SPCC: Testrun of Lc0 J104.1-30 finished

Discussion of computer chess matches and engine tournaments.

Moderators: hgm, Rebel, chrisw

User avatar
pohl4711
Posts: 2439
Joined: Sat Sep 03, 2011 7:25 am
Location: Berlin, Germany
Full name: Stefan Pohl

SPCC: Testrun of Lc0 J104.1-30 finished

Post by pohl4711 »

NN-testrun of Lc0 0.26.3 J104.1-30 finished. New highscore for a small 10x128 net.

https://www.sp-cc.de

After installing Cuda 11.2 by NVIDIA and the DotNet5-runtime environment by Microsoft, I succeeded running Ceres 0.80, using Chad's boxed version:


(This is not the slower debug-version! Using a 30x384 net, Ceres is around +18% faster, than Lc0 0.26.3 on my RTX 2060)

Now, I will do a NN-testrun with Ceres 0.80 66680 net (Lc0 0.26.3 has the highscore, using that net, in my NN-testings - will Ceres 0.80 be stronger?). Result in 3 days, if all works correctly...


(Perhaps you have to clear your browsercache or reload the website)
User avatar
Ozymandias
Posts: 1535
Joined: Sun Oct 25, 2009 2:30 am

Re: SPCC: Testrun of Lc0 J104.1-30 finished

Post by Ozymandias »

Will you also test Ceres with J104.1-30 net?
User avatar
pohl4711
Posts: 2439
Joined: Sat Sep 03, 2011 7:25 am
Location: Berlin, Germany
Full name: Stefan Pohl

Re: SPCC: Testrun of Lc0 J104.1-30 finished

Post by pohl4711 »

Ozymandias wrote: Tue Jan 05, 2021 11:17 am Will you also test Ceres with J104.1-30 net?
Yes, if Ceres runs stable through the first testrun. But not necessesarly direct after finishing the Ceres 66680 testrun...