Finished
StyxdoReckless1024_test_branchdiff8.0+0.08
LLR: 3.00 (-2.25, 2.89) [0.00, 4.00]
Games: 14796 W: 3797 L: 3612 D: 7387
Ptnml(0-2): 64, 1751, 3604, 1894, 85
STC
PeregrRecklesslate-tt-cutdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [0.00, 4.00]
Games: 19264 W: 4796 L: 4604 D: 9864
Ptnml(0-2): 79, 2257, 4789, 2407, 100
test as gainer
WorldReckless896_test_branchdiffN=25000
LLR: 3.13 (-2.25, 2.89) [0.00, 4.00]
Games: 6856 W: 2451 L: 2226 D: 2179
Ptnml(0-2): 232, 692, 1417, 793, 294
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.96 (-2.25, 2.89) [0.00, 4.00]
Games: 7204 W: 1865 L: 1705 D: 3634
Ptnml(0-2): 26, 827, 1761, 937, 51
Retrain same model, run 1 (for PR message)
WorldRecklessconthist-on-pointersdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [0.00, 4.00]
Games: 72000 W: 17739 L: 17408 D: 36853
Ptnml(0-2): 254, 7666, 19844, 7967, 269
speedup?
WorldReckless896_test_branchdiff8.0+0.08
LLR: 2.94 (-2.25, 2.89) [0.00, 4.00]
Games: 19334 W: 4976 L: 4781 D: 9577
Ptnml(0-2): 98, 2244, 4786, 2443, 96
STC
WorldRecklessv22-abc72242diffN=25000
LLR: 3.01 (-2.94, 2.94) [0.00, 4.00]
Games: 90740 W: 30729 L: 30160 D: 29851
Ptnml(0-2): 3383, 9908, 18434, 10047, 3598
another run of the same config
StyxdoReckless896_test_branchdiff40.0+0.40
LLR: 2.90 (-2.25, 2.89) [0.00, 4.00]
Games: 7728 W: 1864 L: 1717 D: 4147
Ptnml(0-2): 10, 836, 2027, 979, 12
SF Batchsize standardization, best STC this far on short training, testing LTC
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.92 (-2.25, 2.89) [0.00, 4.00]
Games: 8102 W: 2137 L: 1978 D: 3987
Ptnml(0-2): 33, 911, 2020, 1038, 49
Short Training with SF batch standardization
WorldReckless896_test_branchdiff40.0+0.40
LLR: 2.89 (-2.25, 2.89) [0.00, 4.00]
Games: 29166 W: 7137 L: 6927 D: 15102
Ptnml(0-2): 37, 3408, 7484, 3616, 38
896, short training, no wdl warmup, S2 CosineDecay
WorldReckless896_test_branchdiffN=25000
LLR: 2.92 (-2.25, 2.89) [0.00, 4.00]
Games: 6406 W: 2280 L: 2067 D: 2059
Ptnml(0-2): 236, 618, 1335, 725, 289
896, short training, no wdl warmup, S2 CosineDecay
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.92 (-2.25, 2.89) [0.00, 4.00]
Games: 10020 W: 2633 L: 2465 D: 4922
Ptnml(0-2): 55, 1149, 2439, 1307, 60
896, short training, no wdl warmup, S2 CosineDecay
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.89 (-2.25, 2.89) [0.00, 4.00]
Games: 7060 W: 1874 L: 1717 D: 3469
Ptnml(0-2): 29, 811, 1711, 932, 47
L1=896, this time on the chonky training
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [0.00, 4.00]
Games: 36144 W: 9296 L: 9049 D: 17799
Ptnml(0-2): 205, 4231, 8969, 4446, 221
Consistent S1 WDL Scheduler with previous training
StyxdoReckless896_test_branchdiff8.0+0.08
LLR: 2.99 (-2.25, 2.89) [0.00, 4.00]
Games: 103882 W: 26251 L: 25789 D: 51842
Ptnml(0-2): 559, 12548, 25322, 12896, 616
Update nnue.rs
StyxdoReckless896_test_branchdiffN=25000
LLR: 3.06 (-2.25, 2.89) [0.00, 4.00]
Games: 4828 W: 1754 L: 1538 D: 1536
Ptnml(0-2): 158, 486, 992, 538, 240
Update nnue.rs
PeregrRecklessmore-negextdiff8.0+0.08
LLR: 2.98 (-2.25, 2.89) [0.00, 4.00]
Games: 26432 W: 6551 L: 6334 D: 13547
Ptnml(0-2): 114, 3109, 6556, 3320, 117
PeregrViridithas[Reckless] maindiff8.0+0.08
Elo: 3.23 +- 3.68 (95%) [N=10000]
Games: 10016 W: 2560 L: 2467 D: 4989
Ptnml(0-2): 88, 1121, 2445, 1318, 36
Viri vs Reckless SMP
PeregrRecklessoptimism-6diff40.0+0.40
LLR: 2.89 (-2.25, 2.89) [0.00, 4.00]
Games: 31698 W: 7328 L: 7113 D: 17257
Ptnml(0-2): 30, 3679, 8207, 3912, 21
PeregrRecklessoptimism-6diff8.0+0.08
LLR: 2.97 (-2.25, 2.89) [0.00, 4.00]
Games: 60078 W: 14798 L: 14480 D: 30800
Ptnml(0-2): 299, 7029, 15017, 7443, 251
PeregrRecklessspsa3-79kdiff40.0+0.40
LLR: 2.89 (-2.25, 2.89) [0.00, 4.00]
Games: 8938 W: 2171 L: 2020 D: 4747
Ptnml(0-2): 7, 1005, 2297, 1150, 10
PeregrRecklessreset-pvdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [-5.00, 0.00]
Games: 46976 W: 11544 L: 11612 D: 23820
Ptnml(0-2): 189, 5183, 12827, 5085, 204
Reset PV in qsearch just like search
PeregrRecklessclamp_betterdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [-4.00, 0.00]
Games: 29344 W: 7160 L: 7118 D: 15066
Ptnml(0-2): 128, 3126, 8128, 3156, 134
better eval range and freedom, TBs on
PeregrRecklessincheck_breakdiff8.0+0.08
LLR: 2.91 (-2.25, 2.89) [0.00, 4.00]
Games: 43548 W: 10709 L: 10445 D: 22394
Ptnml(0-2): 181, 5107, 10962, 5315, 209
PeregrRecklessdecisive_correctiondiff8.0+0.08
LLR: 3.01 (-2.25, 2.89) [0.00, 4.00]
Games: 13398 W: 3403 L: 3221 D: 6774
Ptnml(0-2): 60, 1562, 3317, 1656, 104
Test is_decisive correction with gainer bounds when TBs on