Finished
KierenHalogenr140diffN=40000Elo: 4.78 +- 2.11 (95%) [N=40000]
Games: 40232 W: 11932 L: 11379 D: 16921
Ptnml(0-2): 715, 4570, 9052, 5005, 774
RosentWinternet_502_24x64 *diffN=40000Elo: 2.86 +- 7.28 (95%) [N=4000]
Games: 4006 W: 1111 L: 1078 D: 1817
Ptnml(0-2): 102, 478, 824, 483, 116
Get an understanding of how far apart the based increased size net is compared to the current version. Fixed nodes in this case as system load would otherwise distort results.
RosentWinternet_502_24x64 *diffN=40000LLR: 2.99 (-2.94, 2.94) [0.00, 5.00]
Games: 2282 W: 745 L: 582 D: 955
Ptnml(0-2): 69, 209, 455, 306, 102
Larger net, hopefully a clear improvement at fixed nodes. Around 16% less Nps.
MhouppStashlmr_less_for_checksdiff8.0+0.08LLR: 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
KierenHalogentt-prefetch-key-afterdiff4.0+0.04LLR: 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%
KierenHalogenr139diff40.0+0.40LLR: 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
KierenHalogenr139diffN=40000Elo: 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
KierenHalogenr139diff8.0+0.08LLR: 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
KierenHalogenr138diff40.0+0.40LLR: 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
KierenHalogenr138diff8.0+0.08LLR: 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
RosentWinternet_311 *diff40.0+0.40LLR: 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.
VshcheIgelttc2diff5.0+0.05LLR: 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
RosentWinternet_311 *diff8.0+0.08LLR: 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.
VshcheIgelttc2 *diff5.0+0.05LLR: 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
VshcheIgelttc2diff10.0+0.10LLR: 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
RosentWinternet_test *diff40.0+0.40LLR: 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.
RosentWinternet_test *diff8.0+0.08LLR: 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.
VshcheIgelttc2 *diff10.0+0.10LLR: 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
RosentWinternet_test *diff8.0+0.08LLR: 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.
RosentWinternet_test *diff8.0+0.08LLR: 3.03 (-2.94, 2.94) [0.00, 5.00]
Games: 27442 W: 6402 L: 6150 D: 14890
Ptnml(0-2): 464, 3213, 6148, 3399, 497
ErenStashremove-lmp-depth-conddiff8.0+0.08LLR: 3.04 (-2.94, 2.94) [-5.00, 0.00]
Games: 10680 W: 2762 L: 2683 D: 5235
Ptnml(0-2): 126, 1273, 2484, 1310, 147
VshcheIgelttcdiff10.0+0.10LLR: 3.02 (-2.94, 2.94) [-3.00, 1.00]
Games: 28482 W: 7374 L: 7278 D: 13830
Ptnml(0-2): 186, 3242, 7305, 3306, 202
VshcheIgelttc *diff10.0+0.10LLR: 2.99 (-2.94, 2.94) [-3.00, 1.00]
Games: 23726 W: 4374 L: 4267 D: 15085
Ptnml(0-2): 265, 2575, 6100, 2634, 289
VshcheIgelv2diff5.0+0.05LLR: 2.97 (-2.94, 2.94) [-3.00, 1.00]
Games: 41460 W: 10791 L: 10719 D: 19950
Ptnml(0-2): 198, 4774, 10726, 4822, 210
MhouppStashnmp_only_cutnodesdiff40.0+0.40LLR: 2.99 (-2.94, 2.94) [0.00, 5.00]
Games: 23144 W: 5600 L: 5401 D: 12143
Ptnml(0-2): 117, 2693, 5762, 2874, 126