| Active : 5 Machines / 72 Threads / 74.15 MNPS | ||||||
|---|---|---|---|---|---|---|
| Priority 1 | ||||||
| Finished | ||||||
| Styxdo | Reckless | material-output-buckets | diff | N=25000 | LLR: 2.93 (-2.25, 2.89) [0.00, 4.00] Games: 7374 W: 2492 L: 2281 D: 2601 Ptnml(0-2): 234, 786, 1469, 931, 267 | S2 Early ply skipping to 28, passed STC on Slim, not resetting optimizer this time. |
| Styxdo | Reckless | early_ply_skipping_full | diff | 8.0+0.08 | LLR: -1.93 (-2.25, 2.89) [0.00, 4.00] Games: 4352 W: 1071 L: 1149 D: 2132 Ptnml(0-2): 31, 576, 1033, 512, 24 | Full S2 training with early ply skipping. Slim passed STC. |
| Styxdo | Reckless | blend_both_s1_s2 | diff | 8.0+0.08 | LLR: -2.26 (-2.25, 2.89) [0.00, 4.00] Games: 15240 W: 3826 L: 3884 D: 7530 Ptnml(0-2): 97, 1833, 3789, 1833, 68 | Blend 640 and 1536 data in both stages |
| Styxdo | Reckless | s2_sigmoid_expt_1 | diff | 8.0+0.08 | LLR: -2.30 (-2.25, 2.89) [0.00, 4.00] Games: 2244 W: 519 L: 621 D: 1104 Ptnml(0-2): 26, 304, 546, 238, 8 | S2 Loss SigmoidMPE modification test. |
| Styxdo | Reckless | blend_s1_pure_1536_s2 | diff | 8.0+0.08 | LLR: -2.29 (-2.25, 2.89) [0.00, 4.00] Games: 35482 W: 8954 L: 8951 D: 17577 Ptnml(0-2): 223, 4342, 8569, 4423, 184 | Blend 640+1536 data in S1, Pure 1536 in S2 |
| Styxdo | Reckless | sigmoid_expt_1 | diff | 8.0+0.08 | LLR: -2.29 (-2.25, 2.89) [0.00, 4.00] Games: 18078 W: 4468 L: 4520 D: 9090 Ptnml(0-2): 75, 2339, 4352, 2109, 164 | Loss sigmoid expt |
| Styxdo | Reckless | s2_lr_ub_increase | diff | 40.0+0.40 | LLR: -2.28 (-2.25, 2.89) [0.00, 4.00] Games: 24380 W: 5778 L: 5807 D: 12795 Ptnml(0-2): 35, 2930, 6289, 2901, 35 | LTC |
| Styxdo | Reckless | s2_lr_ub_increase | diff | 8.0+0.08 | LLR: -2.32 (-2.25, 2.89) [0.00, 4.00] Games: 10394 W: 2529 L: 2606 D: 5259 Ptnml(0-2): 68, 1312, 2506, 1251, 60 | Matching increase in S2 LR |
| Styxdo | Reckless | half_batchsize_double_epoch | diff | 40.0+0.40 | LLR: -1.64 (-2.25, 2.89) [0.00, 4.00] Games: 3156 W: 725 L: 786 D: 1645 Ptnml(0-2): 2, 403, 828, 344, 1 | Extending the experiment to S1 too. Half the batchsize as v18, double the epochs. |
| Styxdo | Reckless | test_s2_400_epoch | diff | 40.0+0.40 | LLR: -2.26 (-2.25, 2.89) [0.00, 4.00] Games: 5554 W: 1234 L: 1316 D: 3004 Ptnml(0-2): 9, 695, 1449, 617, 7 | Test changing to smaller batches but more epochs to match. |
| Styxdo | Reckless | styx_gut_feel_experiment | diff | 8.0+0.08 | LLR: 2.97 (-2.25, 2.89) [0.00, 4.00] Games: 11604 W: 2974 L: 2797 D: 5833 Ptnml(0-2): 38, 1417, 2791, 1442, 114 | STC Test of it |
| 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 |