| Active : 40 Machines / 80 Threads / 2.66 MNPS | ||||||
|---|---|---|---|---|---|---|
| Priority 0 | ||||||
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 1800.0+3.00 | LLR: 0.20 (-2.94, 2.94) [0.00, 3.00] Games: 2120 W: 517 L: 504 D: 1099 Ptnml(0-2): 0, 169, 709, 182, 0 | Calibration Elo test for LCZeroCPU on TCEC. (100 Elo) |
| Priority -5 | ||||||
| Menkib | Leela-dag-preview | tcec-tune-with-blocking-cuda * | diff | 40.0+0.40 | Tuning 12 Parameters 54460/100000 Iterations 217840/400000 Games Played | |
| Finished | ||||||
| Kovax | Leela-dag-preview | debl1M-k2hyb-100k | diff | 10.0+0.10 | LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 9740 W: 2267 L: 2088 D: 5385 Ptnml(0-2): 0, 971, 2753, 1142, 4 | k2hyb recheck, as this net played vs 100k instead of 1M |
| Menkib | Leela-dag-preview | tcec-season-30-swiss | diff | 1800.0+3.00 | LLR: -2.95 (-2.94, 2.94) [0.00, 3.00] Games: 5404 W: 1275 L: 1406 D: 2723 Ptnml(0-2): 1, 519, 1792, 390, 0 | Calibration Elo test for LCZeroCPU on TCEC. (200 Elo) |
| Kovax | Leela-dag-preview | policy-blend | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 8412 W: 1970 L: 1798 D: 4644 Ptnml(0-2): 1, 775, 2483, 945, 2 | Optimistic blend vs Master post softmax. |
| Kovax | Leela-dag-preview | policy-blend | diff | 10.0+0.10 | Tuning 6 Parameters 3612/12500 Iterations 57794/200000 Games Played | Tune policy blending on T1 sharp net. |
| Kovax | Leela-dag-preview | master | diff | N=1000 | Elo: 11.91 +- 1.76 (95%) [N=40000] Games: 40014 W: 10593 L: 9222 D: 20199 Ptnml(0-2): 181, 3889, 10566, 5120, 251 | check how much PST and FPU is shift alone gains with the sharp target corpus. |
| Kovax | Leela-dag-preview | policy-blend | diff | N=1000 | Elo: 57.21 +- 2.44 (95%) [N=40000] Games: 21086 W: 7049 L: 3608 D: 10429 Ptnml(0-2): 30, 1176, 4936, 4125, 276 | small node count initial check on sharp policy target + policy head blending tune resutls |
| Kovax | Leela-dag-preview | policy-blend | diff | N=1000 | Tuning 6 Parameters 3000/3000 Iterations 192016/192000 Games Played | Policy blend tune on fix nodes |
| Kovax | Leela-dag-preview | master | diff | 10.0+0.10 | Tuning 2 Parameters 1000/1000 Iterations 16000/16000 Games Played | cleanvisit2 corpus less sharp than previous |
| Menkib | Leela-dag-preview | t3d-kd2-03007500.pb.gz | diff | 180.0+0.30 | LLR: 2.94 (-2.94, 2.94) [0.00, 3.00] Games: 2076 W: 605 L: 444 D: 1027 Ptnml(0-2): 0, 139, 600, 298, 1 | t3d vs BT4 |
| Menkib | Leela-dag-preview | t3d-kd2-03007500.pb.gz * | diff | 180.0+0.30 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 2184 W: 666 L: 487 D: 1031 Ptnml(0-2): 10, 137, 610, 334, 1 | t3d vs BT4 |
| Johnsp | Leela-dag-preview | t3d-kd2-03477500 | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 1698 W: 451 L: 297 D: 950 Ptnml(0-2): 0, 89, 517, 243, 0 | LTC - Verification of T3d-kd2 without uncertainty |
