Life In 19x19
https://lifein19x19.com/

LZ's progression
https://lifein19x19.com/viewtopic.php?f=18&t=15718
Page 16 of 21

Author:  splee99 [ Wed Jan 30, 2019 10:17 pm ]
Post subject:  Re: LZ's progression

I have tried minigov15-modeste_converted and minigov15-cormorant_converted. They look indeed stronger than ELFv1. The minigo style is really far from human style. I don't see apparent activities of acquiring solid territory, nor building walls in the center. It just plays rock solid, so the ELF's sharp attack is not effective. However, this also means it is bad at (giving) handicap games because minigo is not good at attacking opponents weakness, in particular, regarding ko fights and capture races.

Author:  Vargo [ Thu Jan 31, 2019 4:59 am ]
Post subject:  Re: LZ's progression

10 game match
Elfv1 v. MG_000513_revenge

LZ0.16, twogtp 1.5.0 , 2x1080Ti, 8000 visits for Elf, 4000 visits for 513 (corresponding roughly to 2.6 and 3s/move)
-r 5 , no pondering
result : Elf wins 8-2

Attachment:
513_elf.jpg
513_elf.jpg [ 388.04 KiB | Viewed 2506 times ]
NB. I forgot to change the default sgf name, so, the games are labelled mg990elf_v4000-x.sgf, but the network used is revenge_000513, as you can see in the command line.

Author:  Vargo [ Sun Feb 03, 2019 10:17 pm ]
Post subject:  Re: LZ's progression

The first picture of this post shows contrasted results for 990_cormorant v. Elfv1 (cormorant wins at 10s/move and at 120s, but loses at 60s/move)

Here are two more 10 game matches with settings comparable to his 10s/move.
gpu: 2x1080Ti, constant 5s/move (5.03s effectively used) , twogtp, -alternate, -r 5, no pondering
All games by resignation, no error, no duplicate game.
Average length is 247 moves for the first 10 game match, and 212 moves for the second match.

Result : Elf wins 12-8

If we add the results of the three 10 game matches, we get ... 15-15
My conclusion is that 990 cormorant and Elfv1 are about the same strength at 10s/move with one 1080Ti. ;-)

Stats :
Attachment:
1.jpg
1.jpg [ 294.46 KiB | Viewed 2350 times ]
Attachment:
2.jpg
2.jpg [ 274.02 KiB | Viewed 2350 times ]

I'll upload the games if someone wants them.

Author:  And [ Sun Feb 03, 2019 11:27 pm ]
Post subject:  Re: LZ's progression

new network 15x192 60:40 over f438268e:
https://github.com/leela-zero/leela-zero/issues/2192

Author:  And [ Tue Feb 05, 2019 3:08 am ]
Post subject:  Re: LZ's progression

Vargo wrote:
My conclusion is that 990 cormorant and Elfv1 are about the same strength at 10s/move with one 1080Ti.

"v15-19x19_models_000990-cormorant_converted_quantized.txt" is stronger than "000990-cormorant_converted.txt"
https://github.com/leela-zero/leela-zer ... -459413040

Author:  Pippen [ Tue Feb 05, 2019 7:40 am ]
Post subject:  Re: LZ's progression

Is there a possiblity to download the last - say 100.000 games - from LZ's self play as a sgf collection?

Author:  Tryss [ Tue Feb 05, 2019 9:47 am ]
Post subject:  Re: LZ's progression

See here :

https://leela.online-go.com/zero/

Author:  And [ Thu Feb 07, 2019 3:43 am ]
Post subject:  Re: LZ's progression

does anyone know where to download LZ ZQ elf-2, LZ ZQ elf-5 ?
https://github.com/breakwa11/GoAIRatings

Author:  Vargo [ Wed Feb 13, 2019 9:56 am ]
Post subject:  Re: LZ's progression

20 game match at time parity between
LZ0.16 #204 and LZ0.16 Elfv2
1x1080, twogtp 1.5.0, 5min per side and per game.

Elfv2 wins 13-7
All games by resignation, no error, no duplicate game.
Stats :
Attachment:
204 v elfv2.gif
204 v elfv2.gif [ 52.85 KiB | Viewed 1922 times ]

Author:  Uberdude [ Wed Feb 13, 2019 10:07 am ]
Post subject:  Re: LZ's progression

Vargo, about how many playouts per move is this? The official LZ test was 1600 each and LZ won 65%.

