Finished
StyxdoRecklesss0_lite_test1diff8.0+0.08
LLR: -2.26 (-2.25, 2.89) [0.00, 4.00]
Games: 3682 W: 885 L: 981 D: 1816
Ptnml(0-2): 26, 501, 877, 417, 20
Introduction of S0 as discussed. This is 'lite' version, full training on 3080 to follow.
PeregrRecklessbig-brain-see-ideadiff8.0+0.08
LLR: -2.28 (-2.25, 2.89) [0.00, 4.00]
Games: 38328 W: 9269 L: 9257 D: 19802
Ptnml(0-2): 161, 4664, 9517, 4646, 176
PeregrRecklessttpv_force_searchdiff8.0+0.08
LLR: -2.59 (-2.25, 2.89) [0.00, 4.00]
Games: 7258 W: 1701 L: 1797 D: 3760
Ptnml(0-2): 32, 922, 1813, 834, 28
PeregrRecklessneg-ext-npvdiff8.0+0.08
LLR: -2.33 (-2.25, 2.89) [0.00, 4.00]
Games: 17016 W: 4103 L: 4158 D: 8755
Ptnml(0-2): 93, 2031, 4302, 2002, 80
StyxdoRecklessreduced_training_time_expt3diff8.0+0.08
LLR: -2.32 (-2.25, 2.89) [-4.00, 0.00]
Games: 42342 W: 10402 L: 10643 D: 21297
Ptnml(0-2): 268, 5319, 10181, 5192, 211
Adjused S1 Epoch/Batch_size balance but maintained overall training time. S2 Epochs reduced.
PeregrRecklessbonus_noisydiff8.0+0.08
LLR: -2.36 (-2.25, 2.89) [0.00, 4.00]
Games: 19998 W: 4807 L: 4854 D: 10337
Ptnml(0-2): 98, 2413, 5000, 2414, 74
PeregrRecklessbig-brain-see-idea2diff8.0+0.08
LLR: -2.30 (-2.25, 2.89) [0.00, 4.00]
Games: 10070 W: 2391 L: 2466 D: 5213
Ptnml(0-2): 54, 1244, 2505, 1187, 45
WorldRecklesstb-support-fixdiff8.0+0.08
LLR: -2.31 (-2.25, 2.89) [0.00, 4.00]
Games: 10268 W: 2379 L: 2449 D: 5440
Ptnml(0-2): 48, 1102, 2897, 1046, 41
tonight is the night
WorldRecklesstb-supportdiff8.0+0.08
LLR: -0.90 (-2.25, 2.89) [0.00, 4.00]
Games: 11380 W: 2722 L: 2728 D: 5930
Ptnml(0-2): 40, 1212, 3187, 1216, 35
main, lichess uho, -O3
WorldRecklesstb-support-no-pgodiff8.0+0.08
LLR: 2.92 (-2.25, 2.89) [0.00, 4.00]
Games: 10740 W: 2656 L: 2500 D: 5584
Ptnml(0-2): 34, 1096, 2954, 1252, 34
no pgo, lichess uho
WorldRecklesstb-supportdiff8.0+0.08
LLR: -1.24 (-2.25, 2.89) [0.00, 4.00]
Games: 6820 W: 1631 L: 1666 D: 3523
Ptnml(0-2): 35, 766, 1836, 745, 28
uho book
WorldRecklesstb-supportdiff8.0+0.08
LLR: -0.85 (-2.25, 2.89) [0.00, 4.00]
Games: 720 W: 116 L: 142 D: 462
Ptnml(0-2): 0, 63, 260, 37, 0
endgames book
WorldRecklesstb-supportdiffN=50000
LLR: 3.17 (-2.25, 2.89) [0.00, 4.00]
Games: 2606 W: 605 L: 504 D: 1497
Ptnml(0-2): 0, 107, 989, 206, 1
FFFFFFFFFFFFFFS
PeregrRecklesssimpl-aspdiff8.0+0.08
LLR: -2.41 (-2.25, 2.89) [-4.00, 0.00]
Games: 31220 W: 7498 L: 7705 D: 16017
Ptnml(0-2): 147, 3931, 7655, 3736, 141
WorldRecklesstb-support-debugdiff8.0+0.08
LLR: -0.68 (-2.25, 2.89) [0.00, 4.00]
Games: 2438 W: 463 L: 478 D: 1497
Ptnml(0-2): 0, 145, 944, 130, 0
collect some pgns to analyze
WorldRecklesstb-supportdiff8.0+0.08
LLR: -2.16 (-2.25, 2.89) [0.00, 4.00]
Games: 11064 W: 2084 L: 2124 D: 6856
Ptnml(0-2): 3, 586, 4393, 548, 2
endgame book
WorldRecklesstb-supportdiff8.0+0.08
LLR: -0.13 (-2.25, 2.89) [0.00, 4.00]
Games: 3766 W: 935 L: 930 D: 1901
Ptnml(0-2): 13, 379, 1094, 384, 13
fixed, no adjudication
WorldRecklesstb-supportdiff8.0+0.08
LLR: -2.28 (-2.25, 2.89) [0.00, 4.00]
Games: 3896 W: 902 L: 990 D: 2004
Ptnml(0-2): 16, 474, 1052, 394, 12
PeregrRecklesskiller_cntdiff8.0+0.08
LLR: -1.79 (-2.25, 2.89) [0.00, 4.00]
Games: 14534 W: 3516 L: 3554 D: 7464
Ptnml(0-2): 81, 1736, 3657, 1726, 67
PeregrRecklessquiet_hist_lmrdiff8.0+0.08
LLR: -2.32 (-2.25, 2.89) [0.00, 4.00]
Games: 6584 W: 1510 L: 1596 D: 3478
Ptnml(0-2): 30, 831, 1659, 739, 33
StyxdoRecklessreduced_training_time_expt2diff8.0+0.08
LLR: -2.29 (-2.25, 2.89) [0.00, 4.00]
Games: 2542 W: 563 L: 662 D: 1317
Ptnml(0-2): 18, 349, 630, 262, 12
Similar to last time, this time keeps more epoch in S2
PeregrRecklessnoise_hist_lmrdiff8.0+0.08
LLR: -0.92 (-2.25, 2.89) [0.00, 4.00]
Games: 3102 W: 738 L: 771 D: 1593
Ptnml(0-2): 16, 402, 742, 381, 10
WorldRecklesspcm-conthistdiff8.0+0.08
LLR: -2.26 (-2.25, 2.89) [0.00, 4.00]
Games: 19934 W: 4823 L: 4866 D: 10245
Ptnml(0-2): 103, 2380, 5020, 2385, 79
StyxdoRecklessreduced_training_time_expt1diff8.0+0.08
LLR: -2.26 (-2.25, 2.89) [-4.00, 0.00]
Games: 4236 W: 1009 L: 1128 D: 2099
Ptnml(0-2): 27, 572, 1033, 465, 21
Reduced Batchsize, retrains full network on reduced batchsizes attempting to go back to lower training times without losing elo
PeregrRecklessneg-ext-noisydiff8.0+0.08
LLR: -2.34 (-2.25, 2.89) [0.00, 4.00]
Games: 23584 W: 5640 L: 5675 D: 12269
Ptnml(0-2): 101, 2796, 6033, 2761, 101