| Menkib | Leela-dag-preview | t3d-kd2-03477500 | diff | 60.0+1.00 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 1322 W: 432 L: 251 D: 639 Ptnml(0-2): 0, 55, 370, 236, 0 | Test to see if new t3d configuration beats current bt4 configuration at ccc bullet. |
| Johnsp | Leela-dag-preview | t3d-kd2-03477500 | diff | 8.0+0.08 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 1854 W: 537 L: 371 D: 946 Ptnml(0-2): 0, 126, 510, 290, 1 | Verification of T3d-kd2 without uncertainty |
| Menkib | Leela-dag-preview | t3d-kd2-03477500 | diff | 180.0+0.30 | LLR: 1.40 (-2.94, 2.94) [0.00, 3.00] Games: 10498 W: 2581 L: 2496 D: 5421 Ptnml(0-2): 0, 842, 3480, 927, 0 | t3d-kd2-03477500 vs t3d-kd2-03007500 |
| Kovax | Leela-dag-preview | t1-cleanvisit2-polhead-25k | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 9518 W: 2167 L: 1986 D: 5365 Ptnml(0-2): 2, 963, 2646, 1148, 0 | |
| Kovax | Leela-dag-preview | debl1M-cleanvisit-100k-muon | diff | 40.0+0.40 | LLR: 0.31 (-2.94, 2.94) [0.00, 3.00] Games: 2262 W: 503 L: 482 D: 1277 Ptnml(0-2): 0, 233, 644, 254, 0 | higher pst |
| Kovax | Leela-dag-preview | debl1M-cleanvisit-100k-muon | diff | 40.0+0.40 | LLR: 0.30 (-2.94, 2.94) [0.00, 3.00] Games: 2214 W: 503 L: 482 D: 1229 Ptnml(0-2): 0, 235, 616, 256, 0 | scaling test |
| Menkib | Leela-dag-preview | t3d-kd2-03092500 | diff | 180.0+0.30 | LLR: 0.13 (-2.94, 2.94) [0.00, 3.00] Games: 3448 W: 849 L: 837 D: 1762 Ptnml(0-2): 0, 279, 1154, 291, 0 | 03092500 vs 03007500 |
| Menkib | Leela-dag-preview | t3d-kd2-03287500 * | diff | 180.0+0.30 | LLR: -0.42 (-2.94, 2.94) [0.00, 3.00] Games: 3596 W: 838 L: 852 D: 1906 Ptnml(0-2): 0, 328, 1156, 314, 0 | 03287500 vs 03007500 |
| Kovax | Leela-dag-preview | debl1M-cleanvisit-100k-muon | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 5960 W: 1424 L: 1248 D: 3288 Ptnml(0-2): 1, 586, 1633, 756, 4 | Muon vs Adam ELO comparison vs base |
| Kovax | Leela-dag-preview | master | diff | 10.0+0.10 | Tuning 2 Parameters 500/500 Iterations 8000/8000 Games Played | Muon PST,fpu further tune |
| Menkib | Leela-dag-preview | 744706 | diff | 1.0+0.01 | LLR: -0.67 (-2.94, 2.94) [0.00, 3.00] Games: 256 W: 48 L: 103 D: 105 Ptnml(0-2): 11, 49, 54, 12, 2 | Cuda arch detection and c++ standard version on windows (#2402) * Fix cuda arch detection on windows * Add NVCC c++ standard support check * Add cutlass support to cuda 11 builds * Simplify nvcc feature support checks |
| Kovax | Leela-dag-preview | debl1M-cleanvisit-100k | diff | 40.0+0.40 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 7314 W: 1671 L: 1505 D: 4138 Ptnml(0-2): 0, 642, 2207, 808, 0 | |
| Kovax | Leela-dag-preview | debl1M-cleanvisit-100k | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 9206 W: 2153 L: 1975 D: 5078 Ptnml(0-2): 0, 903, 2626, 1067, 7 | |
| Kovax | Leela-dag-preview | master | diff | 10.0+0.10 | Tuning 2 Parameters 1000/1000 Iterations 16000/16000 Games Played | |