You need to specify -w <weight file>, you just missed the -w thingDaniel Shawul wrote:You should make the game against scorpio-mcts-min fairly first because it was using 1 core. If I assume that on the same hardware scorpio's evaluation is 100x faster than leela's (10x128 nn), then to be fair against a 1000 playouts leela on your GPU (i.e. if you have to run it on the GPU), the opponent engines should be using atleast 10 cores. That goes for the leela gauntlets you are doing with other engines too not only for scorpio.
P.S Anyone knows how to configure lczero on cutechess. I have thisBut it says it can't find the weights.txt fileCode: Select all
{ "name": "lczero", "command": "../engines/leela-chess/build/lczero", "workingDirectory": "../engines/leela-chess/build", "protocol": "uci", "options" : [ { "name" : "Hash", "value" : 64 } ] },
Does the working directory specification work for uci engines ?Code: Select all
Using 2 thread(s). Could not open weights file: weights.txt lczero: /home/daniel/engines/leela-chess/src/Network.cpp:376: static void Network::initialize(): Assertion `m_format_version > 0' failed. Aborted (core dumped)
The real elo of lczero is in its name
Moderators: hgm, Rebel, chrisw
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
I tried adding it to the command line even specifiying the full path again but didn't work.
Anyway i though recent versions default to weights.txt.
I tried the following
If I typed the last one directly on the command line it works, so it is probably an issue with the way cutechess handles working directories i think.
Anyway i though recent versions default to weights.txt.
I tried the following
Code: Select all
"command": "../engines/leela-chess/build/lczero",
"command": "../engines/leela-chess/build/lczero -w ID125",
"command": "../engines/leela-chess/build/lczero -w weights.txt",
"command": "../engines/leela-chess/build/lczero -w ../engines/leela-chess/build/weights.tx",
Code: Select all
daniel@dani-xp:~/cutechess-cli$ ./test.sh
Elo difference: nan +/- nan
Warning: Cannot start engine lczero:
Cannot execute command: ~/engines/leela-chess/build/lczero -w ~/engines/leela-chess/build/weights.txt
Finished match
daniel@dani-xp:~/cutechess-cli$ ~/engines/leela-chess/build/lczero -w ~/engines/leela-chess/build/weights.txt
Using 2 thread(s).
Detecting residual layers...v2...128 channels...10 blocks.
BLAS Core: Haswell
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
First results
The following worked
First result you are not going to like 90% for scorpio-mcts
I used a fast 20+0.1 and lczero is loosing almost all its games. I am not making any conclusions from this. My goal is to produce a plot by keep on doubing the time control until leela-chess starts to beat it. This may help to explain that leela is covering up its tactical weakness by conductng test games either at long time control (until it sees tactis that is trivial for full width searcher) or using a hardware that allows it to do many playouts to cover for its lack of tactical awareness.
Btw I am using ID 125 that is being used in tcec.
Code: Select all
{
"name": "lczero",
"command": "./lczero",
"workingDirectory": "../engines/leela-chess/build",
"protocol": "uci",
"options" : [
{
"name" : "Hash",
"value" : 64
}
]
},
Code: Select all
Finished game 23 (lczero vs scorpio-mcts-min): 0-1 {Black mates}
Score of lczero vs scorpio-mcts-min: 2 - 20 - 1 [0.109] 23
Started game 24 of 8000 (scorpio-mcts-min vs lczero)
Btw I am using ID 125 that is being used in tcec.
-
- Posts: 4606
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
The displayed speed in kN/s for Leela is wrong in TCEC.Daniel Shawul wrote:What is astounding is that it lost 20-0 against standard scorpio on single core. Your GPU is getting about 1 kN/s that is 3x slower than TCEC's which was getting about 3-4 kN/s.l
See my other post.
