Lc0 in CCC matches
Moderators: hgm, Rebel, chrisw
-
- Posts: 3292
- Joined: Wed Mar 08, 2006 8:15 pm
-
- Posts: 26
- Joined: Mon Oct 26, 2020 3:05 pm
- Full name: Pedro
Re: Lc0 in CCC matches
And what are the strongest nets or version of Lc0 today?
-
- Posts: 3292
- Joined: Wed Mar 08, 2006 8:15 pm
Re: Lc0 in CCC matches
Obviously same situation as with SF: no progress with nets in 6 months! Both have reached their limits?
Jouni
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: Lc0 in CCC matches
In my testings, T60 net 68002 is the strongest and clearly stronger than J94-100.
https://www.sp-cc.de/nn-vs-sf-testing.htm
-
- Posts: 12541
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Lc0 in CCC matches
I think they should go to double sized networks, like FF2.
On high end hardware at decent time controls, 384x30 are clearly the strongest amongst those tested by the LC0 group.
I have found on my hardware the big networks are considerably stronger tactically.
Since tactical strength appears to be a function of network size, it makes sense to try 2x nets and maybe 4x nets.
On high end hardware at decent time controls, 384x30 are clearly the strongest amongst those tested by the LC0 group.
I have found on my hardware the big networks are considerably stronger tactically.
Since tactical strength appears to be a function of network size, it makes sense to try 2x nets and maybe 4x nets.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 511
- Joined: Sun Apr 26, 2020 11:40 pm
- Full name: Brian D. Smith
Re: Lc0 in CCC matches
Do I smell an area where Team Dragon are going?Dann Corbit wrote: ↑Wed Apr 07, 2021 7:41 pm I think they should go to double sized networks, like FF2.
On high end hardware at decent time controls, 384x30 are clearly the strongest amongst those tested by the LC0 group.
I have found on my hardware the big networks are considerably stronger tactically.
Since tactical strength appears to be a function of network size, it makes sense to try 2x nets and maybe 4x nets.
-
- Posts: 708
- Joined: Mon Jan 16, 2012 6:34 am
Re: Lc0 in CCC matches
The point is resources!Dann Corbit wrote: ↑Wed Apr 07, 2021 7:41 pm I think they should go to double sized networks, like FF2.
On high end hardware at decent time controls, 384x30 are clearly the strongest amongst those tested by the LC0 group.
I have found on my hardware the big networks are considerably stronger tactically.
Since tactical strength appears to be a function of network size, it makes sense to try 2x nets and maybe 4x nets.
Bigger nets need longer time to train.And nobody knows which training methods/parameters is best to train. They are training on smaller nets like T70 to get those parameters before they can run on bigger nets.
Also, nobody knows plateau in current 30x384 nets are due to fully trained or just improperly trained.
-
- Posts: 12541
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: Lc0 in CCC matches
GPUs are also getting more powerful. Every 6 months or so, there will be a new crop, much more powerful than the previous.
I think the real problem with the LC0 approach right now is the miners who are hoarding the GPU cards.
It ramps up the price to sky-high and makes it hard for people to get the new technology.
And what is the produce of these bitcoin type miners?
It is the currency of criminals.
I think the real problem with the LC0 approach right now is the miners who are hoarding the GPU cards.
It ramps up the price to sky-high and makes it hard for people to get the new technology.
And what is the produce of these bitcoin type miners?
It is the currency of criminals.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: Lc0 in CCC matches
So true Dann,Dann Corbit wrote: ↑Thu Apr 08, 2021 4:52 pm GPUs are also getting more powerful. Every 6 months or so, there will be a new crop, much more powerful than the previous.
I think the real problem with the LC0 approach right now is the miners who are hoarding the GPU cards.
It ramps up the price to sky-high and makes it hard for people to get the new technology.
And what is the produce of these bitcoin type miners?
It is the currency of criminals.
Bitcoin Energy Consumption Debate
They say it crashes every 4 years, so wait for next Bitcoin Winter to get the latest GPU.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Lc0 in CCC matches
Lol, what do computer chess enthusiasts produce? What do you produce except burning electricity? What is the purpose of pushing a few Elo in a practically solved and dead game of chess???Dann Corbit wrote: ↑Thu Apr 08, 2021 4:52 pm GPUs are also getting more powerful. Every 6 months or so, there will be a new crop, much more powerful than the previous.
I think the real problem with the LC0 approach right now is the miners who are hoarding the GPU cards.
It ramps up the price to sky-high and makes it hard for people to get the new technology.
And what is the produce of these bitcoin type miners?
It is the currency of criminals.
Miners at least produce money and enable crypto transactions .