This leela seemed strong, 2 games played , 2 games draw vs stockfish is amazing.
Please test this leela.
https://drive.google.com/uc?id=11ueg-md ... t=download
This Leela, 20x256, seemed quite strong.
I played 3+2 mins blitz cuDNN 21st May (3rd version) Leela vs full strength latest vestion 4 cores i5 3.0GHZ stockfish on my 1060, for two games and both games draw. Opening book, perfect chess, 2017, 8 moves.
I will test more games later.
Nay
P.s average speed of Leela is around 2-2.5 Kn/s and average speed of stockfish is around 5 Mn/s.
https://lichess.org/UQytNWdL
https://lichess.org/IlhlNsul
20x256 Leela seemed quite strong
Moderators: hgm, Rebel, chrisw
-
- Posts: 291
- Joined: Wed May 08, 2013 6:49 am
Re: 20x256 Leela seemed quite strong
You mean it got stronger without additional training? How come?
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: 20x256 Leela seemed quite strong
Larger net, no oversampling, removal of a few million buggy games.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 12038
- Joined: Mon Jul 07, 2008 10:50 pm
Re: 20x256 Leela seemed quite strong
would lczero being the same as stockfish mean it is stronger than alphazero ?Nay Lin Tun wrote: ↑Fri May 25, 2018 1:43 pm This leela seemed strong, 2 games played , 2 games draw vs stockfish is amazing.
Please test this leela.
https://drive.google.com/uc?id=11ueg-md ... t=download
This Leela, 20x256, seemed quite strong.
I played 3+2 mins blitz cuDNN 21st May (3rd version) Leela vs full strength latest vestion 4 cores i5 3.0GHZ stockfish on my 1060, for two games and both games draw. Opening book, perfect chess, 2017, 8 moves.
I will test more games later.
Nay
P.s average speed of Leela is around 2-2.5 Kn/s and average speed of stockfish is around 5 Mn/s.
https://lichess.org/UQytNWdL
https://lichess.org/IlhlNsul
-
- Posts: 10948
- Joined: Wed Jul 26, 2006 10:21 pm
- Full name: Kai Laskos
Re: 20x256 Leela seemed quite strong
Well, it doesn't seem significantly stronger than 192x15 NN338 in my gauntlet, maybe weaker. It also performs a bit worse at 10s/position in both tactical and positional test suites. Probably due to 2x slower speed.Nay Lin Tun wrote: ↑Fri May 25, 2018 1:43 pm This leela seemed strong, 2 games played , 2 games draw vs stockfish is amazing.
Please test this leela.
https://drive.google.com/uc?id=11ueg-md ... t=download
This Leela, 20x256, seemed quite strong.
I played 3+2 mins blitz cuDNN 21st May (3rd version) Leela vs full strength latest vestion 4 cores i5 3.0GHZ stockfish on my 1060, for two games and both games draw. Opening book, perfect chess, 2017, 8 moves.
I will test more games later.
Nay
P.s average speed of Leela is around 2-2.5 Kn/s and average speed of stockfish is around 5 Mn/s.
https://lichess.org/UQytNWdL
https://lichess.org/IlhlNsul
Gauntlet (will continue to 60 games each Lc0) with the latest cuDNN Lc0 on GTX 1060 GPU, latest 256x20 net, and NN338 192x15 net, against Houdini 1.5a on one 3.8 GHz core of i7. Time control: 1s/move. Openings: balanced short 3-mover from GM games.
Code: Select all
Games Completed = 50 of 120 (Avg game length = 116.917 sec)
Settings = Gauntlet/64MB/1000ms per move/M 9000cp for 30 moves, D 150 moves/EPD:C:\LittleBlitzer\3moves_GM_04.epd(817)
Time = 6207 sec elapsed, 8689 sec remaining
1. Houdini 1.5a 28.5/50 23-16-11 (L: m=16 t=0 i=0 a=0) (D: r=9 i=1 f=0 s=0 a=1) (tpm=1001.3 d=19.47 nps=3639708)
2. Lc0 NN338 12.0/25 10-11-4 (L: m=11 t=0 i=0 a=0) (D: r=4 i=0 f=0 s=0 a=0) (tpm=753.0 d=3.27 nps=5003)
3. Lc0 NN 256x20 9.5/25 6-12-7 (L: m=12 t=0 i=0 a=0) (D: r=5 i=1 f=0 s=0 a=1) (tpm=777.8 d=2.07 nps=2505)
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: 20x256 Leela seemed quite strong
The author pointed out this did not include the buggy game removal yet, though it is a test he plans to make.Laskos wrote: ↑Fri May 25, 2018 6:03 pmWell, it doesn't seem significantly stronger than 192x15 NN338 in my gauntlet, maybe weaker. It also performs a bit worse at 10s/position in both tactical and positional test suites. Probably due to 2x slower speed.Nay Lin Tun wrote: ↑Fri May 25, 2018 1:43 pm This leela seemed strong, 2 games played , 2 games draw vs stockfish is amazing.
