Well, I'm currently testing ID 25 of the 1st test run, and it's already proving to be around 2900. That's impressive, a 2900 network made in 3 days and only 1 million games. Oh, and it's still 64x6 size. I'm just speechless at that. A0 was trained on 44 million games for comparison, and the 1st (and bugged) Leela run got to around that level of performance after like 320 networks.Ozymandias wrote: ↑Sat Jun 09, 2018 9:15 pmMy perception is that maybe too much is happening at once, and that probably because of that, progress has nearly stalled.CMCanavessi wrote: ↑Sat Jun 09, 2018 6:08 pmthe perception by the community might well be that nothing is happening and that progress has stalled, which is completely understandable.
First Win by Leela Chess Zero against Stockfish dev
Moderators: hgm, Rebel, chrisw
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: First Win by Leela Chess Zero against Stockfish dev
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 1795
- Joined: Thu Sep 18, 2008 10:24 pm
Re: First Win by Leela Chess Zero against Stockfish dev
Yes that is...remarkable. The next week will be fascinating.CMCanavessi wrote: ↑Sat Jun 09, 2018 10:38 pm
Well, I'm currently testing ID 25 of the 1st test run, and it's already proving to be around 2900. That's impressive, a 2900 network made in 3 days and only 1 million games. Oh, and it's still 64x6 size. I'm just speechless at that. A0 was trained on 44 million games for comparison, and the 1st (and bugged) Leela run got to around that level of performance after like 320 networks.
-
- Posts: 1533
- Joined: Sun Oct 25, 2009 2:30 am
Re: First Win by Leela Chess Zero against Stockfish dev
Did you test the old id45? Also around 1 million games.CMCanavessi wrote: ↑Sat Jun 09, 2018 10:38 pmI'm currently testing ID 25 of the 1st test run, and it's already proving to be around 2900. That's impressive, a 2900 network made in 3 days and only 1 million games.
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: First Win by Leela Chess Zero against Stockfish dev
ID 45 was around 1500 elo (I tested 44 and got 1496.7). Must account for different software though, which made a huge progress.
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls
-
- Posts: 1533
- Joined: Sun Oct 25, 2009 2:30 am
Re: First Win by Leela Chess Zero against Stockfish dev
That's indeed some difference.
-
- Posts: 47
- Joined: Mon Oct 31, 2016 9:45 pm
Re: First Win by Leela Chess Zero against Stockfish dev
A very strong indicator that DeepMind put basically zero effort into optimizing A0 for chess. After all, chess is a simpler game than Go, so theoretically speaking, it makes sense that a smaller net would be able to achieve more in chess than it could in Go. (A fully optimized A0 would presumably have been much stronger than the version of A0 we saw.) Sadly, the bugs in Leela's first "trial run" obscured that fact, making many people think that the 6-block net reached its ceiling prematurely. Looking forward to seeing what the true ceiling of the 64x6 net is!CMCanavessi wrote: ↑Sat Jun 09, 2018 10:38 pmWell, I'm currently testing ID 25 of the 1st test run, and it's already proving to be around 2900. That's impressive, a 2900 network made in 3 days and only 1 million games. Oh, and it's still 64x6 size. I'm just speechless at that. A0 was trained on 44 million games for comparison, and the 1st (and bugged) Leela run got to around that level of performance after like 320 networks.Ozymandias wrote: ↑Sat Jun 09, 2018 9:15 pmMy perception is that maybe too much is happening at once, and that probably because of that, progress has nearly stalled.CMCanavessi wrote: ↑Sat Jun 09, 2018 6:08 pmthe perception by the community might well be that nothing is happening and that progress has stalled, which is completely understandable.
-
- Posts: 1339
- Joined: Fri Nov 02, 2012 9:43 am
- Location: New Delhi, India
Re: First Win by Leela Chess Zero against Stockfish dev
Well, I hope this new Leela is better than the old one at least in the End-game.
In two 2 minute/move games (which took up a lot of time), lc0 let slip the advantage against Komodo and was forced to concede Draws.
lc0 was showing Scores like +3.40 and for once even the opponent Komodo seemed to agree by showing Scores like -1.85 to -1.95 .
Against Stockfish, Komodo would have caved in, but it held on for Draws against lc0.
Disappointing.
The wait just got longer.
In two 2 minute/move games (which took up a lot of time), lc0 let slip the advantage against Komodo and was forced to concede Draws.
lc0 was showing Scores like +3.40 and for once even the opponent Komodo seemed to agree by showing Scores like -1.85 to -1.95 .
Against Stockfish, Komodo would have caved in, but it held on for Draws against lc0.
Disappointing.
The wait just got longer.
i7 5960X @ 4.1 Ghz, 64 GB G.Skill RipJaws RAM, Twin Asus ROG Strix OC 11 GB Geforce 2080 Tis
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
Re: First Win by Leela Chess Zero against Stockfish dev
Brianfish defeats lczero
1. e4 c5
2. Nf3 d6
3. d4 cxd4
4. Nxd4 Nf6
5. Nc3 Nc6
6. Nxc6 bxc6
7. Be2 e5
8. O-O Be7
9. Qd3 O-O
10. Qg3 Be6
11. f4 exf4
12. Bxf4 Qb6+
13. Kh1 Qxb2
14. Rab1 Qxc2
15. Bh6 g6
16. Bxf8 Bxf8
17. Rxf6 Bg7
18. e5 Bxf6
19. exf6 Bxa2
20. Qe3 Bxb1
21. Qh6 Qxc3
22. Qg7#
1. e4 c5
2. Nf3 d6
3. d4 cxd4
4. Nxd4 Nf6
5. Nc3 Nc6
6. Nxc6 bxc6
7. Be2 e5
8. O-O Be7
9. Qd3 O-O
10. Qg3 Be6
11. f4 exf4
12. Bxf4 Qb6+
13. Kh1 Qxb2
14. Rab1 Qxc2
15. Bh6 g6
16. Bxf8 Bxf8
17. Rxf6 Bg7
18. e5 Bxf6
19. exf6 Bxa2
20. Qe3 Bxb1
21. Qh6 Qxc3
22. Qg7#
Advanced Micro Devices fan.
-
- Posts: 1766
- Joined: Wed Jun 03, 2009 12:14 am
Re: First Win by Leela Chess Zero against Stockfish dev
i'm only getting 50-70% GPU usage with the testserver net, is that due to the smaller size or changes in the .exe's (https://crem.xyz/lc0/)?
-
- Posts: 1142
- Joined: Thu Dec 28, 2017 4:06 pm
- Location: Argentina
Re: First Win by Leela Chess Zero against Stockfish dev
How many threads? You need a beefy CPU to feed a fast GPU and make it work at 100%yanquis1972 wrote: ↑Sun Jun 10, 2018 7:55 pm i'm only getting 50-70% GPU usage with the testserver net, is that due to the smaller size or changes in the .exe's (https://crem.xyz/lc0/)?
Follow my tournament and some Leela gauntlets live at http://twitch.tv/ccls