OpenBench

OpenBench Testing Framework

Active : 1 Machines / 32 Threads / 30.73 MNPS
Priority 0
Mhoupp	Stash	lmr_less_for_checks	diff	40.0+0.40	LLR: 0.00 (-2.94, 2.94) [0.00, 5.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0	Decrease LMR if the move gives check
Vshche	Igel	nn-epoch1109	diff	10.0+0.10	LLR: -1.94 (-2.94, 2.94) [0.00, 3.00] Games: 7436 W: 1891 L: 2000 D: 3545 Ptnml(0-2): 67, 972, 1754, 853, 72	3.6.12: fix tb tt bug (#324)

Finished
Mhoupp	Stash	lmr_less_for_checks	diff	8.0+0.08	LLR: 2.98 (-2.94, 2.94) [0.00, 5.00] Games: 23534 W: 5929 L: 5710 D: 11895 Ptnml(0-2): 251, 2814, 5469, 2931, 302	Decrease LMR if the move gives check
Kieren	Halogen	tt-prefetch-key-after	diff	4.0+0.04	LLR: 3.05 (-2.94, 2.94) [0.00, 3.00] Games: 11928 W: 3316 L: 3096 D: 5516 Ptnml(0-2): 100, 1244, 3063, 1450, 107	Prefetch TT entry before apply_move using precomputed key AVX2: +2.10% +/- 0.19%
Kieren	Halogen	[Berserk] main	diff	8.0+0.08	Elo: -31.54 +- 11.66 (95%) [N=10000] Games: 1204 W: 273 L: 382 D: 549 Ptnml(0-2): 38, 154, 292, 115, 3	Update default network to ed164cf2.nn (#890)
Kieren	Halogen	r139	diff	40.0+0.40	LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 8544 W: 2249 L: 2056 D: 4239 Ptnml(0-2): 21, 925, 2183, 1126, 17	768 l1
Kieren	Halogen	r139	diff	N=40000	Elo: 13.84 +- 2.11 (95%) [N=40000] Games: 40006 W: 12341 L: 10748 D: 16917 Ptnml(0-2): 628, 4205, 8968, 5350, 852	768 l1
Kieren	Halogen	r139	diff	8.0+0.08	LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 18422 W: 4918 L: 4682 D: 8822 Ptnml(0-2): 169, 2107, 4417, 2355, 163	768 l1
Kieren	Halogen	r138	diff	40.0+0.40	LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 5116 W: 1401 L: 1215 D: 2500 Ptnml(0-2): 14, 517, 1313, 697, 17
Kieren	Halogen	r138	diff	8.0+0.08	LLR: 2.99 (-2.94, 2.94) [0.00, 3.00] Games: 6316 W: 1749 L: 1542 D: 3025 Ptnml(0-2): 38, 693, 1510, 858, 59
Rosent	Winter	net_311m *	diff	8.0+0.08	LLR: -3.02 (-2.94, 2.94) [-2.50, 2.50] Games: 17246 W: 4156 L: 4292 D: 8798 Ptnml(0-2): 402, 2127, 3657, 2079, 358	Trying to better understand the hybrid loss. Both nets are not fully trained, but are at a similar point in training.
Rosent	Winter	net_311l *	diff	8.0+0.08	LLR: -3.10 (-2.94, 2.94) [-3.00, 2.00] Games: 17742 W: 4218 L: 4374 D: 9150 Ptnml(0-2): 424, 2152, 3826, 2094, 375	Trying to better understand the hybrid loss. Both nets are not fully trained, but are at a similar point in training. 311n removes the CE loss component completely. Even if worth Elo, we may not want this.
Rosent	Winter	net_311l *	diff	8.0+0.08	LLR: -2.97 (-2.94, 2.94) [0.00, 5.00] Games: 23074 W: 5479 L: 5505 D: 12090 Ptnml(0-2): 487, 2821, 4936, 2817, 476	Final net with less CE loss component.
Rosent	Winter	net_311d *	diff	8.0+0.08	LLR: -2.95 (-2.94, 2.94) [0.00, 5.00] Games: 20226 W: 5005 L: 5044 D: 10177 Ptnml(0-2): 475, 2478, 4222, 2487, 451	Reduced the weighting of the draw prediction loss component.
