LCZero Testmatch
Seite 1 von 1
LCZero Testmatch
Testmatches under CEGT conditions 40/20: - running on this pc 40/10 real.
(startposition 87kns) (166 = 5169.70)
1 LCZero 0.7/166 1CPU 2057 011½10½0½0½½111½10½0 10.5/20
2 Anechka 0.08 2040 100½01½1½1½½000½01½1 9.5/20
Lczero 187= 5297.69 (startposition 87kns)
1 LCZero 0.7 1CPU 2166 +126 100½1111111010½1½½½1 13.5/20
2 Anechka 0.08 2040 -126 011½0000000101½0½½½0 6.5/20
Lczero 181= 5267.33 (startposition 87kns)
1 EveAnn 1.72 2071 +108 0½1110½110111010½11½ 13.0/20
2 LCZero 0.7/181 1CPU 1963 -108 1½0001½001000101½00½ 7.0/20
Lczero 187 = 5297.69 and GPU Intel Graphics 630 (startposition 145kns)
1 LCZero GPU v0.7/187 1CPU 2124 +53 ½010½01½111½1100101½ 11.5/20
2 EveAnn 1.72 2071 -53 ½101½10½000½0011010½ 8.5/20
Lczero 217 = 5405.12 1CPU (startposition 87kns)
1 LCZero/217 0.7 1CPU 2197 +126 1010100111111101½½½1 13.5/20
2 EveAnn 1.72 2071 -126 0101011000000010½½½0 6.5/20
Lczero 187 = 5297.69 (startposition 87kns)
1 LCZero 0.7 1CPU 2123 010½001101100½111½0½ 10.0/20 100.00
2 Popochin 4.0 2123 101½110010011½000½1½ 10.0/20 100.00
Lczero 217 = 5405.12 1CPU (startposition 87kns)
1 LCZero 0.7 1CPU 2504 +381 1111111111½111111½10 18.0/20 !?
2 Popochin 4.0 2123 -381 0000000000½000000½01 2.0/20
Lczero 187 = 5297.69 (startposition 365 kns)
1 The Baron 3.42 x64 1CPU 2669 +190 11110½101111110½0111 15.0/20
2 LCZero 0.7 CPU 8Threads 2479 -190 00001½010000001½1000 5.0/20
Lczero 187 = 5297.69 (startposition 572 kns)
1 lczero v0.7 4CPU 2598 +89 ½1010½1111000101½111 12.5/20
2 Djinn 1.021 x64 2509 -89 ½0101½0000111010½000 7.5/20
Lczero 217 = 5405.12 1CPU (startposition 87kns) (+100 in selfplay = +50 against other opponents)
1 Djinn 1.021 x64 2509 +190 ½½11½1½101110½11111½ 15.0/20
2 LCZero 0.7 1CPU 2319 -190 ½½00½0½010001½00000½ 5.0/20
(startposition 87kns) (166 = 5169.70)
1 LCZero 0.7/166 1CPU 2057 011½10½0½0½½111½10½0 10.5/20
2 Anechka 0.08 2040 100½01½1½1½½000½01½1 9.5/20
Lczero 187= 5297.69 (startposition 87kns)
1 LCZero 0.7 1CPU 2166 +126 100½1111111010½1½½½1 13.5/20
2 Anechka 0.08 2040 -126 011½0000000101½0½½½0 6.5/20
Lczero 181= 5267.33 (startposition 87kns)
1 EveAnn 1.72 2071 +108 0½1110½110111010½11½ 13.0/20
2 LCZero 0.7/181 1CPU 1963 -108 1½0001½001000101½00½ 7.0/20
Lczero 187 = 5297.69 and GPU Intel Graphics 630 (startposition 145kns)
1 LCZero GPU v0.7/187 1CPU 2124 +53 ½010½01½111½1100101½ 11.5/20
2 EveAnn 1.72 2071 -53 ½101½10½000½0011010½ 8.5/20
Lczero 217 = 5405.12 1CPU (startposition 87kns)
1 LCZero/217 0.7 1CPU 2197 +126 1010100111111101½½½1 13.5/20
2 EveAnn 1.72 2071 -126 0101011000000010½½½0 6.5/20
Lczero 187 = 5297.69 (startposition 87kns)
1 LCZero 0.7 1CPU 2123 010½001101100½111½0½ 10.0/20 100.00
2 Popochin 4.0 2123 101½110010011½000½1½ 10.0/20 100.00
Lczero 217 = 5405.12 1CPU (startposition 87kns)
1 LCZero 0.7 1CPU 2504 +381 1111111111½111111½10 18.0/20 !?
2 Popochin 4.0 2123 -381 0000000000½000000½01 2.0/20
Lczero 187 = 5297.69 (startposition 365 kns)
1 The Baron 3.42 x64 1CPU 2669 +190 11110½101111110½0111 15.0/20
2 LCZero 0.7 CPU 8Threads 2479 -190 00001½010000001½1000 5.0/20
Lczero 187 = 5297.69 (startposition 572 kns)
1 lczero v0.7 4CPU 2598 +89 ½1010½1111000101½111 12.5/20
2 Djinn 1.021 x64 2509 -89 ½0101½0000111010½000 7.5/20
Lczero 217 = 5405.12 1CPU (startposition 87kns) (+100 in selfplay = +50 against other opponents)
1 Djinn 1.021 x64 2509 +190 ½½11½1½101110½11111½ 15.0/20
2 LCZero 0.7 1CPU 2319 -190 ½½00½0½010001½00000½ 5.0/20
Re: LCZero Testmatch
Now testing new Network 15x192! CEGT Conditions 40/20
PC Benchmarks: t=1 Startposition depth 20 CPU Version 31 nps (before I had 87)
Network 227 = 5501.53 (I did not await such a jump from 2319 before)
1 Djinn 1.021 x64 2509 +70 ½½11½10100111½100½1½ 12.0/20
2 LCZero 0.7 1CPU 2439 -70 ½½00½01011000½011½0½ 8.0/20
Network 227 = 5501.53
1 The Baron 3.42 x64 1CPU 2669 +240 11111½11½10½111½1011 16.0/20
2 LCZero 0.7 1CPU 2429 -240 00000½00½01½000½0100 4.0/20
Network 227 = 5501.53
1 Counter 2.6 x64 1CPU 2435 +145 +58/=29/-17 69.71% 72.5/104
2 LCZero 0.7 1CPU 2290 -145 +17/=29/-58 30.29% 31.5/104
Network 227 = 5501.53
1 NanoSzachy 4.1 x64 2357 +165 +30/=15/-7 72.12% 37.5/52
2 LCZero 0.7 1CPU 2192 -165 +7/=15/-30 27.88% 14.5/52
Network 227 = 5501.53 (the other 52 games are included)
1 NanoSzachy 4.1 x64 2356 +169 +62/=27/-15 72.60% 75.5/104
2 LCZero 0.7 1CPU 2188 -169 +15/=27/-62 27.40% 28.5/104
Network 246 = 5599.02 (+100 and ~+50 Elo against other engines?)
1 NanoSzachy 4.1 x64 2356 +125 ½01100111½11½0101110111½1½ 17.5/26
2 LCZero 0.8 1CPU 2231 -125 ½10011000½00½1010001000½0½ 8.5/26
Network 253 = 5641.391; nps: 213 in startposition
The Baron 3.42 x64 2669 111½½001½1½0½00100½11½½½0½ 13.0/26 169.00
2 lczero 0.8 4CPU 2669! 000½½110½0½1½11011½00½½½1½ 13.0/26 169.00
PC Benchmarks: t=1 Startposition depth 20 CPU Version 31 nps (before I had 87)
Network 227 = 5501.53 (I did not await such a jump from 2319 before)
1 Djinn 1.021 x64 2509 +70 ½½11½10100111½100½1½ 12.0/20
2 LCZero 0.7 1CPU 2439 -70 ½½00½01011000½011½0½ 8.0/20
Network 227 = 5501.53
1 The Baron 3.42 x64 1CPU 2669 +240 11111½11½10½111½1011 16.0/20
2 LCZero 0.7 1CPU 2429 -240 00000½00½01½000½0100 4.0/20
Network 227 = 5501.53
1 Counter 2.6 x64 1CPU 2435 +145 +58/=29/-17 69.71% 72.5/104
2 LCZero 0.7 1CPU 2290 -145 +17/=29/-58 30.29% 31.5/104
Network 227 = 5501.53
1 NanoSzachy 4.1 x64 2357 +165 +30/=15/-7 72.12% 37.5/52
2 LCZero 0.7 1CPU 2192 -165 +7/=15/-30 27.88% 14.5/52
Network 227 = 5501.53 (the other 52 games are included)
1 NanoSzachy 4.1 x64 2356 +169 +62/=27/-15 72.60% 75.5/104
2 LCZero 0.7 1CPU 2188 -169 +15/=27/-62 27.40% 28.5/104
Network 246 = 5599.02 (+100 and ~+50 Elo against other engines?)
1 NanoSzachy 4.1 x64 2356 +125 ½01100111½11½0101110111½1½ 17.5/26
2 LCZero 0.8 1CPU 2231 -125 ½10011000½00½1010001000½0½ 8.5/26
Network 253 = 5641.391; nps: 213 in startposition
The Baron 3.42 x64 2669 111½½001½1½0½00100½11½½½0½ 13.0/26 169.00
2 lczero 0.8 4CPU 2669! 000½½110½0½1½11011½00½½½1½ 13.0/26 169.00
Re: LCZero Testmatch
Now testing new Network 15x192! CEGT Conditions 40/20
LCZero 0.9 avx
PC Benchmarks: t=1 Startposition depth 20 CPU Version 66 nps (before I had 31)
Network 263 = 5609.13
1 The Baron 3.42 x64 1CPU 2669 +125 0½½01½111½½½1½101100111111 17.5/26
2 lczero v0.9 1CPU avx 2544 -125 1½½10½000½½½0½010011000000 8.5/26
Network 270 = 5563.32 something is going terrible wrong at the moment!
1 The Baron 3.42 x64 1CPU 2669 +323 11011111110111½11111110111 22.5/26
2 lczero v0.9 avx 1CPU 2346 -323 00100000001000½00000001000 3.5/26
Network 285 = 5462
1 The Baron 3.42 x64 1CPU +354 10111111111111111110111110 23.0/26
2 LCZero2 0.10avx 1CPU -354 01000000000000000001000001 3.0/26
Network 270 = 5563
1 The Baron 3.42 x64 1CPU +229 ½1½111½101½1111½0111½1111½ 20.5/26
2 LCZero3 0.10avx 1CPU -229 ½0½000½010½0000½1000½0000½ 5.5/26
Network 263 = 5609
1 The Baron 3.42 x64 1CPU +125 01½½1½½11½0½½½1111011110½1 17.5/26
2 LCZero4 0.10avx 1CPU -125 10½½0½½00½1½½½0000100001½0 8.5/26
Djinn 1.021 x64 2200 - LCZero 0.10avx303 1CPU 2200 13.5 - 12.5 +9/=9/-8 51.92%
Djinn 1.021 x64 2200 - Lczero2 0.10avx253 1CPU 2200 21.0 - 5.0 +17/=8/-1 80.77%
104 games with weight 303 - 5710
1 Djinn 1.021 x64 2510 +78 +49/=29/-26 61.06% 63.5/104
2 LCZero 0.10avx303 1CPU 2432 -78 +26/=29/-49 38.94% 40.5/104
104 games with weight 331 - 5900
1 Djinn 1.021 x64 2510 +26 +39/=34/-31 53.85% 56.0/104
2 LCZero 0.10avx331 1CPU 2484 -26 +31/=34/-39 46.15% 48.0/104
104 games with weight 349 - 5901
1 GreKo 2018.02 x64 2507 +23 +43/=25/-36 53.37% 55.5/104
2 LCZero 0.10avx349 1CPU 2484 -23 +36/=25/-43 46.63% 48.5/104
104 games with weight 349 - 5901
1 LCZero 0.10avx349 1CPU 2487 +23 +40/=31/-33 53.37% 55.5/104
2 Nebula 2.0 x64 1CPU 2464 -23 +33/=31/-40 46.63% 48.5/104
104 games with weight 431 - 5906
1 DeepGandalf 7 x64 1CPU 2464 +64 +45/=33/-26 59.13% 61.5/104
2 LCZero 0.10avx431 1CPU 2400 -64 +26/=33/-45 40.87% 42.5/104
104 games with weight 526 - 6167
1 Deep Shredder 12 x64 1CPU 2800 +144 +63/=19/-22 69.71% 72.5/104
2 LCZero 0.10avx526 1CPU 2656 -144 +22/=19/-63 30.29% 31.5/104
104 games with weight 526 - 6167 and 4CPUs for LCZero
1 Deep Shredder 12 x64 1CPU 2800 +67 +45/=34/-25 59.62% 62.0/104
2 LCZero 0.10avx 526 4CPU 2733 -67 +25/=34/-45 40.38% 42.0/104
LCZero 0.9 avx
PC Benchmarks: t=1 Startposition depth 20 CPU Version 66 nps (before I had 31)
Network 263 = 5609.13
1 The Baron 3.42 x64 1CPU 2669 +125 0½½01½111½½½1½101100111111 17.5/26
2 lczero v0.9 1CPU avx 2544 -125 1½½10½000½½½0½010011000000 8.5/26
Network 270 = 5563.32 something is going terrible wrong at the moment!
1 The Baron 3.42 x64 1CPU 2669 +323 11011111110111½11111110111 22.5/26
2 lczero v0.9 avx 1CPU 2346 -323 00100000001000½00000001000 3.5/26
Network 285 = 5462
1 The Baron 3.42 x64 1CPU +354 10111111111111111110111110 23.0/26
2 LCZero2 0.10avx 1CPU -354 01000000000000000001000001 3.0/26
Network 270 = 5563
1 The Baron 3.42 x64 1CPU +229 ½1½111½101½1111½0111½1111½ 20.5/26
2 LCZero3 0.10avx 1CPU -229 ½0½000½010½0000½1000½0000½ 5.5/26
Network 263 = 5609
1 The Baron 3.42 x64 1CPU +125 01½½1½½11½0½½½1111011110½1 17.5/26
2 LCZero4 0.10avx 1CPU -125 10½½0½½00½1½½½0000100001½0 8.5/26
Djinn 1.021 x64 2200 - LCZero 0.10avx303 1CPU 2200 13.5 - 12.5 +9/=9/-8 51.92%
Djinn 1.021 x64 2200 - Lczero2 0.10avx253 1CPU 2200 21.0 - 5.0 +17/=8/-1 80.77%
104 games with weight 303 - 5710
1 Djinn 1.021 x64 2510 +78 +49/=29/-26 61.06% 63.5/104
2 LCZero 0.10avx303 1CPU 2432 -78 +26/=29/-49 38.94% 40.5/104
104 games with weight 331 - 5900
1 Djinn 1.021 x64 2510 +26 +39/=34/-31 53.85% 56.0/104
2 LCZero 0.10avx331 1CPU 2484 -26 +31/=34/-39 46.15% 48.0/104
104 games with weight 349 - 5901
1 GreKo 2018.02 x64 2507 +23 +43/=25/-36 53.37% 55.5/104
2 LCZero 0.10avx349 1CPU 2484 -23 +36/=25/-43 46.63% 48.5/104
104 games with weight 349 - 5901
1 LCZero 0.10avx349 1CPU 2487 +23 +40/=31/-33 53.37% 55.5/104
2 Nebula 2.0 x64 1CPU 2464 -23 +33/=31/-40 46.63% 48.5/104
104 games with weight 431 - 5906
1 DeepGandalf 7 x64 1CPU 2464 +64 +45/=33/-26 59.13% 61.5/104
2 LCZero 0.10avx431 1CPU 2400 -64 +26/=33/-45 40.87% 42.5/104
104 games with weight 526 - 6167
1 Deep Shredder 12 x64 1CPU 2800 +144 +63/=19/-22 69.71% 72.5/104
2 LCZero 0.10avx526 1CPU 2656 -144 +22/=19/-63 30.29% 31.5/104
104 games with weight 526 - 6167 and 4CPUs for LCZero
1 Deep Shredder 12 x64 1CPU 2800 +67 +45/=34/-25 59.62% 62.0/104
2 LCZero 0.10avx 526 4CPU 2733 -67 +25/=34/-45 40.38% 42.0/104
LCZero testmatches with longer time controls
1 Deep Shredder 12 x64 1CPU +272 111½1½111111½½01½111½½1111 21.5/26
2 LC0 0.19.1 w31918 4CPU -272 000½0½000000½½10½000½½0000 4.5/26
and now the surprise, same openings but longer time oontrol and only 1CPU:
40 Züge in 40 min 2018 weights_run2_31969.pb.gz; 9141
1 Deep Shredder 12 x64 1CPU +82 0½11½1½011½½½011½1½½½11100 16.0/26
2 LC0 0.19.1 1CPU -82 1½00½0½100½½½100½0½½½00011 10.0/26 = 2718
seems 4CPU do still not work correct and endgames are Long....
40 Züge in 40 min 2018 weights_32247_9999.pb.gz; 9999
1 Lc0 0.20.0-rc2 1CPU +110 1111½1½½½10½1½½0½½½11½½½½1 17.0/26 = 2910
2 Deep Shredder 12 x64 1CPU -110 0000½0½½½01½0½½1½½½00½½½½0 9.0/26
this is a jump with about +200 points from Networks with 9000 points to networks with 10000 points! (on longer time controls).
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU 2992 +157 0½1½11½011½½1½11111½110½1½ 18.5/26
2 LC0 0.20.1 32494-10810 1CPU 2835 -157 1½0½00½100½½0½00000½001½0½ 7.5/26 not the awaited result!
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU 2992 ½½1½½10½100½½½½10½½½½½½01½ 13.0/26 169.00
2 Lc0 0.20.1 11258-96x8-se 1CPU 2992 ½½0½½01½011½½½½01½½½½½½10½ 13.0/26 169.00
this distilled network is very strong! (https://github.com/dkappe/leela-chess-weights/wiki/Distilled-Networks)
40 Züge in 10 min 2019
1 RofChade 2.0 x64 1CPU +70 01½½1½½0½1½½½1½½½101½1½½101½½1½11½0 21.0/35
2 Lc0 0.20.1a 11258-112x9 1CPU -70 10½½0½½1½0½½½0½½½010½0½½010½½0½00½1 14.0/35
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU +40 ½½½11½0½0½10½11101½10½½1½½0½½½01½½1 19.5/35
2 Lc0 0.20.1a 11258-112x9 1CPU -40 ½½½00½1½1½01½00010½01½½0½½1½½½10½½0 15.5/35
I am not longer sure that longer time controls give better results….
40 Züge in 40 min 2019
1 Lc0 0.20.1b 11258-112x9 1CPU +10 0½½½½01½0111½1½½0101½1½½½½1½0½000½1 18.0/35
2 Arasan 21.2 x64 1CPU -10 1½½½½10½1000½0½½1010½0½½½½0½1½111½0 17.0/35
result not ok - too less hash used
2 LC0 0.19.1 w31918 4CPU -272 000½0½000000½½10½000½½0000 4.5/26
and now the surprise, same openings but longer time oontrol and only 1CPU:
40 Züge in 40 min 2018 weights_run2_31969.pb.gz; 9141
1 Deep Shredder 12 x64 1CPU +82 0½11½1½011½½½011½1½½½11100 16.0/26
2 LC0 0.19.1 1CPU -82 1½00½0½100½½½100½0½½½00011 10.0/26 = 2718
seems 4CPU do still not work correct and endgames are Long....
40 Züge in 40 min 2018 weights_32247_9999.pb.gz; 9999
1 Lc0 0.20.0-rc2 1CPU +110 1111½1½½½10½1½½0½½½11½½½½1 17.0/26 = 2910
2 Deep Shredder 12 x64 1CPU -110 0000½0½½½01½0½½1½½½00½½½½0 9.0/26
this is a jump with about +200 points from Networks with 9000 points to networks with 10000 points! (on longer time controls).
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU 2992 +157 0½1½11½011½½1½11111½110½1½ 18.5/26
2 LC0 0.20.1 32494-10810 1CPU 2835 -157 1½0½00½100½½0½00000½001½0½ 7.5/26 not the awaited result!
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU 2992 ½½1½½10½100½½½½10½½½½½½01½ 13.0/26 169.00
2 Lc0 0.20.1 11258-96x8-se 1CPU 2992 ½½0½½01½011½½½½01½½½½½½10½ 13.0/26 169.00
this distilled network is very strong! (https://github.com/dkappe/leela-chess-weights/wiki/Distilled-Networks)
40 Züge in 10 min 2019
1 RofChade 2.0 x64 1CPU +70 01½½1½½0½1½½½1½½½101½1½½101½½1½11½0 21.0/35
2 Lc0 0.20.1a 11258-112x9 1CPU -70 10½½0½½1½0½½½0½½½010½0½½010½½0½00½1 14.0/35
40 Züge in 40 min 2019
1 RofChade 2.0 x64 1CPU +40 ½½½11½0½0½10½11101½10½½1½½0½½½01½½1 19.5/35
2 Lc0 0.20.1a 11258-112x9 1CPU -40 ½½½00½1½1½01½00010½01½½0½½1½½½10½½0 15.5/35
I am not longer sure that longer time controls give better results….
40 Züge in 40 min 2019
1 Lc0 0.20.1b 11258-112x9 1CPU +10 0½½½½01½0111½1½½0101½1½½½½1½0½000½1 18.0/35
2 Arasan 21.2 x64 1CPU -10 1½½½½10½1000½0½½1010½0½½½½0½1½111½0 17.0/35
result not ok - too less hash used
Ähnliche Themen
» Coordination LCZero 0.21.2 (42668)
» Testing LCZero
» testing LCZero 0.10 (462) x64
» testing LCZero v0.20.2 (32930)
» Tests with LCZero 0.24.1 with t40-1541
» Testing LCZero
» testing LCZero 0.10 (462) x64
» testing LCZero v0.20.2 (32930)
» Tests with LCZero 0.24.1 with t40-1541
Seite 1 von 1
Befugnisse in diesem Forum
Sie können in diesem Forum nicht antworten
|
|