Sergio Vieri second net is out

Discussion of anything and everything relating to chess playing software and machines.

Moderators: Harvey Williamson, bob, hgm

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
User avatar
Sylwy
Posts: 3439
Joined: Fri Apr 21, 2006 2:19 pm
Location: IASI (Romania) - the historical capital of MOLDOVA

Sergio Vieri second net is out

Post by Sylwy » Tue Jul 21, 2020 7:20 am


zullil
Posts: 6442
Joined: Mon Jan 08, 2007 11:31 pm
Location: PA USA
Full name: Louis Zulli

Re: Sergio Vieri second net is out

Post by zullil » Tue Jul 21, 2020 10:11 am

Sylwy wrote:
Tue Jul 21, 2020 7:20 am
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. :D

User avatar
Rebel
Posts: 5651
Joined: Thu Aug 18, 2011 10:04 am

Re: Sergio Vieri second net is out

Post by Rebel » Tue Jul 21, 2020 10:32 am

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.

zullil
Posts: 6442
Joined: Mon Jan 08, 2007 11:31 pm
Location: PA USA
Full name: Louis Zulli

Re: Sergio Vieri second net is out

Post by zullil » Tue Jul 21, 2020 11:02 am

Rebel wrote:
Tue Jul 21, 2020 10:32 am
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. :D

mehmet123
Posts: 214
Joined: Sun Jan 26, 2020 9:38 pm
Location: Turkey
Full name: Mehmet Karaman

Re: Sergio Vieri second net is out

Post by mehmet123 » Tue Jul 21, 2020 12:38 pm

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

zullil
Posts: 6442
Joined: Mon Jan 08, 2007 11:31 pm
Location: PA USA
Full name: Louis Zulli

Re: Sergio Vieri second net is out

Post by zullil » Tue Jul 21, 2020 2:11 pm

mehmet123 wrote:
Tue Jul 21, 2020 12:38 pm
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. :wink:

User avatar
Rebel
Posts: 5651
Joined: Thu Aug 18, 2011 10:04 am

Re: Sergio Vieri second net is out

Post by Rebel » Tue Jul 21, 2020 2:25 pm

zullil wrote:
Tue Jul 21, 2020 2:11 pm
mehmet123 wrote:
Tue Jul 21, 2020 12:38 pm
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. :wink:
Ha! indeed :wink:

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.
90% of coding is debugging, the other 10% is writing bugs.

User avatar
Rebel
Posts: 5651
Joined: Thu Aug 18, 2011 10:04 am

Re: Sergio Vieri second net is out

Post by Rebel » Tue Jul 21, 2020 11:50 pm

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.
90% of coding is debugging, the other 10% is writing bugs.

User avatar
Rebel
Posts: 5651
Joined: Thu Aug 18, 2011 10:04 am

Re: Sergio Vieri second net is out

Post by Rebel » Wed Jul 22, 2020 8:44 am

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
90% of coding is debugging, the other 10% is writing bugs.

User avatar
Laskos
Posts: 10782
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: Sergio Vieri second net is out

Post by Laskos » Wed Jul 22, 2020 8:57 am

Rebel wrote:
Wed Jul 22, 2020 8:44 am
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).

Post Reply