checkpoint @ game=850 steps=850

training_log.txt

@@ -1141,3 +1141,13 @@
 [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
+[2026-06-15 08:32:59] game=  841 | 1/2-1/2 | moves= 71 | buf=70,000 | steps=841 | loss=8.5842 (p=8.4493 v=0.1349) | game=6.9s train=178.5s
+[2026-06-15 08:36:07] game=  842 | 1/2-1/2 | moves= 48 | buf=70,000 | steps=842 | loss=8.9360 (p=8.4493 v=0.4867) | game=9.2s train=178.5s
+[2026-06-15 08:39:15] game=  843 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=843 | loss=8.9101 (p=8.4493 v=0.4608) | game=9.4s train=178.5s
+[2026-06-15 08:42:19] game=  844 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=844 | loss=8.8853 (p=8.4493 v=0.4360) | game=5.9s train=178.5s
+[2026-06-15 08:45:26] game=  845 | 1/2-1/2 | moves= 68 | buf=70,000 | steps=845 | loss=8.8469 (p=8.4493 v=0.3976) | game=6.5s train=180.0s
+[2026-06-15 08:48:32] game=  846 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=846 | loss=8.8041 (p=8.4493 v=0.3548) | game=7.8s train=178.6s
+[2026-06-15 08:51:36] game=  847 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=847 | loss=8.7670 (p=8.4493 v=0.3177) | game=4.8s train=178.7s
+[2026-06-15 08:54:41] game=  848 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=848 | loss=8.7333 (p=8.4493 v=0.2840) | game=5.2s train=179.8s
+[2026-06-15 08:57:45] game=  849 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=849 | loss=8.7133 (p=8.4493 v=0.2640) | game=5.7s train=178.6s
+[2026-06-15 09:00:50] game=  850 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=850 | loss=8.6553 (p=8.4493 v=0.2060) | game=4.9s train=180.2s