checkpoint @ game=850 steps=850

training_log.txt

@@ -767,3 +767,13 @@
 [2026-06-13 04:10:08] game=  838 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=838 | loss=nan (p=nan v=0.6643) | game=24.2s train=16.0s
 [2026-06-13 04:10:50] game=  839 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=839 | loss=nan (p=nan v=0.5233) | game=24.3s train=16.9s
 [2026-06-13 04:11:31] game=  840 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=840 | loss=nan (p=nan v=0.5764) | game=23.7s train=17.2s
+[2026-06-13 04:12:14] game=  841 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=841 | loss=nan (p=nan v=0.5249) | game=23.7s train=17.8s
+[2026-06-13 04:12:56] game=  842 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=842 | loss=nan (p=nan v=0.5466) | game=23.6s train=18.2s
+[2026-06-13 04:13:44] game=  843 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=843 | loss=nan (p=nan v=0.6403) | game=30.7s train=17.8s
+[2026-06-13 04:14:27] game=  844 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=844 | loss=nan (p=nan v=0.6250) | game=23.8s train=18.9s
+[2026-06-13 04:15:10] game=  845 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=845 | loss=nan (p=nan v=0.5851) | game=23.7s train=19.3s
+[2026-06-13 04:15:54] game=  846 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=846 | loss=nan (p=nan v=0.4998) | game=23.7s train=19.7s
+[2026-06-13 04:16:38] game=  847 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=847 | loss=nan (p=nan v=0.5390) | game=23.8s train=20.2s
+[2026-06-13 04:17:22] game=  848 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=848 | loss=nan (p=nan v=0.5781) | game=23.7s train=20.6s
+[2026-06-13 04:18:06] game=  849 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=849 | loss=nan (p=nan v=0.6172) | game=23.8s train=20.2s
+[2026-06-13 04:18:48] game=  850 | 1-0 | moves= 67 | buf=50,000 | steps=850 | loss=nan (p=nan v=0.5476) | game=20.4s train=20.6s