Active : 40 Machines / 80 Threads / 2.66 MNPS
Priority 0
MenkibLeela-dag-previewtcec-season-30-swissdiff1800.0+3.00LLR: 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
MenkibLeela-dag-previewtcec-tune-with-blocking-cuda *diff40.0+0.40Tuning 12 Parameters
54460/100000 Iterations
217840/400000 Games Played
Finished
KovaxLeela-dag-previewdebl1M-k2hyb-100kdiff10.0+0.10LLR: 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
MenkibLeela-dag-previewtcec-season-30-swissdiff1800.0+3.00LLR: -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)
KovaxLeela-dag-previewpolicy-blenddiff10.0+0.10LLR: 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.
KovaxLeela-dag-previewpolicy-blenddiff10.0+0.10Tuning 6 Parameters
3612/12500 Iterations
57794/200000 Games Played
Tune policy blending on T1 sharp net.
KovaxLeela-dag-previewmasterdiffN=1000Elo: 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.
KovaxLeela-dag-previewpolicy-blenddiffN=1000Elo: 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
KovaxLeela-dag-previewpolicy-blenddiffN=1000Tuning 6 Parameters
3000/3000 Iterations
192016/192000 Games Played
Policy blend tune on fix nodes
KovaxLeela-dag-previewmasterdiff10.0+0.10Tuning 2 Parameters
1000/1000 Iterations
16000/16000 Games Played
cleanvisit2 corpus less sharp than previous
MenkibLeela-dag-previewt3d-kd2-03007500.pb.gzdiff180.0+0.30LLR: 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
MenkibLeela-dag-previewt3d-kd2-03007500.pb.gz *diff180.0+0.30LLR: 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
JohnspLeela-dag-previewt3d-kd2-03477500diff40.0+0.40LLR: 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
MenkibLeela-dag-previewt3d-kd2-03477500diff60.0+1.00LLR: 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.
JohnspLeela-dag-previewt3d-kd2-03477500diff8.0+0.08LLR: 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
MenkibLeela-dag-previewt3d-kd2-03477500diff180.0+0.30LLR: 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
KovaxLeela-dag-previewt1-cleanvisit2-polhead-25kdiff10.0+0.10LLR: 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
KovaxLeela-dag-previewdebl1M-cleanvisit-100k-muondiff40.0+0.40LLR: 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
KovaxLeela-dag-previewdebl1M-cleanvisit-100k-muondiff40.0+0.40LLR: 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
MenkibLeela-dag-previewt3d-kd2-03092500diff180.0+0.30LLR: 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
MenkibLeela-dag-previewt3d-kd2-03287500 *diff180.0+0.30LLR: -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
KovaxLeela-dag-previewdebl1M-cleanvisit-100k-muondiff10.0+0.10LLR: 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
KovaxLeela-dag-previewmasterdiff10.0+0.10Tuning 2 Parameters
500/500 Iterations
8000/8000 Games Played
Muon PST,fpu further tune
MenkibLeela-dag-preview744706diff1.0+0.01LLR: -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
KovaxLeela-dag-previewdebl1M-cleanvisit-100kdiff40.0+0.40LLR: 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
KovaxLeela-dag-previewdebl1M-cleanvisit-100kdiff10.0+0.10LLR: 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
KovaxLeela-dag-previewmasterdiff10.0+0.10Tuning 2 Parameters
1000/1000 Iterations
16000/16000 Games Played