From Discord channel:Guenther wrote: ↑Tue Aug 04, 2020 5:15 pm Good judgement...
As expected the cloning on NNUE nets has begun.
People can now test clones of engines with clones of nets w/o knowing they play A+A vs. A+A.
This so called qh-fine-0803-5 net is 99.99999% identical to Sergio Vieris net 20200729-0109.
Only at the very end of millions of hex entries 'someone' changed a few hex values
An amazing net for SF-NNUE.
Moderators: hgm, Rebel, chrisw
-
- Posts: 4467
- Joined: Fri Apr 21, 2006 4:19 pm
- Location: IASI - the historical capital of MOLDOVA
- Full name: SilvianR
Re: An amazing net for SF-NNUE.
-
- Posts: 4606
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: An amazing net for SF-NNUE.
You should have mentioned that he simply 'tried' to fine-tune an exisisting SV net (which failed miserably),Sylwy wrote: ↑Wed Aug 05, 2020 9:51 amFrom Discord channel:Guenther wrote: ↑Tue Aug 04, 2020 5:15 pm Good judgement...
As expected the cloning on NNUE nets has begun.
People can now test clones of engines with clones of nets w/o knowing they play A+A vs. A+A.
This so called qh-fine-0803-5 net is 99.99999% identical to Sergio Vieris net 20200729-0109.
Only at the very end of millions of hex entries 'someone' changed a few hex values ;-)
before jumping here and just post a link to something, praised as something new by you, w/o further informations.
After checking this discord channel, I see that he openly stated he used already a SV net for his previous attempt,
but not expliccitely for this new one, though.
Obviously his fine-tuning attempts failed either due to bugs or errors in his procedure.
The result remains the same. At least it seems not intentionally.
https://discord.com/channels/4359437104 ... 6523195462qhapaq_rope_6
03.08.2020
@linox qh 0726 is fine-tuned function from 20200721-1907.bin. It uses approximatedly 20 million positions.
There is no such message about qh-fine-0803-5.
-
- Posts: 4556
- Joined: Tue Jul 03, 2007 4:30 am
-
- Posts: 229
- Joined: Thu Mar 10, 2016 6:17 pm
- Location: Canada
Re: An amazing net for SF-NNUE.
-
- Posts: 4467
- Joined: Fri Apr 21, 2006 4:19 pm
- Location: IASI - the historical capital of MOLDOVA
- Full name: SilvianR
Re: An amazing net for SF-NNUE.
-
- Posts: 919
- Joined: Sat May 31, 2014 8:28 am
Re: An amazing net for SF-NNUE.
That's a nice list you have there...pohl4711 wrote: ↑Tue Aug 04, 2020 12:55 pmI tested it vs. SF 200717, like all S.Vieri nets. Look here:Zenmastur wrote: ↑Mon Aug 03, 2020 9:33 pmHow does this net fair against some of Sergio's more recent nets?Sylwy wrote: ↑Mon Aug 03, 2020 8:49 pm Trained on Reinforcement Learn and fine tuned using CCRL games:
https://www.dropbox.com/s/71qy3j8gtgch2 ... 5.zip?dl=0
https://www.sp-cc.de/files/ergebnisse_nnue_schnell.txt
The net is very strong, but not the best in that tests. The best is still sv200730_1934
While not enough games to be definitive it certainly gives one an idea of which nets to try and which to stay away from. I liked it enough to save a copy in my NNUE nets directory for future reference.
Regards,
Zenmastur
Only 2 defining forces have ever offered to die for you.....Jesus Christ and the American Soldier. One died for your soul, the other for your freedom.
-
- Posts: 2435
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: An amazing net for SF-NNUE.
That was the idea. Because S.Vieri builds so much new nets, it is not possible to test them all with some thousand games using a "quite normal" thinking-time (even though I use bullet-speed, 60''+0.5''). So, 500 games have to be enough...
But this list is only a collection of pre-tests, so, I can find out, which nets I should test in a regular 7000 game testrun (with 3'+1'') for my ratinglist... Not more, not less.