wdl-model-training

Live · 10s
Fixed · #401Active
27,882games / 100,000 target
Elo difference
+0.47± 1.91 at 95% confidence
Progress
27.9%
Wins / losses / draws
6,447 / 6,409 / 15,026

Configuration

shaheryar · 1793420513
SettingDevBase
EngineStockDoryStockDory
Sourcehttps://github.com/TheBlackPlague/StockDoryhttps://github.com/TheBlackPlague/StockDory
Revisioncbbb51f0b480ca061fd00eef1e1f77c4e9a58938cbbb51f0b480ca061fd00eef1e1f77c4e9a58938
Branchwdl-model-trainingwdl-model-training
Bench33112083311208
Network——
OptionsThreads=1 Hash=128Threads=1 Hash=128
Time control60.0+0.6060.0+0.60
Opening bookUHO_Lichess_4852_v1.epd
Upload PGNsCOMPACT
ScalingBASE 1600000 NPS
Syzygy WDLDISABLED
Syzygy ADJ.OPTIONAL
Win ADJ.movecount=3 score=400
Draw ADJ.movenumber=40 movecount=8 score=10

wdl-model-training vs wdl-model-training

Elo   | 0.47 +- 1.91 (95%)
Conf | 60.0+0.60s Threads=1 Hash=128MB
Games | N: 27882 W: 6447 L: 6409 D: 15026
Penta | [49, 2827, 8166, 2835, 64]

Results by contributor, CPU & ISA

Individual machine results

#UserGamesPentaPairsTimeCrash