Please test this leela.
https://drive.google.com/uc?id=11ueg-md ... t=download
This Leela, 20x256, seemed quite strong.
I played 3+2 mins blitz cuDNN 21st May (3rd version) Leela vs full strength latest vestion 4 cores i5 3.0GHZ stockfish on my 1060, for two games and both games draw. Opening book, perfect chess, 2017, 8 moves.
I will test more games later.
Nay
P.s average speed of Leela is around 2-2.5 Kn/s and average speed of stockfish is around 5 Mn/s.
https://lichess.org/UQytNWdL
https://lichess.org/IlhlNsul
Gauntlet (will continue to 60 games each Lc0) with the latest cuDNN Lc0 on GTX 1060 GPU, latest 256x20 net, and NN338 192x15 net, against Houdini 1.5a on one 3.8 GHz core of i7. Time control: 1s/move. Openings: balanced short 3-mover from GM games.I will report later on the final result. Keep in mind that Lc0 scales better than standard AB engines, so it is stronger at LTC.Code: Select all
Games Completed = 50 of 120 (Avg game length = 116.917 sec) Settings = Gauntlet/64MB/1000ms per move/M 9000cp for 30 moves, D 150 moves/EPD:C:\LittleBlitzer\3moves_GM_04.epd(817) Time = 6207 sec elapsed, 8689 sec remaining 1. Houdini 1.5a 28.5/50 23-16-11 (L: m=16 t=0 i=0 a=0) (D: r=9 i=1 f=0 s=0 a=1) (tpm=1001.3 d=19.47 nps=3639708) 2. Lc0 NN338 12.0/25 10-11-4 (L: m=11 t=0 i=0 a=0) (D: r=4 i=0 f=0 s=0 a=0) (tpm=753.0 d=3.27 nps=5003) 3. Lc0 NN 256x20 9.5/25 6-12-7 (L: m=12 t=0 i=0 a=0) (D: r=5 i=1 f=0 s=0 a=1) (tpm=777.8 d=2.07 nps=2505)
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 12538
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: 20x256 Leela seemed quite strong
Two games is a rather small sample.Nay Lin Tun wrote: ↑Fri May 25, 2018 1:43 pm This leela seemed strong, 2 games played , 2 games draw vs stockfish is amazing.
Please test this leela.
https://drive.google.com/uc?id=11ueg-md ... t=download
This Leela, 20x256, seemed quite strong.
I played 3+2 mins blitz cuDNN 21st May (3rd version) Leela vs full strength latest vestion 4 cores i5 3.0GHZ stockfish on my 1060, for two games and both games draw. Opening book, perfect chess, 2017, 8 moves.
I will test more games later.
Nay
P.s average speed of Leela is around 2-2.5 Kn/s and average speed of stockfish is around 5 Mn/s.
https://lichess.org/UQytNWdL
https://lichess.org/IlhlNsul
After two thousand, we can make a better conclusion.
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: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: 20x256 Leela seemed quite strong
Really, 20x256 is looking really good !Albert Silver wrote: ↑Fri May 25, 2018 2:58 pmLarger net, no oversampling, removal of a few million buggy games.
lc0 CUDA just beat Komodo 11.2.2 in a 10'+10" Game.
Slower but ZERO Blunders.
https://lichess.org/g2ebFdCr
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis
-
- Posts: 708
- Joined: Mon Jan 16, 2012 6:34 am
Re: 20x256 Leela seemed quite strong
Sure, if Leela got 50% scores vs stockfish after playing 2000 games, then there is reasonable confidence that Leela will be within 20-30 elo . Well at least, I wont do that , it is so boring for me. In comparision with other results from other testers, the general conclusion is that Leela on my 1060GTX card is within 300-500 elo range vs 4 cores stockfish , (results may vary depending on the hardware and time control).
I tested multiple blitz games of leela vs stockfish before, previous versions of leela never survive as black.This version amazed me cos, it was the first version of leela that could survive as black.
I tested multiple blitz games of leela vs stockfish before, previous versions of leela never survive as black.This version amazed me cos, it was the first version of leela that could survive as black.
-
- Posts: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: 20x256 Leela seemed quite strong
No 'may vary' about it. It will DEFINITELY vary depending on the Hardware and TC used.Nay Lin Tun wrote: ↑Fri May 25, 2018 7:19 pm (results may vary depending on the hardware and time control).
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis