checkpoint @ game=840 steps=840

training_log.txt

@@ -1131,3 +1131,13 @@
 [2026-06-15 07:52:46] game=  828 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=828 | loss=8.8371 (p=8.4493 v=0.3878) | game=5.7s train=179.7s
 [2026-06-15 07:55:51] game=  829 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=829 | loss=8.7737 (p=8.4493 v=0.3244) | game=5.9s train=178.4s
 [2026-06-15 07:58:58] game=  830 | 1/2-1/2 | moves= 79 | buf=70,000 | steps=830 | loss=8.7566 (p=8.4493 v=0.3073) | game=8.9s train=178.4s
+[2026-06-15 08:02:07] game=  831 | 1/2-1/2 | moves= 64 | buf=70,000 | steps=831 | loss=8.6945 (p=8.4493 v=0.2452) | game=6.2s train=179.6s
+[2026-06-15 08:05:13] game=  832 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=832 | loss=8.7055 (p=8.4493 v=0.2562) | game=7.8s train=178.5s
+[2026-06-15 08:08:18] game=  833 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=833 | loss=8.6843 (p=8.4493 v=0.2350) | game=5.4s train=179.8s
+[2026-06-15 08:11:22] game=  834 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=834 | loss=8.6519 (p=8.4493 v=0.2026) | game=5.0s train=178.5s
+[2026-06-15 08:14:27] game=  835 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=835 | loss=8.6228 (p=8.4493 v=0.1735) | game=5.2s train=179.8s
+[2026-06-15 08:17:32] game=  836 | 1/2-1/2 | moves= 66 | buf=70,000 | steps=836 | loss=8.6168 (p=8.4493 v=0.1675) | game=6.4s train=178.6s
+[2026-06-15 08:20:38] game=  837 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=837 | loss=8.6169 (p=8.4493 v=0.1676) | game=6.4s train=180.0s
+[2026-06-15 08:23:43] game=  838 | 1/2-1/2 | moves= 66 | buf=70,000 | steps=838 | loss=8.5825 (p=8.4493 v=0.1332) | game=6.5s train=178.6s
+[2026-06-15 08:26:48] game=  839 | 1/2-1/2 | moves= 64 | buf=70,000 | steps=839 | loss=8.5920 (p=8.4493 v=0.1427) | game=6.2s train=178.4s
+[2026-06-15 08:29:51] game=  840 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=840 | loss=8.5768 (p=8.4493 v=0.1276) | game=4.9s train=178.5s