(SetRange(-16, 16), optPcMult); Passed STC: https://tests.stockfishchess.org/tests/view/64a5a9b402cd07745c60ed07 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 173632 W: 44417 L: 43903 D: 85312 Ptnml(0-2): 547, 20025, 45068, 20719, 457 Passed LTC: https://tests.stockfishchess.org/tests/view/64a972a302cd07745c6136af LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 277644 W: 70955 L: 70147 D: 136542 Ptnml(0-2): 193, 29902, 77787, 30784, 156 closes https://github.com/official-stockfish/Stockfish/pull/4681 bench 1556301 |
||
|
Linmiao XuandJoost VandeVondele
|
e699fee513 |
Update default net to nn-c38c3d8d3920.nnue
This was a later epoch from the same experiment that led to the previous master net. After training, it was prepared the same way: 1. greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620 2. leb128 compression with https://github.com/glinscott/nnue-pytorch/pull/251 3. greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640 Local elo at 25k nodes per move (vs. L1-1536 nn-fdc1d0fe6455.nnue): nn-epoch739.nnue : 20.2 +/- 1.7 Passed STC: https://tests.stockfishchess.org/tests/view/64a050b33ee09aa549c4e4c8 LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 195552 W: 49977 L: 49430 D: 96145 Ptnml(0-2): 556, 22775, 50607, 23242, 596 Passed LTC: https://tests.stockfishchess.org/tests/view/64a127bd3ee09aa549c4f60c LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 235452 W: 60327 L: 59609 D: 115516 Ptnml(0-2): 119, 25173, 66426, 25887, 121 closes https://github.com/official-stockfish/Stockfish/pull/4666 bench 2427629 |
||
|
Linmiao XuandJoost VandeVondele
|
915532181f |
Update NNUE architecture to SFNNv7 with larger L1 size of 2048
Creating this net involved: - a 5-step training process from scratch - greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620 - leb128 compression with https://github.com/glinscott/nnue-pytorch/pull/251 - greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640 The 5 training steps were: 1. 400 epochs, lambda 1.0, lr 9.75e-4 UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9.binpack (178G) nodes5000pv2_UHO.binpack data_pv-2_diff-100_nodes-5000.binpack wrongIsRight_nodes5000pv2.binpack multinet_pv-2_diff-100_nodes-5000.binpack dfrc_n5000.binpack large_gensfen_multipvdiff_100_d9.binpack ep399 chosen as start model for step2 2. 800 epochs, end-lambda 0.75, skip 16 LeelaFarseer-T78juntoaugT79marT80dec.binpack (141G) T60T70wIsRightFarseerT60T74T75T76.binpack test78-junjulaug2022-16tb7p.no-db.min.binpack test79-mar2022-16tb7p.no-db.min.binpack test80-dec2022-16tb7p.no-db.min.binpack ep559 chosen as start model for step3 3. 800 epochs, end-lambda 0.725, skip 20 leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr.binpack (223G) leela96-filt-v2.min.binpack dfrc99-16tb7p-eval-filt-v2.min.binpack test80-dec2022-16tb7p-filter-v6-sk20.min-mar2023.binpack test80-jan2023-16tb7p-filter-v6-sk20.min-mar2023.binpack test80-feb2023-16tb7p-filter-v6-sk20.min-mar2023.binpack test80-mar2023-2tb7p-filter-v6.min.binpack test77-dec2021-16tb7p.no-db.min.binpack test78-janfeb2022-16tb7p.no-db.min.binpack test79-apr2022-16tb7p.no-db.min.binpack ep499 chosen as start model for step4 4. 800 epochs, end-lambda 0.7, skip 24 0dd1cebea57 dataset https://github.com/official-stockfish/Stockfish/pull/4606 ep599 chosen as start model for step5 5. 