| Finished | ||||||
|---|---|---|---|---|---|---|
| World | Reckless | spsa-2-sanity-31k | diff | 8.0+0.08 | LLR: 0.67 (-2.25, 2.89) [0.00, 4.00] Games: 11256 W: 2809 L: 2745 D: 5702 Ptnml(0-2): 50, 1301, 2860, 1369, 48 | spsa values after 31k games at STC |
| World | Reckless | spsa-2-sanity-31k | diff | 40.0+0.40 | LLR: 2.90 (-2.25, 2.89) [0.00, 4.00] Games: 7808 W: 1847 L: 1700 D: 4261 Ptnml(0-2): 5, 858, 2036, 995, 10 | spsa values after 31k games |
| World | Reckless | main | diff | 40.0+0.40 | Tuning 103 Parameters 26985/100000 Iterations 53970/200000 Games Played | Bugged |
| World | Reckless | spsa-2-90k | diff | 8.0+0.08 | LLR: -2.30 (-2.25, 2.89) [0.00, 4.00] Games: 3426 W: 795 L: 891 D: 1740 Ptnml(0-2): 26, 450, 840, 388, 9 | spsa is not bugged at least, but worth testing this in stc also |
| World | Reckless | spsa-2 | diff | N=12500 | Tuning 103 Parameters 11409/25000 Iterations 91274/200000 Games Played | let's see if spsa works, stat with fixed nodes (Pere idea/task) |
| World | Reckless | spsa-2-90k | diff | N=12500 | LLR: 4.37 (-2.25, 2.89) [0.00, 4.00] Games: 1780 W: 784 L: 480 D: 516 Ptnml(0-2): 39, 134, 343, 232, 142 | |
| World | Reckless | nmp-eval-beta | diff | 8.0+0.08 | LLR: -1.16 (-2.25, 2.89) [0.00, 4.00] Games: 10936 W: 2681 L: 2701 D: 5554 Ptnml(0-2): 40, 1333, 2759, 1279, 57 | |
| World | Reckless | qs-failfirm | diff | 8.0+0.08 | LLR: -1.20 (-2.25, 2.89) [0.00, 4.00] Games: 6298 W: 1559 L: 1595 D: 3144 Ptnml(0-2): 35, 772, 1565, 748, 29 | fail high adjustment interpolation |
| World | Reckless | probcut-static-eval-beta | diff | 8.0+0.08 | LLR: -1.91 (-2.25, 2.89) [0.00, 4.00] Games: 6314 W: 1479 L: 1548 D: 3287 Ptnml(0-2): 32, 804, 1547, 749, 25 | |
| World | Reckless | lmr-tt-noisy-2 | diff | 8.0+0.08 | LLR: -1.35 (-2.25, 2.89) [0.00, 4.00] Games: 25268 W: 6261 L: 6246 D: 12761 Ptnml(0-2): 131, 3034, 6276, 3075, 118 | |
| World | Reckless | nnue-1536 | diff | 8.0+0.08 | Elo: 6.13 +- 3.49 (95%) [N=40000] Games: 10826 W: 2789 L: 2598 D: 5439 Ptnml(0-2): 44, 1248, 2663, 1389, 69 | old big net |
| World | Reckless | qs-ub-move | diff | 8.0+0.08 | LLR: -2.32 (-2.25, 2.89) [0.00, 4.00] Games: 9820 W: 2364 L: 2440 D: 5016 Ptnml(0-2): 42, 1219, 2459, 1153, 37 | |
| World | Reckless | fpn-5 | diff | 8.0+0.08 | LLR: -2.28 (-2.25, 2.89) [0.00, 4.00] Games: 5312 W: 1266 L: 1356 D: 2690 Ptnml(0-2): 28, 700, 1287, 616, 25 | |
| World | Reckless | [Viridithas] master | diff | 40.0+0.40 | Elo: -26.99 +- 3.26 (95%) [N=40000] Games: 11518 W: 2317 L: 3210 D: 5991 Ptnml(0-2): 25, 1901, 2816, 976, 41 | [LTC] Reckless vs. Viridithas |
| World | Reckless | [Viridithas] master | diff | 8.0+0.08 | Elo: -19.48 +- 2.82 (95%) [N=40000] Games: 18322 W: 4150 L: 5176 D: 8996 Ptnml(0-2): 135, 2846, 4263, 1744, 173 | [STC] Reckless vs. Viridithas |
| World | Reckless | reductions-before-pruning-again | diff | 8.0+0.08 | LLR: -2.41 (-2.25, 2.89) [0.00, 4.00] Games: 10390 W: 2521 L: 2599 D: 5270 Ptnml(0-2): 44, 1280, 2622, 1208, 41 | |
| World | Reckless | reductions-before-pruning-again-2 | diff | 8.0+0.08 | LLR: -2.37 (-2.25, 2.89) [0.00, 4.00] Games: 14876 W: 3632 L: 3696 D: 7548 Ptnml(0-2): 72, 1852, 3654, 1788, 72 | |
| World | Reckless | guard-qs-tt-cutoff | diff | 8.0+0.08 | LLR: -2.41 (-2.25, 2.89) [0.00, 4.00] Games: 8660 W: 2076 L: 2162 D: 4422 Ptnml(0-2): 41, 1120, 2106, 1010, 53 | |
| World | Reckless | history-above-beta | diff | 8.0+0.08 | LLR: -2.90 (-2.25, 2.89) [0.00, 4.00] Games: 8092 W: 1969 L: 2077 D: 4046 Ptnml(0-2): 56, 980, 2050, 936, 24 | |
| World | Reckless | conthist-3 | diff | 8.0+0.08 | LLR: -2.93 (-2.25, 2.89) [0.00, 4.00] Games: 10952 W: 2608 L: 2710 D: 5634 Ptnml(0-2): 51, 1419, 2619, 1355, 32 | |
| World | Reckless | s1_upper_lr_bound_increase | diff | 40.0+0.40 | LLR: -2.28 (-2.25, 2.89) [0.00, 4.00] Games: 26622 W: 6109 L: 6131 D: 14382 Ptnml(0-2): 37, 3075, 7095, 3081, 23 | Increase S1 training LR Upper bound to initial_lr: 0.002 (up from 0.0015) |
| World | Reckless | pere-patch | diff | 8.0+0.08 | LLR: -2.27 (-2.25, 2.89) [0.00, 4.00] Games: 11644 W: 2793 L: 2862 D: 5989 Ptnml(0-2): 62, 1423, 2918, 1360, 59 | |
| 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 | s1_upper_lr_bound_increase | diff | N=25000 | LLR: -2.26 (-2.25, 2.89) [0.00, 4.00] Games: 5856 W: 1823 L: 1936 D: 2097 Ptnml(0-2): 189, 725, 1197, 644, 173 | 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 |