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
Ah, so it could be 3x more than what is displayed, so maybe 9-12x kN/s then.Guenther wrote:The displayed speed in kN/s for Leela is wrong in TCEC.Daniel Shawul wrote:What is astounding is that it lost 20-0 against standard scorpio on single core. Your GPU is getting about 1 kN/s that is 3x slower than TCEC's which was getting about 3-4 kN/s.l
See my other post.
20+0.1 is done now and it ended up a -420 for leela
Code: Select all
20+0.1
Score of lczero vs scorpio-mcts-min: 2 - 40 - 3 [0.078] 45
Elo difference: -429.59 +/- 252.08
SPRT: llr -3.01, lbound -2.94, ubound 2.94 - H0 was accepted
Finished match
Daniel
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: First results
20+0.1
40+0.1
Getting better. I am gonna cap of the rest of the matches at 50 games for the sake of time.
Code: Select all
Score of lczero vs scorpio-mcts-min: 2 - 40 - 3 [0.078] 45
Elo difference: -429.59 +/- 252.08
SPRT: llr -3.01, lbound -2.94, ubound 2.94 - H0 was accepted
Finished match
Code: Select all
Score of lczero vs scorpio-mcts-min: 3 - 35 - 8 [0.152] 46
Elo difference: -298.39 +/- 125.93
SPRT: llr -3.03, lbound -2.94, ubound 2.94 - H0 was accepted
Finished match
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
It is not wrong, what may be misleading is the total number of nodes, because of tree reuse. Those are not part of the real speed, it's like cache.Guenther wrote:The displayed speed in kN/s for Leela is wrong in TCEC.Daniel Shawul wrote:What is astounding is that it lost 20-0 against standard scorpio on single core. Your GPU is getting about 1 kN/s that is 3x slower than TCEC's which was getting about 3-4 kN/s.l
See my other post.
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 4185
- Joined: Tue Mar 14, 2006 11:34 am
- Location: Ethiopia
Re: First results
80+0.2
Stopped this one early as it seems it's gotten worse now. I m going for a 4x bigger time control now 320+0.4. But seeing Ferd's result with 12h+1min not optimistic that I would get this done soon. i.e. overpass the 2300-2400 elo scorpio-mcts-min on my "slow" i7 cpu that does 200 pps. A0 results could probably be explained by this massive hardware acceleration of its bulky NN eval to cover up for tactical weakness; just like an FGPA can be used to accelerate a massive evaluation. Strictly speaking from an algorithmic point of view however their MCTS sucks.
Note that
Code: Select all
Finished game 36 (scorpio-mcts-min vs lczero): * {No result}
Score of lczero vs scorpio-mcts-min: 0 - 30 - 5 [0.071] 35
Elo difference: -445.58 +/- 206.80
Finished match
Note that
-
- Posts: 2283
- Joined: Sat Jun 02, 2012 2:13 am
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
How are you able to run Leela in infinite analysis? My Leela (v0.6) runs analysis for about 1 sec and then it stops (running on cpu's).Nay Lin Tun wrote:I tested Leela with challenging puzzles. Lol
I let Leela run for infinite analysis for 12 mins. Had 3.3 million visits and she could not solve .LOl
Solution. e5!!
https://ibb.co/gjruBn[/url]
Thanks,
CL
-
- Posts: 4606
- Joined: Wed Oct 01, 2008 6:33 am
- Location: Regensburg, Germany
- Full name: Guenther Simon
Re: Leela 43 cores Versus Scorpio 32 cores at TCEC
If this is true I see no way to get a reliable bench with LCZero.CMCanavessi wrote:It is not wrong, what may be misleading is the total number of nodes, because of tree reuse. Those are not part of the real speed, it's like cache.Guenther wrote:The displayed speed in kN/s for Leela is wrong in TCEC.Daniel Shawul wrote:What is astounding is that it lost 20-0 against standard scorpio on single core. Your GPU is getting about 1 kN/s that is 3x slower than TCEC's which was getting about 3-4 kN/s.l
See my other post.
It can just print a fictional nps, because it does not show which nodes
are reused and which not.