800 epochs, end-lambda 0.7, skip 28 same dataset as step4 ep619 became nn-1b951f8b449d.nnue For the final step5 training: python3 easy_train.py \ --experiment-name L1-2048-S5-sameData-sk28-S4-0dd1cebea57-shuffled-S3-leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr-sk20-S2-LeelaFarseerT78T79T80-ep399-S1-UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9 \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \ --early-fen-skipping 28 \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-2048 \ --engine-test-branch linrock/Stockfish/L1-2048 \ --start-from-engine-test-net False \ --start-from-model /data/experiments/experiment_L1-2048-S4-0dd1cebea57-shuffled-S3-leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr-sk20-S2-LeelaFarseerT78T79T80-ep399-S1-UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9/training/run_0/nn-epoch599.nnue --max_epoch 800 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --tui False \ --seed $RANDOM \ --gpus 0 SF training data components for the step1 dataset: https://drive.google.com/drive/folders/1yLCEmioC3Xx9KQr4T7uB6GnLm5icAYGU Leela training data for steps 2-5 can be found at: https://robotmoon.com/nnue-training-data/ Due to larger L1 size and slower inference, the speed penalty loses elo at STC. Measurements from 100 bench runs at depth 13 with x86-64-modern on Intel Core i5-1038NG7 2.00GHz: sf_base = 1240730 +/- 3443 (95%) sf_test = 1153341 +/- 2832 (95%) diff = -87388 +/- 1616 (95%) speedup = -7.04330% +/- 0.130% (95%) Local elo at 25k nodes per move (vs. L1-1536 nn-fdc1d0fe6455.nnue): nn-epoch619.nnue : 21.1 +/- 3.2 Failed STC: https://tests.stockfishchess.org/tests/view/6498ee93dc7002ce609cf979 LLR: -2.95 (-2.94,2.94) <0.00,2.00> Total: 11680 W: 3058 L: 3299 D: 5323 Ptnml(0-2): 44, 1422, 3149, 1181, 44 LTC: https://tests.stockfishchess.org/tests/view/649b32f5dc7002ce609d20cf Elo: 0.68 ± 1.5 (95%) LOS: 80.5% Total: 40000 W: 10887 L: 10809 D: 18304 Ptnml(0-2): 36, 3938, 11958, 4048, 20 nElo: 1.50 ± 3.4 (95%) PairsRatio: 1.02 Passed VLTC 180+1.8: https://tests.stockfishchess.org/tests/view/64992b43dc7002ce609cfd20 LLR: 3.06 (-2.94,2.94) <0.00,2.00> Total: 38086 W: 10612 L: 10338 D: 17136 Ptnml(0-2): 9, 3316, 12115, 3598, 5 Passed VLTC SMP 60+0.6 th 8: https://tests.stockfishchess.org/tests/view/649a21fedc7002ce609d0c7d LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 38936 W: 11091 L: 10820 D: 17025 Ptnml(0-2): 1, 2948, 13305, 3207, 7 closes https://github.com/official-stockfish/Stockfish/pull/4646 Bench: 2505168 |
||
|
Linmiao XuandJoost VandeVondele
|
a49b3ba7ed |
Update default net to nn-5af11540bbfe.nnue
Created by retraining the sparsified master net (nn-cd2ff4716c34.nnue) on a 100% minified dataset including Leela transformers data from T80 may2023. Weights permuted with the exact methods and code in: https://github.com/official-stockfish/Stockfish/pull/4620 LEB128 compression done with the new serialize.py param in: https://github.com/glinscott/nnue-pytorch/pull/251 Initially trained with max epoch 800. Around epoch 780, training was paused and max epoch raised to 960. python3 easy_train.py \ --experiment-name L1-1536-sparse-master-retrain \ --training-dataset /data/leela96-dfrc99-v2-T60novdecT77decT78jantosepT79aprmayT80juntonovjan-v6dd-T80febtomay2023.min.binpack \ --early-fen-skipping 27 \ --start-from-engine-test-net True \ --max_epoch 960 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --tui False \ --seed $RANDOM \ --gpus 0 For preparing the training dataset (interleaved size 328G): python3 interleave_binpacks.py \ leela96-filt-v2.min.binpack \ dfrc99-16tb7p-eval-filt-v2.min.binpack \ filt-v6-dd-min/test60-novdec2021-12tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test77-dec2021-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test78-jantomay2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test78-juntosep2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test79-apr2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test79-may2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-jun2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-jul2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-aug2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-sep2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-oct2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-nov2022-16tb7p-filter-v6-dd.min.binpack \ filt-v6-dd-min/test80-jan2023-16tb7p-filter-v6-dd.min.binpack \ test80-2023/test80-feb2023-16tb7p-no-db.min.binpack \ test80-2023/test80-mar2023-2tb7p-no-db.min.binpack \ test80-2023/test80-apr2023-2tb7p-no-db.min.binpack \ test80-2023/test80-may2023-2tb7p-no-db.min.binpack \ /data/leela96-dfrc99-v2-T60novdecT77decT78jantosepT79aprmayT80juntonovjan-v6dd-T80febtomay2023.min.binpack Minified binpacks and Leela T80 training data from 2023 available at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move: nn-epoch879.nnue : 3.9 +/- 5.7 Passed STC: https://tests.stockfishchess.org/tests/view/64928c1bdc7002ce609c7690 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 72000 W: 19242 L: 18889 D: 33869 Ptnml(0-2): 182, 7787, 19716, 8126, 189 Passed LTC: https://tests.stockfishchess.org/tests/view/64930a37dc7002ce609c82e3 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 54552 W: 14978 L: 14647 D: 24927 Ptnml(0-2): 23, 5123, 16650, 5460, 20 closes https://github.com/official-stockfish/Stockfish/pull/4635 bench 2593605 |
||
|
Linmiao XuandStéphane Nicolet
|
932f5a2d65 |
Update default net to nn-ea57bea57e32.nnue
Created by retraining an earlier epoch (ep659) of the experiment that led to the first SFNNv6 net: - First retrained on the nn-0dd1cebea573 dataset - Then retrained with skip 20 on a smaller dataset containing unfiltered Leela data - And then retrained again with skip 27 on the nn-0dd1cebea573 dataset The equivalent 7-step training sequence from scratch that led here was: 1. max-epoch 400, lambda 1.0, constant LR 9.75e-4, T79T77-filter-v6-dd.min.binpack ep379 chosen for retraining in step2 2. max-epoch 800, end-lambda 0.75, T60T70wIsRightFarseerT60T74T75T76.binpack ep679 chosen for retraining in step3 3. max-epoch 800, end-lambda 0.75, skip 28, nn-e1fb1ade4432 dataset ep799 chosen for retraining in step4 4. max-epoch 800, end-lambda 0.7, skip 28, nn-e1fb1ade4432 dataset ep759 became nn-8d69132723e2.nnue (first SFNNv6 net) ep659 chosen for retraining in step5 5. max-epoch 800, end-lambda 0.7, skip 28, nn-0dd1cebea573 dataset ep759 chosen for retraining in step6 6. max-epoch 800, end-lambda 0.7, skip 20, leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack ep639 chosen for retraining in step7 7. max-epoch 800, end-lambda 0.7, skip 27, nn-0dd1cebea573 dataset ep619 became nn-ea57bea57e32.nnue For the last retraining (step7): python3 easy_train.py --experiment-name L1-1536-Re6-masterShuffled-ep639-sk27-Re5-leela-dfrc-v2-T77toT80small-Re4-masterShuffled-ep659-Re3-sameAs-Re2-leela96-dfrc99-16t-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-Re1-LeelaFarseer-new-T77T79 \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --early-fen-skipping 27 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 800 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-Re5-leela-dfrc-v2-T77toT80small-epoch639.nnue \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --seed $RANDOM \ --gpus "0," For preparing the step6 leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack dataset: python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-16tb7p-eval-filt-v2.binpack \ test77-dec2021-16tb7p.no-db.min-mar2023.binpack \ test78-janfeb2022-16tb7p.no-db.min-mar2023.binpack \ test79-apr2022-16tb7p-filter-v6-dd.binpack \ test80-apr2022-16tb7p.no-db.min-mar2023.binpack \ /data/leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack The unfiltered Leela data used for the step6 dataset can be found at: https://robotmoon.com/nnue-training-data Local elo at 25k nodes per move: nn-epoch619.nnue : 2.3 +/- 1.9 Passed STC: https://tests.stockfishchess.org/tests/view/6480d43c6e6ce8d9fc6d7cc8 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 40992 W: 11017 L: 10706 D: 19269 Ptnml(0-2): 113, 4400, 11170, 4689, 124 Passed LTC: https://tests.stockfishchess.org/tests/view/648119ac6e6ce8d9fc6d8208 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 129174 W: 35059 L: 34579 D: 59536 Ptnml(0-2): 66, 12548, 38868, 13050, 55 closes https://github.com/official-stockfish/Stockfish/pull/4611 bench: 2370027 |
||
|
Linmiao XuandJoost VandeVondele
|
54ad986768 |
Remove optimism multiplier in nnue eval calculation
The same formula had passed SPRT against an earlier version of master. Passed non-regression STC vs. |
||
|
Linmiao XuandJoost VandeVondele
|
373359b44d |
Update default net to nn-0dd1cebea573.nnue
Created by retraining an earlier epoch of the experiment leading to the first SFNNv6 net on a more-randomized version of the nn-e1fb1ade4432.nnue dataset mixed with unfiltered T80 apr2023 data. Trained using early-fen-skipping 28 and max-epoch 960. The trainer settings and epochs used in the 5-step training sequence leading here were: 1. train from scratch for 400 epochs, lambda 1.0, constant LR 9.75e-4, T79T77-filter-v6-dd.min.binpack 2. retrain ep379, max-epoch 800, end-lambda 0.75, T60T70wIsRightFarseerT60T74T75T76.binpack 3. retrain ep679, max-epoch 800, end-lambda 0.75, skip 28, nn-e1fb1ade4432 dataset 4. retrain ep799, max-epoch 800, end-lambda 0.7, skip 28, nn-e1fb1ade4432 dataset 5. retrain ep439, max-epoch 960, end-lambda 0.7, skip 28, shuffled nn-e1fb1ade4432 + T80 apr2023 This net was epoch 559 of the final (step 5) retraining: ```bash python3 easy_train.py \ --experiment-name L1-1536-Re4-leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr-shuffled-sk28 \ --training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --early-fen-skipping 28 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --max_epoch 960 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-Re3-nn-epoch439.nnue \ --engine-test-branch linrock/Stockfish/L1-1536 \ --lr 4.375e-4 \ --gamma 0.995 \ --tui False \ --seed $RANDOM \ --gpus "0," ``` During data preparation, most binpacks were unminimized by removing positions with score 32002 (`VALUE_NONE`). This makes the tradeoff of increasing dataset filesize on disk to increase the randomness of positions in interleaved datasets. The code used for unminimizing is at: https://github.com/linrock/Stockfish/tree/tools-unminify For preparing the dataset used in this experiment: ```bash python3 interleave_binpacks.py \ leela96-filt-v2.binpack \ dfrc99-16tb7p-eval-filt-v2.binpack \ filt-v6-dd-min/test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-aug2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.