| Finished | ||||||
|---|---|---|---|---|---|---|
| Peregr | Reckless | lmr_stuff1 | diff | 8.0+0.08 | LLR: 2.93 (-2.25, 2.89) [0.00, 4.00] Games: 79640 W: 19446 L: 19071 D: 41123 Ptnml(0-2): 311, 9521, 19851, 9756, 381 | |
| World | Reckless | s1_upper_lr_bound_increase | diff | 8.0+0.08 | LLR: 3.08 (-2.25, 2.89) [0.00, 4.00] Games: 11404 W: 2986 L: 2808 D: 5610 Ptnml(0-2): 60, 1291, 2824, 1465, 62 | Increase S1 training LR Upper bound to initial_lr: 0.002 (up from 0.0015) |
| World | Reckless | fix-more-history-updates | diff | 8.0+0.08 | LLR: 3.08 (-2.25, 2.89) [-4.00, 0.00] Games: 11382 W: 2780 L: 2675 D: 5927 Ptnml(0-2): 40, 1307, 2915, 1366, 63 | as it turns out, we had another case where the history value got beyond the limit |
| World | Reckless | rfp-tt-pv | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 18674 W: 4586 L: 4396 D: 9692 Ptnml(0-2): 68, 2200, 4644, 2324, 101 | |
| World | Reckless | remove-null-move-history | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [-4.00, 0.00] Games: 15310 W: 3737 L: 3650 D: 7923 Ptnml(0-2): 61, 1847, 3771, 1896, 80 | |
| World | Reckless | fix-factorizer-update | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [-4.00, 0.00] Games: 84500 W: 20323 L: 20446 D: 43731 Ptnml(0-2): 377, 10309, 20963, 10262, 339 | |
| World | Reckless | refactoring-2 | diff | 8.0+0.08 | LLR: 2.94 (-2.25, 2.89) [-4.00, 0.00] Games: 19970 W: 4816 L: 4748 D: 10406 Ptnml(0-2): 72, 2031, 5711, 2099, 72 | cleanups |
| Styxdo | Reckless | styx_gut_feel_experiment | diff | 8.0+0.08 | LLR: 2.97 (-2.25, 2.89) [0.00, 4.00] Games: 11604 W: 2974 L: 2797 D: 5833 Ptnml(0-2): 38, 1417, 2791, 1442, 114 | STC Test of it |
| Styxdo | Reckless | styx_gut_feel_experiment | diff | N=25000 | LLR: 3.19 (-2.25, 2.89) [0.00, 4.00] Games: 4900 W: 1713 L: 1495 D: 1692 Ptnml(0-2): 140, 511, 1006, 577, 216 | Various changes, most notably, increased WDL in both S1 and S2, more epochs, slightly altered LR bounds. |
| World | Reckless | main | diff | 40.0+0.40 | Elo: 18.04 +- 3.42 (95%) [N=10000] Games: 10006 W: 2696 L: 2177 D: 5133 Ptnml(0-2): 7, 971, 2550, 1446, 29 | LTC PT |
| Styxdo | Reckless | v18-bf93ebe8 | diff | N=25000 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 54310 W: 18004 L: 17601 D: 18705 Ptnml(0-2): 1849, 5981, 11178, 6212, 1935 | Same training parameters except filtering logic to match distribution |
| Peregr | Reckless | pcm_stuff2 | diff | 8.0+0.08 | LLR: 3.00 (-2.25, 2.89) [0.00, 4.00] Games: 53486 W: 12990 L: 12691 D: 27805 Ptnml(0-2): 217, 6379, 13261, 6660, 226 | |
| World | Reckless | v18-bf93ebe8 | diff | 8.0+0.08 | LLR: 3.02 (-2.25, 2.89) [0.00, 4.00] Games: 19226 W: 4873 L: 4673 D: 9680 Ptnml(0-2): 86, 2289, 4700, 2415, 123 | Same training parameters except filtering logic to match distribution |
| World | Reckless | main | diff | 8.0+0.08 | Elo: 18.59 +- 2.61 (95%) [N=20000] Games: 20038 W: 5592 L: 4521 D: 9925 Ptnml(0-2): 97, 2003, 4813, 2944, 162 | STC PT |
| World | Reckless | simplify-window-expansion | diff | 8.0+0.08 | LLR: 2.96 (-2.25, 2.89) [-4.00, 0.00] Games: 8152 W: 2018 L: 1907 D: 4227 Ptnml(0-2): 35, 933, 2037, 1028, 43 | |
| World | Reckless | asp-expansions | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 11962 W: 2987 L: 2824 D: 6151 Ptnml(0-2): 36, 1301, 3154, 1444, 46 | increase aspiration window size if the previous searches expanded a lot |
| World | Reckless | bad-noisy-pruning-2 | diff | 8.0+0.08 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 11082 W: 2751 L: 2582 D: 5749 Ptnml(0-2): 45, 1274, 2749, 1413, 60 | |
| Peregr | Reckless | conthist_bonus3 | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 15670 W: 3829 L: 3650 D: 8191 Ptnml(0-2): 73, 1748, 4013, 1929, 72 | |
| Styxdo | Reckless | l1_768_test | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 8118 W: 2115 L: 1954 D: 4049 Ptnml(0-2): 38, 931, 1971, 1070, 49 | STC test for L1=768 (128 more neurons) |
| Styxdo | Reckless | l1_768_test | diff | N=25000 | LLR: 2.98 (-2.25, 2.89) [0.00, 4.00] Games: 5506 W: 1930 L: 1720 D: 1856 Ptnml(0-2): 170, 580, 1117, 642, 244 | L1=768 identical training parameters |
| World | Reckless | post-lmr-research | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [0.00, 4.00] Games: 21806 W: 5363 L: 5164 D: 11279 Ptnml(0-2): 93, 2531, 5461, 2720, 98 | |
| Peregr | Reckless | trying_to_fix_repetition | diff | 8.0+0.08 | LLR: 2.89 (-2.25, 2.89) [-4.00, 0.00] Games: 15312 W: 3796 L: 3711 D: 7805 Ptnml(0-2): 73, 1760, 3889, 1877, 57 | |
| Peregr | Reckless | viz_stuff2 | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [0.00, 4.00] Games: 27854 W: 6784 L: 6566 D: 14504 Ptnml(0-2): 120, 3290, 6908, 3470, 139 | |
| World | Reckless | 50mr-checkmate | diff | 8.0+0.08 | LLR: 2.89 (-2.25, 2.89) [-4.00, 0.00] Games: 12682 W: 3075 L: 2988 D: 6619 Ptnml(0-2): 62, 1232, 3652, 1347, 48 | |
| Peregr | Reckless | fix_unclamped_eval | diff | 8.0+0.08 | LLR: 2.97 (-2.25, 2.89) [-4.00, 0.00] Games: 23454 W: 5700 L: 5635 D: 12119 Ptnml(0-2): 117, 2795, 5839, 2858, 118 | Fix unclamped eval after correction |