Author:  Vargo [ Wed Feb 13, 2019 10:44 am ]
Post subject:  Re: LZ's progression

Uberdude wrote:
how many playouts per move is this?
5 min per side and per game is, in fact, ~3.5 min/game effectively used, and is ~2s/move. It's similar to -v 1600 for #204 and -v 3000 for Elfv2 , all this with 1x1080.

Author:  Vargo [ Thu Feb 14, 2019 9:39 am ]
Post subject:  Re: LZ's progression

Another 10 game match between LZ0.16_#204 and LZ0.16_Elfv2 at time parity
2x1080Ti, 5 minutes per side per game (probably similar to -v 5000 for #204 and to -v 9000 for Elfv2)
twogtp 1.5.0, no pondering, komi 7.5, no duplicate game, no error.
Result : Elfv2 wins 7-3.

The games :
Attachment:
204_Elfv2.zip [9.67 KiB]
Downloaded 19 times
I've used "-alternate", so, #204 is B in the even numbered games, and #204 is W for the odd numbers.
(#204 only won the games numbered 1, 3, and 6)


The command lines and the stats :
Attachment:
elfv2v204.gif
elfv2v204.gif [ 50.97 KiB | Viewed 1862 times ]

Author:  nbc44 [ Sun Feb 17, 2019 9:47 pm ]
Post subject:  Re: LZ's progression

LZ0.16_#204 vs LZ0.16_Elfv2 2x1080Ti, 3s per move:
gogui-twogtp -black "C:\APPS\l0gpu16\leelaz.exe --gtp --weights=C:\APPS\net\05d10f27.gz -t 12 --gpu 0 --gpu 1 --noponder --precision single" -white "C:\APPS\l0gpu16\leelaz.exe --gtp --weights=C:\APPS\net\05dbca15.gz -t 12 --gpu 0 --gpu 1 --noponder --precision single" -games 100 -sgffile 204-elfv2 -auto -time 1s+4s/1 -komi 7.5 -verbose
gogui-twogtp -white "C:\APPS\l0gpu16\leelaz.exe --gtp --weights=C:\APPS\net\05d10f27.gz -t 12 --gpu 0 --gpu 1 --noponder --precision single" -black "C:\APPS\l0gpu16\leelaz.exe --gtp --weights=C:\APPS\net\05dbca15.gz -t 12 --gpu 0 --gpu 1 --noponder --precision single" -games 100 -sgffile elfv2-204 -auto -time 1s+4s/1 -komi 7.5 -verbose

Nothing interesting:

Code:
+28-72=0 (as black)
+34-66=0 (as white)

Total: +62-138=0

Attachments:
204-elfv2-stat.zip [5.72 KiB]
Downloaded 17 times

Author:  Vargo [ Tue Feb 19, 2019 3:10 am ]
Post subject:  Re: LZ's progression

nbc44 wrote:
Nothing interesting:
Why do you say that ? I find it very interesting, particularly considering it's 200 games :tmbup: !
________________________________________________________________________________________

New network #205

40 game match #205 v. Elfv2

1x1080, 5min per side and per game, no pondering, komi 7.5

Elfv2 wins 25-15 (62.5 %)

40 games :
Attachment:
elfV2_205.zip [34.9 KiB]
Downloaded 17 times

Command lines and stats (205 is B) :
Attachment:
Elfv2_205B.gif
Elfv2_205B.gif [ 96.14 KiB | Viewed 1560 times ]
Command lines and stats (205 is W) :
Attachment:
Elfv2_205W.gif
Elfv2_205W.gif [ 99.14 KiB | Viewed 1560 times ]

Author:  nbc44 [ Tue Feb 19, 2019 9:15 pm ]
Post subject:  Re: LZ's progression

Vargo wrote:
Why do you say that ? I find it very interesting, particularly considering it's 200 games :tmbup: !

I suppose the test result is predetermined.

Long test now:
LZ0.16_#205 vs LZ0.16_Elfv2 - 2x1080Ti, 120s (wow!) per move, (it will be 10 games):

+1-4=0 (#205 is black)
+1-4=0 (#205 is white)

Elfv2 wins 8-2 (80 %)

P.S.
Dragon tail loss :o :


Attachments:
File comment: logs-part2
elfv2-205.zip [1.21 MiB]
Downloaded 13 times
File comment: logs-part1
205-elfv2.zip [1.26 MiB]
Downloaded 13 times
games.zip [10.1 KiB]
Downloaded 16 times

Author:  Vargo [ Sun Mar 03, 2019 8:25 am ]
Post subject:  Re: LZ's progression

In another thread, @jlt wrote an interesting comment :
Quote:
... I would be surprised if, for some n, LeelaZero(n) didn't beat LeelaZero(n-10) more than 50% of the time.


The last 40b network is #207, it's now 50 networks away from the last 15b, and 30+ networks from the last 20b.

20 game matches LZ(n) v. LZ(n-10) at time parity, 3 min/game and /side, 1x1080, komi 7.5, no pondering, LZ0.16, twogtp 1.5.0.

#207 v. #197 --> 12-8 (40b v. 40b)
#197 v. #187 --> 12-8 (40b v. 40b)
#187 v. #177 --> 15-5 (40b v. 40b)
#177 v. #167 --> 13-7 (40b v. 20b)
#167 v. #157 --> 5-15 (20b v. 15b)

And one more match : LZ(n) v. LZ(n-50)

#207 v. #157 --> 15-5 (40b v. 15b)

All games by resignation, no error, no duplicate game.

Average time was around 1.3 sec/move.

Below, the little hands point the networks #157,167,177, etc.
Attachment:
elo2.gif
elo2.gif [ 27.31 KiB | Viewed 1226 times ]

If someone wants the games or the stats, I'll upload them.

Author:  jlt [ Sun Mar 03, 2019 8:32 am ]
Post subject:  Re: LZ's progression

Yes, I should have added the condition "if LZ(n) and LZ(n-10) are networks of the same size". Changing the network size introduces some discontinuity. When 20-block networks were introduced, results were disappointing, that's why the LeelaZero project shifted to 40 blocks rather quickly.

Author:  Vargo [ Sun Mar 03, 2019 9:45 am ]
Post subject:  Re: LZ's progression

You're right, 15b #157 was a turning point, and 20b #158 was weaker.

Another 20 game match (just finished, with the same parameters) :
LZ(n) v. LZ(n-49)

#207 v. #158 --> 19-1 (40b v. 20b)

Not very surprising, but still... it's hard to pretend that LZ doesn't progress anymore ;-)

Author:  Vargo [ Mon Mar 04, 2019 10:41 am ]
Post subject:  Re: LZ's progression

100 game match : LZ(today) v. LZ(1 year ago)

One year ago, the best LZ network was #90 (6x128)
2 minutes per game and side, LZ0.16, twogtp 1.5.0 no pondering, komi 7.5, gpu : 1x1080

Try to guess the result :scratch:
NB. Because of the "-alternate" command, #207 is always named B, even though it was W 50 times.
Attachment:
90.jpg
90.jpg [ 331.19 KiB | Viewed 1092 times ]

Author:  Vargo [ Sat Mar 09, 2019 10:46 pm ]
Post subject:  Re: LZ's progression

What's the effect of the number of visits on a given network ?
For example, what would be the score of LZ#207 --visits=801 v. LZ#207 --visits=1601 ?

I ran such a match yesterday (#207 with --visits=1, --visits=401, --visits=801, --visits=1601, --visits=3201) but... the results were inconclusive, more than half the games were duplicates :sad: :sad: :sad:
Attachment:
dup.gif
dup.gif [ 46.78 KiB | Viewed 797 times ]
probably because #207 knows all the tricks of #207 ;-)

______________________________________________________________________________

Anyway, there's a new network, #208.
20 game matches : #208 with various visits counts, and -m 40
-m 40 is used to have a bit more randomness in the first 40 moves, and so, avoid duplicate games.

Code:
gogui-twogtp -black "C:\PATH TO LZ\leelaz.exe --gtp --weights=C:\PATH TO NETWORKS\208.gz --noponder -m 40 -v yyyy" -white "C:\PATH TO LZ\leelaz.exe --gtp --weights=C:\PATH TO NETWORKS\208.gz --noponder -m 40 -v zzzz" -games 20 -sgffile XXX -auto -komi 7.5 -alternate
twogtp 1.5.0, LZ0.16, gpu:1x1080
no duplicate game, no error.

time/move seems to scale linearly :
-v 1 : ~0 sec/move
-v 401 : ~0.8
-v 801 : ~1.5
-v 1601 : ~3
-v 3201 : ~5 to 6


Results :
Attachment:
208.gif
208.gif [ 9.4 KiB | Viewed 797 times ]



If someone wants all the stats (times, lengthes, etc) , I'll upload them.


All the games :
The smallest number of visits is always B in the even numbered games (and W in the odd ones)
for example, 208_401_801-17 is game number 17 between #208 with 400 visits and # 208 with 800 visits. 400 visits is W

Attachment:
games.zip [143.93 KiB]
Downloaded 13 times

Page 16 of 21 All times are UTC - 8 hours [ DST ]
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group
http://www.phpbb.com/