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-min/test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd-min/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd/test79-apr2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test79-may2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd-min/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.binpack \ filt-v6-dd/test78-juntosep2022-16tb7p-filter-v6-dd.binpack \ filt-v6-dd/test77-dec2021-16tb7p-filter-v6-dd.binpack \ test80-apr2023-2tb7p.binpack \ /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack ``` T80 apr2023 data was converted using lc0-rescorer with ~2tb of tablebases and can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024): nn-epoch559.nnue : 25.7 +/- 1.6 Passed STC: https://tests.stockfishchess.org/tests/view/647cd3b87cf638f0f53f9cbb LLR: 2.95 (-2.94,2.94) <0.00,2.00> Total: 59200 W: 16000 L: 15660 D: 27540 Ptnml(0-2): 159, 6488, 15996, 6768, 189 Passed LTC: https://tests.stockfishchess.org/tests/view/647d58de726f6b400e4085d8 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 58800 W: 16002 L: 15657 D: 27141 Ptnml(0-2): 44, 5607, 17748, 5962, 39 closes https://github.com/official-stockfish/Stockfish/pull/4606 bench 2141197 |
||
|
Linmiao XuandJoost VandeVondele
|
ced0311890 |
Remove static eval threshold for extensions when giving check
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/647685d54a36543c4c9f4f2a LLR: 2.93 (-2.94,2.94) <-1.75,0.25> Total: 114688 W: 30701 L: 30571 D: 53416 Ptnml(0-2): 336, 12708, 31136, 12818, 346 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/64774b02b81f005b572de770 LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 107310 W: 28920 L: 28796 D: 49594 Ptnml(0-2): 33, 10427, 32621, 10531, 43 closes https://github.com/official-stockfish/Stockfish/pull/4599 bench 2597974 |
||
|
Linmiao XuandJoost VandeVondele
|
6cf8d938c5 |
Simplify blending nnue complexity with optimism
Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6478a26d54dd118e1d98f21c LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 241248 W: 64058 L: 64063 D: 113127 Ptnml(0-2): 644, 26679, 65960, 26720, 621 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/647b464854dd118e1d9928b2 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 24336 W: 6658 L: 6451 D: 11227 Ptnml(0-2): 8, 2316, 7312, 2525, 7 closes https://github.com/official-stockfish/Stockfish/pull/4602 bench 2425813 |
||
|
Linmiao XuandJoost VandeVondele
|
07bd8adcbc |
Simplify nnue eval complexity calculation
Remove a multiplier when blending nnue complexity with semi-classical complexity. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/6473a71dd29264e4cfa75839 LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 124768 W: 33180 L: 33060 D: 58528 Ptnml(0-2): 314, 13797, 34030, 13941, 302 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6474af3dd29264e4cfa768f4 LLR: 2.96 (-2.94,2.94) <-1.75,0.25> Total: 108180 W: 29008 L: 28884 D: 50288 Ptnml(0-2): 29, 10420, 33075, 10530, 36 closes https://github.com/official-stockfish/Stockfish/pull/4592 bench 2316827 |
||
|
Linmiao XuandJoost VandeVondele
|
c1fff71650 |
Update NNUE architecture to SFNNv6 with larger L1 size of 1536
Created by training a new net from scratch with L1 size increased from 1024 to 1536. Thanks to Vizvezdenec for the idea of exploring larger net sizes after recent training data improvements. A new net was first trained with lambda 1.0 and constant LR 8.75e-4. Then a strong net from a later epoch in the training run was chosen for retraining with start-lambda 1.0 and initial LR 4.375e-4 decaying with gamma 0.995. Retraining was performed a total of 3 times, for this 4-step process: 1. 400 epochs, lambda 1.0 on filtered T77+T79 v6 deduplicated data 2. 800 epochs, end-lambda 0.75 on T60T70wIsRightFarseerT60T74T75T76.binpack 3. 800 epochs, end-lambda 0.75 and early-fen-skipping 28 on the master dataset 4. 