Sergio Vieri second net is out

[Sylwy]

Here are both:

https://www.comp.nus.edu.sg/~sergio-v/nnue/

[zullil]

Here are both:

https://www.comp.nus.edu.sg/~sergio-v/nnue/

And now his third. A new net will arrive every 5 hours. I think we can stop announcing each new arrival now.

[Rebel]

After 1000 games with the slow popcount executable this net has a 57.1% core, 2.4% more than the net of Henk. Still 1000 games to go.

[zullil]

After 1000 games with the slow popcount executable this net has a 57.1% core, 2.4% more than the net of Henk. Still 1000 games to go.

"90% of coding is debugging, the other 10% is writing bugs." Not to mention typos. Took me a bit to understand what a "57.1% core" meant.

[mehmet123]

I think this is the speed ratio of Stockfish NNUE according to Stockfish

[zullil]

I think this is the speed ratio of Stockfish NNUE according to Stockfish

No, I think he meant to type "score" and lost the first letter.

[Rebel]

I think this is the speed ratio of Stockfish NNUE according to Stockfish

No, I think he meant to type "score" and lost the first letter.

Ha! indeed

Code: Select all

Score of henk vs sf11: 677 - 429 - 894  [0.562] 2000
...      henk playing White: 405 - 161 - 434  [0.622] 1000
...      henk playing Black: 272 - 268 - 460  [0.502] 1000
...      White vs Black: 673 - 433 - 894  [0.560] 2000
Elo difference: 43.3 +/- 11.3, LOS: 100.0 %, DrawRatio: 44.7 %
Finished match

1.5% more as previous net, +10 elo.

[Rebel]

Last Sergio nets.

Code: Select all

https://github.com/nodchip/Stockfish
https://www.comp.nus.edu.sg/~sergio-v/nnue/

Stockfish 11        Nodes/second   : 1.664.010
SF-NNUE (popcount)  Nodes/second   :   796.674

TC 40m/20s, 2000 games.

henk-2706     54.7%   2020-07-19
sergio-1432   56.1%   2020-07-21 15:56
sergio-1907   58.9%   2020-07-21 19:14
sergio-2323   58.4%   2020-07-21 23:23
sergio-0359   58.8%   2020-07-22 03:59

Stagnation?

Too early to tell.

Tomorrw is a new day.

[Rebel]

2 more nets, no progress, 59% apparently is a hard nut to crack.

Code: Select all

https://github.com/nodchip/Stockfish
https://www.comp.nus.edu.sg/~sergio-v/nnue/

Stockfish 11        Nodes/second   : 1.664.010
SF-NNUE (popcount)  Nodes/second   :   796.674

SF-NNUE (popcount) vs Stockfish 11
henk-2706     54.7%   2020-07-19
sergio-1432   56.1%   2020-07-21 15:56
sergio-1907   58.9%   2020-07-21 19:14
sergio-2323   58.4%   2020-07-21 23:23
sergio-0359   58.8%   2020-07-22 03:59
sergio-0944   58.9%   2020-07-22 09:44
sergio-1153   58.3%   2020-07-22 11:53

[Laskos]

2 more nets, no progress, 59% apparently is a hard nut to crack.

Code: Select all

https://github.com/nodchip/Stockfish
https://www.comp.nus.edu.sg/~sergio-v/nnue/

Stockfish 11        Nodes/second   : 1.664.010
SF-NNUE (popcount)  Nodes/second   :   796.674

SF-NNUE (popcount) vs Stockfish 11
henk-2706     54.7%   2020-07-19
sergio-1432   56.1%   2020-07-21 15:56
sergio-1907   58.9%   2020-07-21 19:14
sergio-2323   58.4%   2020-07-21 23:23
sergio-0359   58.8%   2020-07-22 03:59
sergio-0944   58.9%   2020-07-22 09:44
sergio-1153   58.3%   2020-07-22 11:53

Here I have the cumulative improvement of Sergio's nets after 6 nets:

6s + 0.1s

Code: Select all

Score of Sergio_22.07_0944 vs Sergio_20.07_1017: 1399 - 1137 - 1464  [0.533] 4000

...      Sergio_22.07_0944 playing White: 737 - 528 - 735  [0.552] 2000
...      Sergio_22.07_0944 playing Black: 662 - 609 - 729  [0.513] 2000
...      White vs Black: 1346 - 1190 - 1464  [0.519] 4000

Elo difference: 22.8 +/- 8.6, LOS: 100.0 %, DrawRatio: 36.6 %
Finished match

I get about 4 Elo points per net, if the improvement is linear (it is probably not).