| Finished | ||||||
|---|---|---|---|---|---|---|
| Styxdo | Reckless | styx_gut_feel_experiment | diff | N=25000 | LLR: 3.19 (-2.25, 2.89) [0.00, 4.00] Games: 4900 W: 1713 L: 1495 D: 1692 Ptnml(0-2): 140, 511, 1006, 577, 216 | Various changes, most notably, increased WDL in both S1 and S2, more epochs, slightly altered LR bounds. |
| Styxdo | Reckless | v18-bf93ebe8 | diff | N=25000 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 54310 W: 18004 L: 17601 D: 18705 Ptnml(0-2): 1849, 5981, 11178, 6212, 1935 | Same training parameters except filtering logic to match distribution |
| Styxdo | Reckless | l1_768_test | diff | 8.0+0.08 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 8118 W: 2115 L: 1954 D: 4049 Ptnml(0-2): 38, 931, 1971, 1070, 49 | STC test for L1=768 (128 more neurons) |
| Styxdo | Reckless | l1_768_test | diff | N=25000 | LLR: 2.98 (-2.25, 2.89) [0.00, 4.00] Games: 5506 W: 1930 L: 1720 D: 1856 Ptnml(0-2): 170, 580, 1117, 642, 244 | L1=768 identical training parameters |
| Styxdo | Reckless | multifile_loader_w_1536_data | diff | N=25000 | Elo: -1.70 +- 2.40 (95%) [N=40000] Games: 40318 W: 13201 L: 13398 D: 13719 Ptnml(0-2): 1433, 4515, 8446, 4346, 1419 | Essentially same training as before, test of multifile loader, side effects was a lower Loss, so testing. |
| Styxdo | Reckless | l1_640_new_1536_data_wdl_adj1 | diff | N=25000 | Elo: -16.43 +- 2.62 (95%) [N=40000] Games: 35490 W: 11061 L: 12738 D: 11691 Ptnml(0-2): 1620, 4239, 7203, 3564, 1119 | Same training parameters as v16, only difference is WDL in S2 is 0.5, and the data used is from 1536 net. |
| Styxdo | Reckless | styx_v5 | diff | 8.0+0.08 | Elo: -7.43 +- 3.00 (95%) [N=20000] Games: 15718 W: 3843 L: 4179 D: 7696 Ptnml(0-2): 150, 2022, 3792, 1804, 91 | STC |
| Styxdo | Reckless | styx_v5 | diff | N=25000 | Elo: -10.90 +- 2.42 (95%) [N=40000] Games: 40412 W: 12880 L: 14147 D: 13385 Ptnml(0-2): 1681, 4655, 8407, 4176, 1287 | Retrain with correct params |
| Styxdo | Reckless | pure_1536_3650m_l1_640 | diff | 8.0+0.08 | LLR: -1.18 (-2.25, 2.89) [0.00, 4.00] Games: 5744 W: 1442 L: 1480 D: 2822 Ptnml(0-2): 45, 700, 1414, 674, 39 | STC |
| Styxdo | Reckless | pure_1536_3650m_l1_640 | diff | N=25000 | LLR: -2.91 (-2.25, 2.89) [0.00, 4.00] Games: 12102 W: 4028 L: 4159 D: 3915 Ptnml(0-2): 472, 1336, 2506, 1325, 412 | Fixed Node test |
| Styxdo | Reckless | v16-4dd4d325 | diff | 40.0+0.40 | LLR: 2.96 (-2.25, 2.89) [0.00, 4.00] Games: 10296 W: 2500 L: 2342 D: 5454 Ptnml(0-2): 12, 1160, 2646, 1318, 12 | STC passed, LTC |
| Styxdo | Reckless | v16-4dd4d325 | diff | 8.0+0.08 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 6938 W: 1776 L: 1618 D: 3544 Ptnml(0-2): 34, 769, 1714, 909, 43 | 3695M, Higher training time |
| Styxdo | Reckless | v16-4dd4d325 | diff | N=25000 | LLR: 3.07 (-2.25, 2.89) [0.00, 4.00] Games: 5504 W: 1907 L: 1696 D: 1901 Ptnml(0-2): 170, 542, 1161, 665, 214 | Same data as last run, higher training time. |
| Styxdo | Reckless | v14-46e0bb9a | diff | 40.0+0.40 | LLR: 1.11 (-2.25, 2.89) [0.00, 4.00] Games: 45250 W: 10805 L: 10626 D: 23819 Ptnml(0-2): 70, 5317, 11668, 5504, 66 | STC Passed at : https://rickdiculous.pythonanywhere.com/test/3940/ Testing LTC |
| Styxdo | Reckless | main | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [0.00, 4.00] Games: 14308 W: 3451 L: 3283 D: 7574 Ptnml(0-2): 54, 1484, 3911, 1650, 55 | Summary: S1=50 (halved), batch_per_batchsize=12208 (doubled) S2=200 (doubled), batch_per_batchsize=2500(halved) |
| Styxdo | Reckless | nmp_verification_search | diff | 8.0+0.08 | LLR: 3.24 (-2.25, 2.89) [-5.00, 0.00] Games: 10258 W: 2467 L: 2387 D: 5404 Ptnml(0-2): 41, 1230, 2510, 1304, 44 | Verification Search in nmp |
| Styxdo | Reckless | imrovement_in_razoring | diff | 8.0+0.08 | LLR: -2.35 (-2.25, 2.89) [0.00, 4.00] Games: 10070 W: 2378 L: 2455 D: 5237 Ptnml(0-2): 41, 1260, 2519, 1165, 50 | Change scale of improvement val |
| Styxdo | Reckless | imrovement_in_razoring | diff | 8.0+0.08 | LLR: -2.43 (-2.25, 2.89) [0.00, 4.00] Games: 55200 W: 13208 L: 13152 D: 28840 Ptnml(0-2): 250, 6646, 13743, 6720, 241 | Draft 1 of using World's idea of improvement in Razoring |
| Styxdo | Reckless | tried_to_cut | diff | 8.0+0.08 | LLR: -2.26 (-2.25, 2.89) [0.00, 4.00] Games: 32168 W: 7574 L: 7580 D: 17014 Ptnml(0-2): 144, 3883, 8043, 3863, 151 | tried to cut, but even less reduction on probcut |
| Styxdo | Reckless | tried_cut_and_null | diff | 8.0+0.08 | LLR: -2.02 (-2.25, 2.89) [0.00, 4.00] Games: 4988 W: 1145 L: 1222 D: 2621 Ptnml(0-2): 25, 628, 1262, 557, 22 | Combines the condition for both npm and probcut, increases the chances of a hit |
| Styxdo | Reckless | tried_to_cut_null | diff | 8.0+0.08 | LLR: -1.56 (-2.25, 2.89) [0.00, 4.00] Games: 12154 W: 2797 L: 2831 D: 6526 Ptnml(0-2): 49, 1475, 3063, 1441, 49 | (Fixed) |
| Styxdo | Reckless | tried_to_cut_more | diff | 8.0+0.08 | LLR: -2.51 (-2.25, 2.89) [0.00, 4.00] Games: 19332 W: 4508 L: 4564 D: 10260 Ptnml(0-2): 82, 2374, 4814, 2310, 86 | Slightly changing the value, aligning with how we treat PV |
| Styxdo | Reckless | tried_to_cut | diff | 8.0+0.08 | LLR: -2.33 (-2.25, 2.89) [0.00, 4.00] Games: 46046 W: 10786 L: 10753 D: 24507 Ptnml(0-2): 205, 5588, 11423, 5583, 224 | Essentially the same thing as the other test (that one is nmp only), this is probcut only |