Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Re-evaluate some small net positions for more accurate evals #5238

Closed
wants to merge 1 commit into from

Conversation

linrock
Copy link
Contributor

@linrock linrock commented May 12, 2024

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

bench 2955600

@mstembera
Copy link
Contributor

Congrats! and thanks for making it work.

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

bench 2955600

Co-Authored-By: mstembera <5421953+mstembera@users.noreply.github.com>
@vondele vondele added the to be merged Will be merged shortly label May 13, 2024
@vondele vondele closed this in 0b08953 May 13, 2024
@mstembera
Copy link
Contributor

It's probably not a big deal but technically we are now using the wrong constants to the adjustEval() call on line 87 since smallNet stays set to true even after we reevaluate w/ the big net. Is it ok to test a fix for this w/ non regression bounds? @vondele @Disservin

@vondele
Copy link
Member

vondele commented May 13, 2024

yes, fine with me.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
functional-change 🚀 gainer Gains elo to be merged Will be merged shortly
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants