Seer

[Gabor Szots]

Gauntlet running for Seer 1.1. Remarks:

1. Quite slow (a factor of about 5-10, depending on opponent), I guess it's because of using NNUE. Typical value on my i5-4690K running at 3.5 GHz is about 400 knps.
2. It displays PV only after it has made its move. I have come across that with other engines as well, maybe it won't display PV's with low depths?
3. Seems much weaker than 3000 Elos. Can't say by how much, only 25 games have been played (TC is 2+1).

[Sylwy]

Gauntlet running for Seer 1.1. Remarks:

1. Quite slow (a factor of about 5-10, depending on opponent), I guess it's because of using NNUE. Typical value on my i5-4690K running at 3.5 GHz is about 400 knps.
2. It displays PV only after it has made its move. I have come across that with other engines as well, maybe it won't display PV's with low depths?
3. Seems much weaker than 3000 Elos. Can't say by how much, only 25 games have been played (TC is 2+1).

Hi, Gabor !
1.-Correct. On my i5-7400 3GHz (Kaby Lake) the speed is the same (around 400 knps). An increase of about 25% over the previous version.
2.-I think it's because of the architecture of this engine. Years ago, Thinker had the same behavior. I may be wrong.
3. After 38 games (TC=4"+2") Seer 1.1_x64_skylake seems to have around 2.850 Elo points. + 100 Elo points compared to the previous version. Tomorrow night I will post my results for both versions (Seer 1.0 x64_skylake has around 2750 Elo points in my test).



An engine with a very interesting play. Is my favourite among all 12 engines having NNUE feature.

[connor_mcmonigle]

Gauntlet running for Seer 1.1. Remarks:

1. Quite slow (a factor of about 5-10, depending on opponent), I guess it's because of using NNUE. Typical value on my i5-4690K running at 3.5 GHz is about 400 knps.
2. It displays PV only after it has made its move. I have come across that with other engines as well, maybe it won't display PV's with low depths?
3. Seems much weaker than 3000 Elos. Can't say by how much, only 25 games have been played (TC is 2+1).

Haha. 3000 elo may have been quite optimistic in that case That estimate came from testing in only an 80 game match at 4/40 against Koivisto 3.0 with a 4 move book (my engine was up a single game at the end. It could be Koivisto underperforms in cyclical time controls). I don't do much testing against other engines as I don't really have the resources, but I get around 600 knps on a single thread on my Ryzen 3600 which might have something to do with it.

[Gabor Szots]

Oh and I forgot to mention a minor issue. After 1. d4 Nf6 2. d5 it took the pawn on d5. Arena log:

2020-11-03 17:08:57,443 Arena 3.5.1
2020-11-03 17:08:57,455
2020-11-03 17:08:57,971**----------New game---2020-11-03 17:08:57,971 K -------------
2020-11-03 17:08:58,111**screen: 1536x864
2020-11-03 17:08:58,111**Monitors: 1
2020-11-03 17:08:58,111**Monitor0: 1536x864
2020-11-03 17:08:58,111**FormMonitor: 0
2020-11-03 17:08:58,111**DesktopRect: 0/0 .. 1536/864
2020-11-03 17:08:58,135**Loading 1
2020-11-03 17:09:00,890**----------New game---2020-11-03 17:09:00,890 K -------------
2020-11-03 17:09:00,915**Loading book: E:\Sakk\Arena2\Books\IM_4mvs.abk
2020-11-03 17:09:02,920*1*---------------------Starting engine 1 Seer 1.1 64-bit----------------------
2020-11-03 17:09:02,920*1*Configured Engine 1 Type: UCI
2020-11-03 17:09:02,920*1*Engine 1 dir: E:\Sakk\UCI-engines\Seer
2020-11-03 17:09:02,920*1*Engine 1 commandline: E:\Sakk\UCI-engines\Seer\Seer_1.1-x64.exe
2020-11-03 17:09:03,041*1*Child Process Prio Adj: PID 7500 conhost.exe
2020-11-03 17:09:03,041*1*Engine 1 ProcessID: 10244
2020-11-03 17:09:03,041*1*Engine 1 Prio:32 ThreadPrio:0
2020-11-03 17:09:03,079-->1:uci
2020-11-03 17:09:03,079<--1:id name Seer 1.1
2020-11-03 17:09:03,079<--1:id author C. McMonigle
2020-11-03 17:09:03,079<--1:option name Clear Hash type button
2020-11-03 17:09:03,079<--1:option name Threads type spin default 1 min 1 max 512
2020-11-03 17:09:03,079<--1:option name Hash type spin default 128 min 1 max 65536
2020-11-03 17:09:03,079<--1:option name Weights type string
2020-11-03 17:09:03,079<--1:uciok
2020-11-03 17:09:03,079-->1:setoption name Hash value 256
2020-11-03 17:09:03,079-->1:setoption name Weights value E:\Sakk\UCI-engines\Seer\save.bin
2020-11-03 17:09:03,081*1*Child Process Prio Adj: PID 7500 conhost.exe
2020-11-03 17:09:03,081-->1:isready
2020-11-03 17:09:03,260<--1:readyok
2020-11-03 17:09:03,320*1*Start calc, move no: 1
2020-11-03 17:09:03,322*1*Main Book Move IM_4mvs.abk: g8f6
2020-11-03 17:09:04,431*1*Start calc, move no: 3
2020-11-03 17:09:04,432-->1:ucinewgame
2020-11-03 17:09:04,432-->1:isready
2020-11-03 17:09:04,467<--1:readyok
2020-11-03 17:09:04,478-->1:position startpos moves d2d4 g8f6 d4d5
2020-11-03 17:09:04,478-->1:go wtime 121375 btime 121000 winc 1000 binc 1000
2020-11-03 17:09:04,480<--1:info depth 1 seldepth 1 multipv 1 score cp 0 nodes 0 nps 0 tbhits 0 time 1 pv
2020-11-03 17:09:09,362<--1:info depth 6 seldepth 6 multipv 1 score cp 0 nodes 6953 nps 316045 tbhits 0 time 21 pv f6d5 d1d5 h7h5 d5h5 h8h5 h2h3
2020-11-03 17:09:09,362<--1:info depth 7 seldepth 7 multipv 1 score cp 0 nodes 42062 nps 362603 tbhits 0 time 115 pv f6d5 d1d5 h7h5 d5h5 h8h5 h2h3 h5h3
2020-11-03 17:09:09,362<--1:bestmove f6d5
2020-11-03 17:09:09,362*1*Found move:Nf6xd5

[connor_mcmonigle]

Oh and I forgot to mention a minor issue. After 1. d4 Nf6 2. d5 it took the pawn on d5. Arena log:

Oh dear... (I misread that initially)

[Rebel]

I get 2700 elo for Seer 1.1, can that be?

Code: Select all

                     The SRL rating list of : Tue Nov  3 08:28:03 2020
    EPD  : epd\lc1.epd
    Time : 1000ms
                                                                     Max            Time   Hash          
    Engine                 Points  Used Time   Found   Pos    Elo   Score   Score    ms     Mb  Cpu  Errors
 1  Stockfish 12           341638  11:34:09.7  25383  40000  3416  400000  85.41%   1000   128    1     0
 2  Ethereal-NNUE          334327  11:37:45.7  24676  40000  3343  400000  83.58%   1000   128    1     0
 3  RubiChess 1.8 NNUE     328244  11:30:21.7  23651  40000  3282  400000  82.06%   1000   128    1     0
 4  Minic 2.51 SF12        327917  11:02:37.3  23628  40000  3279  400000  81.98%   1000   128    1     0
 5  Minic 2.51 NNUE        325905  11:01:15.1  23441  40000  3259  400000  81.48%   1000   128    1     0
 6  Minic 2.50 NNUE        322147  11:06:22.6  22986  40000  3221  400000  80.54%   1000   128    1     0
 7  Nemorino 6.00          319148  10:36:00.7  22853  40000  3191  400000  79.79%   1000   128    1    42
 8  Orion 0.7 NNUE_Player  318886  11:43:55.1  22654  40000  3188  400000  79.72%   1000   128    1     0
 9  Ethereal 12.62         317128  11:37:07.9  22428  40000  3171  400000  79.28%   1000   128    1     0
10  Komodo 14              317110  11:09:21.4  22398  40000  3171  400000  79.28%   1000   128    1     0
11  igel 2.80 NNUE         316831  11:32:02.3  22679  40000  3168  400000  79.21%   1000   128    1     0
12  Minic 2.51 nexus       315288  11:01:57.0  22397  40000  3152  400000  78.82%   1000   128    1     0
13  Houdini 6.03           314596  11:27:54.8  22218  40000  3146  400000  78.65%   1000   128    1     0
14  SlowChess 2.2          313139  10:30:56.4  21860  40000  3131  400000  78.28%   1000   128    1     0
15  Minic 2.51 nutrient    312407  11:02:18.3  21729  40000  3124  400000  78.10%   1000   128    1     0
16  rofChade 2.3           309642  11:24:20.2  21587  40000  3096  400000  77.41%   1000   128    1    41
17  Ethereal 12            309088  11:30:20.9  21840  40000  3090  400000  77.27%   1000   128    1     0
18  Laser 1.7              308178  11:29:30.5  21320  40000  3081  400000  77.04%   1000   128    1     0
19  Schooner 2.2           306808  10:22:01.9  21335  40000  3068  400000  76.70%   1000   128    1     0
20  Xiphos 0.6             306796  10:03:55.9  21333  40000  3068  400000  76.70%   1000   128    1     0
21  Booot 6.4              305082  12:56:19.6  21267  40000  3050  400000  76.27%   1000   128    1   124
22  Defenchess 2.2         303754  10:12:00.7  21208  40000  3037  400000  75.94%   1000   128    1    41
23  Andscacs 0.95          301560  12:10:30.8  20745  40000  3015  400000  75.39%   1005   128    1    41
24  Shredder 13            300619  11:28:47.0  20946  40000  3006  400000  75.15%   1000   128    1     0
25  Wasp 4.00              299925  11:45:50.1  20727  40000  2999  400000  74.98%   1000   128    1     0
26  Senpai 2               299279  11:36:50.5  20615  40000  2992  400000  74.82%   1000   128    1    42
27  Winter 0.9             298713  10:06:38.6  20518  40000  2987  400000  74.68%   1000   128    1     0
28  Arasan 22              298663  11:27:32.7  20460  40000  2986  400000  74.67%   1000   128    1     0
29  ice 4.0                297995  11:49:51.1  20767  40000  2980  400000  74.50%   1000   128    1     0
30  Critter 1.6            297939  11:38:55.1  20654  40000  2979  400000  74.48%   1000   128    1    22
31  Fire 7.1               296996  11:26:35.7  20356  40000  2970  400000  74.25%   1000   128    1     0
32  Vajolet 2.8            296269  11:25:51.6  20327  40000  2962  400000  74.07%   1000   128    1     0
33  Demolito 200514        295686  10:53:58.5  20429  40000  2956  400000  73.92%   1000   128    1     0
34  Gogobello 2.2          293824  11:44:24.1  20296  40000  2938  400000  73.46%   1000   128    1    41
35  Weiss 1.2              293517  11:27:33.1  20047  40000  2935  400000  73.38%   1000   128    1     0
36  Nemorino 5.00          291649  10:05:27.4  19882  40000  2916  400000  72.91%   1000   128    1    41
37  Rodent 4               291647  11:45:03.3  19774  40000  2916  400000  72.91%   1000   128    1     0
38  Winter 0.8             291596  10:02:03.0  20057  40000  2916  400000  72.90%   1000   128    1    41
39  Hannibal 1.7           291446  11:39:04.6  19985  40000  2914  400000  72.86%   1000   128    1     0
40  Combusken 1.2          291389  12:25:31.9  19902  40000  2914  400000  72.85%   1000   128    1    41
41  Texel 1.7              291164  11:27:40.3  20064  40000  2911  400000  72.79%   1000   128    1     0
42  Monolith 2             290807  11:31:27.5  19972  40000  2908  400000  72.70%   1000   128    1     0
43  Topple 0.7.5           290649  12:13:57.0  19696  40000  2906  400000  72.66%   1000   128    1     0
44  Deuterium 2019         290578  11:31:42.7  19819  40000  2905  400000  72.64%   1000   128    1     0
45  Chiron 4               290250  11:46:17.8  19978  40000  2902  400000  72.56%   1000   128    1     0
46  Godel 7.0              290222  12:52:57.9  19758  40000  2902  400000  72.56%   1000   128    1    42
47  Amoeba 3.1             289712  09:40:26.2  19682  40000  2897  400000  72.43%   1000   128    1     0
48  FabChess 1.15          289296  11:50:40.2  19849  40000  2892  400000  72.32%   1000   128    1    41
49  sting-sf-21            288904  11:31:56.3  19905  40000  2889  400000  72.23%   1000   128    1     0
50  Marvin 3.60            288732  10:48:52.8  19848  40000  2887  400000  72.18%   1000   128    1    41
51  Bobcat 8               287527  10:54:11.9  19486  40000  2875  400000  71.88%   1000   128    1     0
52  Weiss 1.1              286949  11:27:27.3  19401  40000  2869  400000  71.74%   1000   128    1     0
53  Invictus r305          285355  10:16:08.6  19227  40000  2853  400000  71.34%   1000   128    1     0
54  Counter 3.5            285137  11:25:20.1  19329  40000  2851  400000  71.28%   1000   128    1     0
55  Weiss 1.0              284693  11:23:14.3  19241  40000  2846  400000  71.17%   1000   128    1     0
56  Asymptote 0.8          284305  12:19:43.9  19245  40000  2843  400000  71.08%   1000   128    1    41
57  Tucano 8.0             280426  04:46:55.0  18777  40000  2804  400000  70.11%   1000   128    1     0
58  RuyDos 1.1.11          278666  10:25:44.5  18567  40000  2786  400000  69.67%   1000   128    1     0
59  Cheese 2.1             277252  11:28:33.3  18763  40000  2772  400000  69.31%   1000   128    1     0
60  GreKo 2020.03          276482  11:29:35.7  18694  40000  2764  400000  69.12%   1000   128    1     0
61  Fruit 2.3              275618  11:30:55.1  18270  40000  2756  400000  68.90%   1000   128    1     0
62  ProDeo 2.2             273793  11:29:46.3  18263  40000  2738  400000  68.45%   1000   128    1     0
63  Benjamin               271801  11:29:55.8  17985  40000  2718  400000  67.95%   1000   128    1     0
64  Fridolin 3.10          271357  11:40:42.9  18030  40000  2713  400000  67.84%   1000   128    1     0
65  Fruit 2.1              270830  11:29:45.7  17982  40000  2708  400000  67.71%   1000   128    1     0
66  Seer 1.1               270072  11:41:04.9  18072  40000  2700  400000  67.52%   1000   128    1     0
67  Devel 3.0.0b           269433  12:22:53.0  17986  40000  2694  400000  67.36%   1000   128    1    65
68  Ruffian 2              265592  11:13:01.7  17740  40000  2656  400000  66.40%   1000   128    1     0
69  Stash 18.0             253693  11:10:20.4  16848  40000  2536  400000  63.42%   1000   128    1     0
70  CT800 1.40             253449  10:45:20.4  16533  40000  2534  400000  63.36%   1000   128    1     0
71  Ares 005-2             243380  04:42:01.1  15937  40000  2433  400000  60.84%   1000   128    1     0
72  FoxSee 3.3.3           240244  11:08:18.3  15505  40000  2402  400000  60.06%   1000   128    1     0

                                    Created with MEA
                                          by
                                       Ferdinand
                                         Mosca

[connor_mcmonigle]

Oh and I forgot to mention a minor issue. After 1. d4 Nf6 2. d5 it took the pawn on d5. Arena log:

uci id name Seer 1.1
id author C. McMonigle
option name Clear Hash type button
option name Threads type spin default 1 min 1 max 512
option name Hash type spin default 128 min 1 max 65536

option name Weights type string
uciok
setoption name Hash value 256
setoption name Weights value C:\tools\msys64\home\conno\Develop\seer-nnue\train\model\save.bin

isready

readyok
ucinewgame
isready

readyok

position startpos moves d2d4 g8f6 d4d5
go wtime 121375 btime 121000 winc 1000 binc 1000
info depth 1 seldepth 1 multipv 1 score cp 0 nodes 0 nps 0 tbhits 0 time 6 pv
info depth 2 seldepth 2 multipv 1 score cp 99 nodes 202 nps 6312 tbhits 0 time 31 pv c7c6 d5c6 b8c6
info depth 5 seldepth 5 multipv 1 score cp 155 nodes 850 nps 17708 tbhits 0 time 47 pv e7e6 g1f3 f6d5 e2e4 f8b4 c2c3
info depth 6 seldepth 6 multipv 1 score cp 124 nodes 1852 nps 28937 tbhits 0 time 63 pv c7c6 c2c4 d8a5 b1c3 c6d5 c4d5
info depth 8 seldepth 8 multipv 1 score cp 45 nodes 4319 nps 53320 tbhits 0 time 80 pv c7c6 c2c4 c6d5 c4d5 e7e6 b1c3 f8b4 c1d2 e8g8
info depth 10 seldepth 10 multipv 1 score cp 57 nodes 8327 nps 81637 tbhits 0 time 101 pv c7c6 c2c4 e7e5 g1f3 e5e4 f3d2 f8b4 e2e3
info depth 11 seldepth 11 multipv 1 score cp 65 nodes 16504 nps 117885 tbhits 0 time 139 pv c7c6 c2c4 c6d5 c4d5 e7e6 b1c3 f8b4 c1g5 e6d5
info depth 12 seldepth 12 multipv 1 score cp 85 nodes 21940 nps 115473 tbhits 0 time 189 pv c7c6 c2c4 c6d5 c4d5 e7e6 h2h4 e6d5 b1c3 b8c6 g1f3 f8b4
d1d5

info depth 13 seldepth 13 multipv 1 score cp 77 nodes 63628 nps 183365 tbhits 0 time 346 pv c7c6 c2c4 c6d5 c4d5 e7e6 d5e6 f7e6 g1f3 b8c6 a2a3
d7d5 e2e3 f8e7

info depth 14 seldepth 14 multipv 1 score cp 77 nodes 77560 nps 198871 tbhits 0 time 389 pv c7c6 c2c4 c6d5 c4d5 e7e6 e2e4 f6e4 g1f3 e6d5 d1d5 f8b4 b1c3 e4c3 d5e5 b4e7

info depth 15 seldepth 15 multipv 1 score cp 115 nodes 138751 nps 237181 tbhits 0 time 584 pv e7e6 d5e6 f7e6 g1f3 d7d5 c1f4 b8c6 e2e3 c6d4
info depth 16 seldepth 16 multipv 1 score cp 105 nodes 384791 nps 278028 tbhits 0 time 1383 pv c7c6 c2c4 c6d5 c4d5 e7e6 b1c3 d8a5 e2e3 f6d5 d1c2
info depth 17 seldepth 17 multipv 1 score cp 78 nodes 643043 nps 289268 tbhits 0 time 2222 pv c7c6 c2c4 c6d5 c4d5 e7e6 d5e6 f7e6 e2e3 d7d5 b1c3 b8c6 c1d2 f8e7 a2a3 e8g8

info depth 18 seldepth 18 multipv 1 score cp 78 nodes 1074208 nps 293259 tbhits 0 time 3662 pv c7c6 c2c4 c6d5 c4d5 e7e6 d5e6 f7e6 e2e3 d7d5 g1f3 b8c6 f1e2 f8e7 c1d2 e8g8 d2c3 e7d6

info depth 19 seldepth 19 multipv 1 score cp 91 nodes 1333238 nps 292890 tbhits 0 time 4551 pv c7c6 c2c4 c6d5 c4d5 e7e6 d5e6 f7e6 g1f3 b8c6 e2e4 f6e4 b1d2 e4d2 d1d2
bestmove c7c6

The above test was on my laptop.
It could be a non deterministic bug, but when Nxd5 was observed, are you sure the weights were loaded correctly? The fact that the score was all zeros and it only reached depth 7 tells me something was likely wrong with the weights getting loaded.

[Gabor Szots]

It could be a non deterministic bug, but when Nxd5 was observed, are you sure the weights were loaded correctly? The fact that the score was all zeros and it only reached depth 7 tells me something was likely wrong with the weights getting loaded.

Oops. Wrong bin name. I renamed save.bin to save11.bin but did not change the engine parameter. I owe you a beer (and you are not the only one...).

[connor_mcmonigle]

I get 2700 elo for Seer 1.1, can that be?

Thank you for testing! Could you elaborate on that time control a little? Was it 1s per move fixed? In that case, it's possible as I've never really tested at such a time control. Would you know if it was losing on time? It's been a long time since there was any reason to test against Fruit 2.1, but I'll run a short match now.

[connor_mcmonigle]

It could be a non deterministic bug, but when Nxd5 was observed, are you sure the weights were loaded correctly? The fact that the score was all zeros and it only reached depth 7 tells me something was likely wrong with the weights getting loaded.

Oops. Wrong bin name. I renamed save.bin to save11.bin but did not change the engine parameter. I owe you a beer (and you are not the only one...).

No worries Thanks for testing it. I'm just glad it's not an issue on my end. I'm probably going to explore including the weights in the executable next release so that loading the Weights is less of an issue going forwards.