Mhoupp	Stash	se_negext_pv	diff	8.0+0.08	LLR: -2.98 (-2.94, 2.94) [0.00, 5.00] Games: 8150 W: 1970 L: 2057 D: 4123 Ptnml(0-2): 114, 1000, 1922, 937, 102	Increase Negative Singular Extensions by one ply for PV nodes Bench: 4,382,866
Kieren	Halogen	r137	diff	8.0+0.08	LLR: -2.99 (-2.94, 2.94) [0.00, 3.00] Games: 4072 W: 992 L: 1179 D: 1901 Ptnml(0-2): 63, 541, 978, 428, 26	check if non-Syzygy data does better with access to Syzygy than without
Kieren	Halogen	r137	diff	8.0+0.08	LLR: -2.95 (-2.94, 2.94) [0.00, 3.00] Games: 4496 W: 1140 L: 1323 D: 2033 Ptnml(0-2): 65, 598, 1070, 485, 30	9.3B new data
Rosent	Winter	net_311d *	diff	8.0+0.08	LLR: -2.95 (-2.94, 2.94) [0.00, 5.00] Games: 11346 W: 2730 L: 2809 D: 5807 Ptnml(0-2): 236, 1434, 2411, 1357, 235	Draw calibration handled with MSE loss directly on the draw probability should be less sensitive to outliers that are common in the high entropy STC time controls the training data stems from.
Rosent	Winter	net_311 *	diff	40.0+0.40	LLR: 2.96 (-2.94, 2.94) [0.00, 5.00] Games: 3948 W: 860 L: 731 D: 2357 Ptnml(0-2): 32, 395, 1004, 498, 45	Fully trained model with identical hyperparameters to prior gen, but extra data. This should clearly beat the master branch.
Vshche	Igel	ttc2 *	diff	60.0+0.60	LLR: 1.88 (-2.94, 2.94) [-3.00, 1.00] Games: 25814 W: 3241 L: 3202 D: 19371 Ptnml(0-2): 80, 2105, 8522, 2096, 104	3.6.10: fix cache entry
Vshche	Igel	ttc2	diff	60.0+0.60	LLR: 0.39 (-2.94, 2.94) [-3.00, 1.00] Games: 2680 W: 678 L: 665 D: 1337 Ptnml(0-2): 8, 289, 738, 292, 13	3.6.10: fix cache entry
Vshche	Igel	ttc2	diff	5.0+0.05	LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Games: 9688 W: 2554 L: 2436 D: 4698 Ptnml(0-2): 41, 1061, 2524, 1175, 43	3.6.10: fix cache entry
Rosent	Winter	net_311 *	diff	8.0+0.08	LLR: 2.96 (-2.94, 2.94) [0.00, 5.00] Games: 8158 W: 2101 L: 1925 D: 4132 Ptnml(0-2): 193, 922, 1694, 1056, 214	Testing net with same hyperparameters but extra self play data a bit prematurely to get a sense of where things lie.
Vshche	Igel	ttc2 *	diff	5.0+0.05	LLR: 2.97 (-2.94, 2.94) [-3.00, 1.00] Games: 10058 W: 1610 L: 1497 D: 6951 Ptnml(0-2): 53, 936, 2964, 997, 79	3.6.10: fix cache entry
Vshche	Igel	ttc2	diff	10.0+0.10	LLR: 3.00 (-2.94, 2.94) [-3.00, 1.00] Games: 54722 W: 14226 L: 14171 D: 26325 Ptnml(0-2): 407, 6133, 14232, 6176, 413	3.6.10: fix cache entry
Rosent	Winter	net_test *	diff	40.0+0.40	LLR: 2.95 (-2.94, 2.94) [0.00, 5.00] Games: 3618 W: 807 L: 675 D: 2136 Ptnml(0-2): 37, 366, 880, 480, 46	Trained with new data. The new training data has a very different distribution and has neutral effect on validation metrics.
Rosent	Winter	net_test *	diff	8.0+0.08	LLR: 2.97 (-2.94, 2.94) [-2.00, 3.00] Games: 7204 W: 1851 L: 1710 D: 3643 Ptnml(0-2): 160, 820, 1495, 973, 154	Trained with new data. The new training data has a very different distribution and has neutral effect on validation metrics.

1 2 3 1329 1330 1331