Skip to content

Conversation

@SFisGOD
Copy link
Contributor

@SFisGOD SFisGOD commented Jun 28, 2021

Optimization of eight subnetwork output layers of Michael's nn-190f102a22c3.nnue using SPSA
https://tests.stockfishchess.org/tests/view/60d5510642a522cc50282ef3

Parameters: A total of 256 net weights and 8 net biases were tuned
New best values: The raw values at the end of the tuning run were used (800k games, 5 seconds TC)
Settings: default ck value and SPSA A is 30,000 (3.75% of the total number of games)

STC:
LLR: 2.94 (-2.94,2.94) <-0.50,2.50>
Total: 29064 W: 2435 L: 2269 D: 24360
Ptnml(0-2): 72, 1857, 10505, 2029, 69
https://tests.stockfishchess.org/tests/view/60d8ea123beab81350ac9eb6

LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.50>
Total: 61848 W: 2055 L: 1884 D: 57909
Ptnml(0-2): 18, 1708, 27310, 1861, 27
https://tests.stockfishchess.org/tests/view/60d8f0393beab81350ac9ec6

Bench: 5548055

@SFisGOD
Copy link
Contributor Author

SFisGOD commented Jun 28, 2021

@vondele If you like, I could submit a new PR after you finish merging the commits before this one so that it's easier for you.

Both tests are on top of PR #3592

@vondele vondele added cluster to be merged Will be merged shortly and removed cluster labels Jun 28, 2021
@MichaelB7
Copy link
Contributor

MichaelB7 commented Jun 28, 2021

I support the merge of this net on top of my net without further testing. It beat my net on an "apples to apples" basis and should be declared the default net.

@vondele vondele closed this in 49283d3 Jun 28, 2021
vondele pushed a commit to vondele/Stockfish that referenced this pull request Jul 3, 2021
Optimization of nn-956480d8378f.nnue using SPSA
https://tests.stockfishchess.org/tests/view/60da2bf63beab81350ac9fe7

Same method as described in PR official-stockfish#3593

STC:
LLR: 2.93 (-2.94,2.94) <-0.50,2.50>
Total: 17792 W: 1525 L: 1372 D: 14895
Ptnml(0-2): 28, 1156, 6401, 1257, 54
https://tests.stockfishchess.org/tests/view/60deffc59ea99d7c2d693c19

LTC:
LLR: 2.96 (-2.94,2.94) <0.50,3.50>
Total: 36544 W: 1245 L: 1109 D: 34190
Ptnml(0-2): 12, 988, 16139, 1118, 15
https://tests.stockfishchess.org/tests/view/60df11339ea99d7c2d693c22

closes official-stockfish#3601

Bench: 4687476
MichaelB7 pushed a commit to MichaelB7/Stockfish that referenced this pull request Jul 6, 2021
Optimization of eight subnetwork output layers of Michael's nn-190f102a22c3.nnue using SPSA
https://tests.stockfishchess.org/tests/view/60d5510642a522cc50282ef3

Parameters: A total of 256 net weights and 8 net biases were tuned
New best values: The raw values at the end of the tuning run were used (800k games, 5 seconds TC)
Settings: default ck value and SPSA A is 30,000 (3.75% of the total number of games)

STC:
LLR: 2.94 (-2.94,2.94) <-0.50,2.50>
Total: 29064 W: 2435 L: 2269 D: 24360
Ptnml(0-2): 72, 1857, 10505, 2029, 69
https://tests.stockfishchess.org/tests/view/60d8ea123beab81350ac9eb6

LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.50>
Total: 61848 W: 2055 L: 1884 D: 57909
Ptnml(0-2): 18, 1708, 27310, 1861, 27
https://tests.stockfishchess.org/tests/view/60d8f0393beab81350ac9ec6

closes official-stockfish#3593

Bench: 4770936
MichaelB7 pushed a commit to MichaelB7/Stockfish that referenced this pull request Jul 6, 2021
Optimization of nn-956480d8378f.nnue using SPSA
https://tests.stockfishchess.org/tests/view/60da2bf63beab81350ac9fe7

Same method as described in PR official-stockfish#3593

STC:
LLR: 2.93 (-2.94,2.94) <-0.50,2.50>
Total: 17792 W: 1525 L: 1372 D: 14895
Ptnml(0-2): 28, 1156, 6401, 1257, 54
https://tests.stockfishchess.org/tests/view/60deffc59ea99d7c2d693c19

LTC:
LLR: 2.96 (-2.94,2.94) <0.50,3.50>
Total: 36544 W: 1245 L: 1109 D: 34190
Ptnml(0-2): 12, 988, 16139, 1118, 15
https://tests.stockfishchess.org/tests/view/60df11339ea99d7c2d693c22

closes official-stockfish#3601

Bench: 4687476
vondele pushed a commit to vondele/Stockfish that referenced this pull request Jul 26, 2021
SPSA: https://tests.stockfishchess.org/tests/view/60fba335d8a6b65b2f3a7891

New best values: Half of the changes from the tuning run.
Setting: nodestime=300 with 10+0.1 (approximate real TC is 2.5 seconds)
The rest is the same as described in official-stockfish#3593

The change from nodestime=600 to 300 was suggested by gekkehenker to prevent time losses for some slow workers
SFisGOD/Stockfish@94cd757#commitcomment-53324840

STC:
LLR: 2.96 (-2.94,2.94) <-0.50,2.50>
Total: 67448 W: 5241 L: 5036 D: 57171
Ptnml(0-2): 151, 4198, 24827, 4391, 157
https://tests.stockfishchess.org/tests/view/60fd50f2d8a6b65b2f3a798e

LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.50>
Total: 48752 W: 1504 L: 1358 D: 45890
Ptnml(0-2): 13, 1226, 21754, 1368, 15
https://tests.stockfishchess.org/tests/view/60fd7bb2d8a6b65b2f3a79a9

Closes official-stockfish#3630

Bench:  5124774
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

to be merged Will be merged shortly

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants