It is currently Thu Mar 28, 2024 5:27 am

All times are UTC - 8 hours [ DST ]




Post new topic Reply to topic  [ 418 posts ]  Go to page Previous  1 ... 9, 10, 11, 12, 13, 14, 15 ... 21  Next
Author Message
Offline
 Post subject: Re: LZ's progression
Post #221 Posted: Wed Dec 19, 2018 10:12 am 
Gosei
User avatar

Posts: 1753
Liked others: 177
Was liked: 491
Oops, I indeed made a confusion between two names. The game rn195_lz195_2sec_c_LZ_B-5.sgf was unfinished, so it's impossible to count.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #222 Posted: Thu Dec 20, 2018 7:17 pm 
Beginner

Posts: 13
Liked others: 1
Was liked: 3
Sometime RLO plays PASS at losing game, because they cannot find any good move, but win rate is bigger than a resign threshold.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #223 Posted: Sat Dec 22, 2018 1:57 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
new network 15x192 from bjiyxo is stronger lz157: 92297ff2 VS d351f06e 260 : 144 (64.36%)
http://zero.sjeng.org

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #224 Posted: Sat Dec 22, 2018 3:39 am 
Lives in gote

Posts: 337
Liked others: 22
Was liked: 97
100 game match between #196 and #157 at short time parity
1 min per side per game, komi 7.5 no pondering, 1x1080, LZ0.16, twogtp V1.5.0
0 duplicate game, 0 error, all games by resignation.
#196 wins 55:45
196 is now clearly stronger than 157, even at short time settings (both networks spending 0.5-0.6 sec/move)

The 100 games :
Attachment:
157_196_1minute.zip [81.87 KiB]
Downloaded 365 times
Detailed stats :
Attachment:
Pas de nom.jpg
Pas de nom.jpg [ 215.24 KiB | Viewed 7577 times ]

And wrote:
new network 15x192 from bjiyxo is stronger lz157: 92297ff2 VS d351f06e 260 : 144 (64.36%)
Very interesting !

I've launched a 100 game match at 1 min per game between #196 and this new network 92297ff2, result later.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #225 Posted: Sat Dec 22, 2018 6:36 am 
Lives in gote

Posts: 337
Liked others: 22
Was liked: 97
Here we are :
#196 (40x256) vs 92297ff2 (15x192) at short time parity : 1 min per side per game, komi 7.5, no pondering, 1x1080, LZ0.16, twogtp V1.5.0
0 duplicate game, 0 error, all games by resignation.

This time, #196 is not the winner :

92297ff2 v 196 : 63:37

It was to be expected, because 92297ff is stronger than #157.

The 100 games :
Attachment:
196_15x192black_1m.zip [82.36 KiB]
Downloaded 370 times
The stats :
Attachment:
Pas de nom.jpg
Pas de nom.jpg [ 685.42 KiB | Viewed 7528 times ]


This post by Vargo was liked by: And
Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #226 Posted: Sat Dec 22, 2018 10:14 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
I wonder if 92297ff2 is stronger than elf? (time parity)

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #227 Posted: Sat Dec 22, 2018 12:26 pm 
Dies with sente

Posts: 101
Liked others: 2
Was liked: 16
Rank: KGS 2 D
Vargo wrote:
Here we are :
#196 (40x256) vs 92297ff2 (15x192) at short time parity : 1 min per side per game, komi 7.5, no pondering, 1x1080, LZ0.16, twogtp V1.5.0
0 duplicate game, 0 error, all games by resignation.

This time, #196 is not the winner :



What is (maybe) unexpected, is that #196 is not as strong as #195 in some aspects. I had run some handicap games on my computer and got this feeling.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #228 Posted: Sat Dec 22, 2018 11:23 pm 
Dies with sente

Posts: 101
Liked others: 2
Was liked: 16
Rank: KGS 2 D
Just run two time parity games with 20 seconds per move between ELF and #196 and #196 won both games. It looks like to me that the 40b weight is indeed superior in handling large groups and taking advantage of a ko fight. However, I don't understand why #196 lost to the new 15b weight in the above tests. Maybe the game time is too short ( 1 minute )?

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #229 Posted: Sat Dec 22, 2018 11:47 pm 
Lives in gote

Posts: 337
Liked others: 22
Was liked: 97
splee99 wrote:
I don't understand why #196 lost to the new 15b weight in the above tests. Maybe the game time is too short ( 1 minute )?
I thinnk you're right.

I've run two more matches #196 v 92297ff at time parity :
the three results are :

1min/game (corresponding to visits=~300 and visits=~1100) #196 wins 37% (100 games, 1x1080)
5min/game (corresponding to visits=~1000 and visits=~3600) #196 wins 60% (20 games, 1x 1080)
5min/game with 2 GPU (corresponding to visits=~3000 and visits=~10800) #196 wins 65% (20 games, 2x 1080Ti)

I've done several tests to determine time-visits ratio, the results vary a lot, these correspondences are approximate.

games and stats for 2 gpus :
Attachment:
196_v_92297_5min_2gpu.zip [19.19 KiB]
Downloaded 360 times
Attachment:
2gpu.jpg
2gpu.jpg [ 247.26 KiB | Viewed 7409 times ]


This post by Vargo was liked by: Waylon
Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #230 Posted: Sun Dec 23, 2018 2:36 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
20 games is enough for a confident conclusion? I doubt, especially considering the slight advantage

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #231 Posted: Sun Dec 23, 2018 8:29 am 
Lives in gote

Posts: 337
Liked others: 22
Was liked: 97
And wrote:
20 games is enough for a confident conclusion?
20 games is not nearly enough, but each of these 20 game match is almost 3 hours...
After several such matches, we can hopefully see a trend.

Ideally, this kind of match should be... 400 games, for example ;-)
To do this, one possiblity would be to find 20 people OK to run a 20 game match with the same parameters including -v 1000 for #196 and -v 3600 for #92297ff, so, we would have 400 games at time parity, and at the same strength, I think -v 1000 and -v 3600 should be at near time parity on any machine (?)
But it would probably be more useful for people to donate their GPU time to autogtp.

Anyway, I ran 40 more games on each machine, and after 60 games, #196's winrate has gone down.

5min/game (corresponding to visits=~1000 and visits=~3600) #196 wins 52% (31:29, 1x 1080)
5min/game with 2 GPU (corresponding to visits=~3000 and visits=~10800) #196 wins 52% too (31:29, 2x 1080Ti)

I'll upload stats and/or games if someone wants them.


This post by Vargo was liked by: And
Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #232 Posted: Sun Dec 23, 2018 8:41 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
thanks! after such a result (52%) is not the fact that #196 is stronger

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #233 Posted: Mon Dec 24, 2018 3:03 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
Strange, why there is no new network 92297ff2 in the table "Best Network Hash"? (http://zero.sjeng.org) for example, under the number 197. it is logical and convenient

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #234 Posted: Mon Dec 24, 2018 3:43 am 
Lives in gote

Posts: 502
Liked others: 1
Was liked: 153
Rank: KGS 2k
GD Posts: 100
KGS: Tryss
Because this network is not trained the same way.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #235 Posted: Mon Dec 24, 2018 5:28 am 
Gosei

Posts: 1590
Liked others: 886
Was liked: 527
Rank: AGA 3k Fox 3d
GD Posts: 61
KGS: dfan
And wrote:
Strange, why there is no new network 92297ff2 in the table "Best Network Hash"? (http://zero.sjeng.org) for example, under the number 197. it is logical and convenient

It's a 15-block network, which played a test match against the previous best 15-block network, not against the current best 40-block network.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #236 Posted: Mon Dec 24, 2018 5:53 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
In the table there are other networks 15x192 (weaker) and from bjiyxo. where then to look for this network, if not in this table? the strongest 15x192!

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #237 Posted: Mon Dec 24, 2018 6:02 am 
Gosei

Posts: 1590
Liked others: 886
Was liked: 527
Rank: AGA 3k Fox 3d
GD Posts: 61
KGS: dfan
Each entry in the table is stronger than the entry before it (reading from bottom to top). To put this latest 15-block network one in, they'd have to either break that rule or change all the numbers or call this network 157a or something. Maybe they should have used a 2-dimensional numbering scheme.

I agree that it would be nice to have a place to easily find the best 15-block network.

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #238 Posted: Mon Dec 24, 2018 6:12 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
the table is made for the convenience of people, not for the report! besides, it has a Hash, Size, Elo, Games, Training. if a person came to this site, then this is not a random visitor, and he will understand what's what

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #239 Posted: Mon Dec 24, 2018 6:52 am 
Gosei

Posts: 1590
Liked others: 886
Was liked: 527
Rank: AGA 3k Fox 3d
GD Posts: 61
KGS: dfan
I was just trying to answer your original question of why it was not in the table. If you would like the format of the table to be changed, you could try opening an issue on the Leela Zero GitHub page: https://github.com/gcp/leela-zero/issues

Top
 Profile  
 
Offline
 Post subject: Re: LZ's progression
Post #240 Posted: Mon Dec 24, 2018 7:06 am 
Gosei
User avatar

Posts: 1348
Liked others: 202
Was liked: 203
Formal reasons are clear to me, but thanks anyway for your answers!


This post by And was liked by: dfan
Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 418 posts ]  Go to page Previous  1 ... 9, 10, 11, 12, 13, 14, 15 ... 21  Next

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: No registered users and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group