800 epochs, end-lambda 0.7 and early-fen-skipping 28 on the master dataset In the training sequence that reached the new nn-8d69132723e2.nnue net, the epochs used for the 3x retraining runs were: 1. epoch 379 trained on T77T79-filter-v6-dd.min.binpack 2. epoch 679 trained on T60T70wIsRightFarseerT60T74T75T76.binpack 3. epoch 799 trained on the master dataset For training from scratch: python3 easy_train.py \ --experiment-name new-L1-1536-T77T79-filter-v6dd \ --training-dataset /data/T77T79-filter-v6-dd.min.binpack \ --max_epoch 400 \ --lambda 1.0 \ --start-from-engine-test-net False \ --engine-test-branch linrock/Stockfish/L1-1536 \ --nnue-pytorch-branch linrock/Stockfish/misc-fixes-L1-1536 \ --tui False \ --gpus "0," \ --seed $RANDOM Retraining commands were similar to each other. For the 3rd retraining run: python3 easy_train.py \ --experiment-name L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-Re3-sameData \ --training-dataset /data/leela96-dfrc99-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd.binpack \ --early-fen-skipping 28 \ --max_epoch 800 \ --start-lambda 1.0 \ --end-lambda 0.7 \ --lr 4.375e-4 \ --gamma 0.995 \ --start-from-engine-test-net False \ --start-from-model /data/L1-1536-T77T79-v6dd-Re1-LeelaFarseer-Re2-masterDataset-nn-epoch799.nnue \ --engine-test-branch linrock/Stockfish/L1-1536 \ --nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \ --tui False \ --gpus "0," \ --seed $RANDOM The T77+T79 data used is a subset of the master dataset available at: https://robotmoon.com/nnue-training-data/ T60T70wIsRightFarseerT60T74T75T76.binpack is available at: https://drive.google.com/drive/folders/1S9-ZiQa_3ApmjBtl2e8SyHxj4zG4V8gG Local elo at 25k nodes per move vs. nn-e1fb1ade4432.nnue (L1 size 1024): nn-epoch759.nnue : 26.9 +/- 1.6 Failed STC https://tests.stockfishchess.org/tests/view/64742485d29264e4cfa75f97 LLR: -2.94 (-2.94,2.94) <0.00,2.00> Total: 13728 W: 3588 L: 3829 D: 6311 Ptnml(0-2): 71, 1661, 3610, 1482, 40 Failing LTC https://tests.stockfishchess.org/tests/view/64752d7c4a36543c4c9f3618 LLR: -1.91 (-2.94,2.94) <0.50,2.50> Total: 35424 W: 9522 L: 9603 D: 16299 Ptnml(0-2): 24, 3579, 10585, 3502, 22 Passed VLTC 180+1.8 https://tests.stockfishchess.org/tests/view/64752df04a36543c4c9f3638 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 47616 W: 13174 L: 12863 D: 21579 Ptnml(0-2): 13, 4261, 14952, 4566, 16 Passed VLTC SMP 60+0.6 th 8 https://tests.stockfishchess.org/tests/view/647446ced29264e4cfa761e5 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 19942 W: 5694 L: 5451 D: 8797 Ptnml(0-2): 6, 1504, 6707, 1749, 5 closes https://github.com/official-stockfish/Stockfish/pull/4593 bench 2222567 |
||
|
Linmiao XuandJoost VandeVondele
|
21d6b69f7c |
Update 7 eval and optimism params
Params found using spsa at 30+0.3 with this tuning config: ``` // evaluate.cpp int nnueOptScaleBase = 1001; int nnueComplexityMult = 406; int nnueComplexityOptOffset = 424; int evalOptComplexityOffset = 272; int evalOptScaleOffset = 748; TUNE(SetRange(801, 1201), nnueOptScaleBase); TUNE(SetRange(306, 506), nnueComplexityMult); TUNE(SetRange(324, 524), nnueComplexityOptOffset); TUNE(SetRange(172, 372), evalOptComplexityOffset); TUNE(SetRange(648, 848), evalOptScaleOffset); // search.cpp int searchOptBase = 120; int searchOptDenom = 161; TUNE(SetRange(20, 220), searchOptBase); TUNE(SetRange(111, 211), searchOptDenom); ``` Passed STC: https://tests.stockfishchess.org/tests/view/644dda8accf5e93df5e50cbe LLR: 2.93 (-2.94,2.94) <0.00,2.00> Total: 136800 W: 36682 L: 36237 D: 63881 Ptnml(0-2): 353, 14910, 37492, 15229, 416 Passed LTC: https://tests.stockfishchess.org/tests/view/644eaedb3f31c3bbe4a3d345 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 64548 W: 17624 L: 17272 D: 29652 Ptnml(0-2): 33, 6112, 19631, 6466, 32 closes https://github.com/official-stockfish/Stockfish/pull/4550 bench 3670343 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
