OpenBench

OpenBench Testing Framework

Active : 1 Machines / 32 Threads / 22.58 MNPS
Priority 0
Rosent	Winter	net_311l *	diff	8.0+0.08	LLR: 1.11 (-2.94, 2.94) [0.00, 5.00] Games: 8876 W: 2146 L: 2056 D: 4674 Ptnml(0-2): 177, 1027, 1974, 1049, 211	Final net with less CE loss component.
Rosent	Winter	net_311d *	diff	8.0+0.08	LLR: -2.18 (-2.94, 2.94) [0.00, 5.00] Games: 19146 W: 4748 L: 4757 D: 9641 Ptnml(0-2): 450, 2333, 3992, 2372, 426	Reduced the weighting of the draw prediction loss component.
Priority -1
Rosent	Winter	net_311m *	diff	8.0+0.08	LLR: -0.71 (-2.94, 2.94) [-2.50, 2.50] Games: 3340 W: 824 L: 857 D: 1659 Ptnml(0-2): 86, 426, 674, 403, 81	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: -1.17 (-2.94, 2.94) [-3.00, 2.00] Games: 2048 W: 480 L: 535 D: 1033 Ptnml(0-2): 57, 252, 448, 223, 44	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.

Finished
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.
Rosent	Winter	net_test *	diff	40.0+0.40	LLR: 1.77 (-2.94, 2.94) [0.00, 5.00] Games: 4820 W: 1009 L: 922 D: 2889 Ptnml(0-2): 42, 513, 1225, 576, 54	Net trained with some extra data I had laying around and not yet utilized.
Vshche	Igel	ttc2 *	diff	10.0+0.10	LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Games: 16216 W: 3056 L: 2936 D: 10224 Ptnml(0-2): 220, 1683, 4185, 1797, 223	3.6.10: fix cache entry
Vshche	Igel	nn-epoch537	diff	10.0+0.10	LLR: -1.02 (-2.94, 2.94) [0.00, 3.00] Games: 5340 W: 1383 L: 1436 D: 2521 Ptnml(0-2): 46, 669, 1292, 618, 45
Vshche	Igel	nn-epoch568	diff	10.0+0.10	LLR: -1.21 (-2.94, 2.94) [0.00, 3.00] Games: 7160 W: 1892 L: 1953 D: 3315 Ptnml(0-2): 54, 917, 1722, 810, 77
Vshche	Igel	nn-epoch518	diff	10.0+0.10	LLR: -2.95 (-2.94, 2.94) [0.00, 3.00] Games: 14124 W: 3616 L: 3772 D: 6736 Ptnml(0-2): 117, 1791, 3404, 1631, 119
Vshche	Igel	nn-epoch462	diff	10.0+0.10	LLR: -1.65 (-2.94, 2.94) [0.00, 3.00] Games: 5138 W: 1290 L: 1387 D: 2461 Ptnml(0-2): 59, 665, 1215, 574, 56
Vshche	Igel	nn-epoch467	diff	10.0+0.10	LLR: -1.10 (-2.94, 2.94) [0.00, 3.00] Games: 3382 W: 825 L: 889 D: 1668 Ptnml(0-2): 32, 441, 810, 375, 33
Vshche	Igel	nn-epoch554	diff	10.0+0.10	LLR: -1.18 (-2.94, 2.94) [0.00, 3.00] Games: 5018 W: 1267 L: 1333 D: 2418 Ptnml(0-2): 51, 644, 1190, 568, 56
Vshche	Igel	nn-epoch535	diff	10.0+0.10	LLR: -1.27 (-2.94, 2.94) [0.00, 3.00] Games: 2194 W: 533 L: 613 D: 1048 Ptnml(0-2): 24, 311, 505, 235, 22
Rosent	Winter	net_test *	diff	8.0+0.08	LLR: 2.95 (-2.94, 2.94) [0.00, 5.00] Games: 4334 W: 1208 L: 1050 D: 2076 Ptnml(0-2): 92, 482, 903, 556, 134	Net trained with some extra data I had laying around and not yet utilized.
Rosent	Winter	net_test *	diff	40.0+0.40	LLR: 2.17 (-2.94, 2.94) [0.00, 5.00] Games: 8822 W: 1791 L: 1673 D: 5358 Ptnml(0-2): 80, 938, 2276, 1018, 99	Confirmed 2 year old net reproduced and slightly improved
Vshche	Igel	htypo	diff	10.0+0.10	LLR: 0.57 (-2.94, 2.94) [-3.00, 1.00] Games: 2096 W: 558 L: 535 D: 1003 Ptnml(0-2): 13, 229, 544, 246, 16	3.6.10: fix history typo

1 2 3 1329 1330 1331