7bd23d4d04 |
Simplify away nnue scale pawn count multiplier
Removes 2x multipliers in nnue scale calculation along with the pawn count term that was recently reintroduced. Passed non-regression STC: https://tests.stockfishchess.org/tests/view/64305bc720eb941419bdf72e LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 38008 W: 10234 L: 10021 D: 17753 Ptnml(0-2): 96, 4151, 10323, 4312, 122 Passed non-regression LTC: https://tests.stockfishchess.org/tests/view/6430b76a028b029b01ac9bfd LLR: 2.94 (-2.94,2.94) <-1.75,0.25> Total: 91232 W: 24686 L: 24547 D: 41999 Ptnml(0-2): 30, 8721, 27986, 8838, 41 closes https://github.com/official-stockfish/Stockfish/pull/4510 bench 4017320 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
69639d764b |
Reintroduce nnue pawn scaling with lower lazy thresholds
Params found with the nevergrad TBPSA optimizer via nevergrad4sf modified to: * use SPRT LLR with fishtest STC elo gainer bounds [0, 2] as the objective function * increase the game batch size after each new optimal point is found The params were the optimal point after TBPSA iteration 7 and 160 nevergrad evaluations with: * initial batch size of 96 games per evaluation * batch size increase of 64 games after each iteration * a budget of 512 evaluations * TC: fixed 1.5 million nodes per move, no time limit nevergrad4sf enables optimizing stockfish params with TBPSA: https://github.com/vondele/nevergrad4sf Using pentanomial game results with smaller game batch sizes was inspired by: Use of SPRT LLR calculated from pentanomial game results as the objective function was an experiment at maximizing the information from game batches to reduce the computational cost for TBPSA to converge on good parameters. For the exact code used to find the params: https://github.com/linrock/tuning-fork Passed STC: https://tests.stockfishchess.org/tests/view/63f4ef5ee74a12625bcd114a LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 66552 W: 17736 L: 17390 D: 31426 Ptnml(0-2): 164, 7229, 18166, 7531, 186 Passed LTC: https://tests.stockfishchess.org/tests/view/63f56028e74a12625bcd2550 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 71264 W: 19150 L: 18787 D: 33327 Ptnml(0-2): 23, 6728, 21771, 7083, 27 closes https://github.com/official-stockfish/Stockfish/pull/4401 bench 3687580 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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 |
||
|
Linmiao XuandJoost VandeVondele
|
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
|
||
|
Linmiao XuandJoost VandeVondele
|
7f8166db89 |
Tuned safe checks and minor piece king protectors
A combination of terms related to king safety one tuned safe check weights,
the other tuned knight and bishop king protector weights separately with
some compensation in the high outpost bonuses given to the minor pieces.
passed STC
LLR: 2.95 (-2.94,2.94) {-0.50,1.50}
Total: 39892 W: 7594 L: 7350 D: 24948
Ptnml(0-2): 643, 4559, 9314, 4771, 659
https://tests.stockfishchess.org/tests/view/5ea49635b908f6dd28f34b82
passed LTC
LLR: 2.94 (-2.94,2.94) {0.25,1.75}
Total: 104934 W: 13300 L: 12834 D: 78800
Ptnml(0-2): 697, 9571, 31514, 9939, 746
https://tests.stockfishchess.org/tests/view/5ea4abf6b908f6dd28f34bcb
closes https://github.com/official-stockfish/Stockfish/pull/2649
Bench 4800754
|