checkpoint @ game=920 steps=920

training_log.txt

@@ -837,3 +837,13 @@
 [2026-06-13 05:17:19] game=  908 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=908 | loss=nan (p=nan v=0.6563) | game=24.9s train=55.1s
 [2026-06-13 05:18:40] game=  909 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=909 | loss=nan (p=nan v=0.5935) | game=24.7s train=56.5s
 [2026-06-13 05:20:04] game=  910 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=910 | loss=nan (p=nan v=0.5852) | game=27.1s train=56.7s
+[2026-06-13 05:21:28] game=  911 | 1-0 | moves= 79 | buf=50,000 | steps=911 | loss=nan (p=nan v=0.5626) | game=24.1s train=58.4s
+[2026-06-13 05:22:52] game=  912 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=912 | loss=nan (p=nan v=0.6253) | game=24.7s train=59.0s
+[2026-06-13 05:24:20] game=  913 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=913 | loss=nan (p=nan v=0.5704) | game=27.2s train=60.4s
+[2026-06-13 05:25:46] game=  914 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=914 | loss=nan (p=nan v=0.5934) | game=24.9s train=61.0s
+[2026-06-13 05:27:22] game=  915 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=915 | loss=nan (p=nan v=0.4450) | game=31.3s train=64.9s
+[2026-06-13 05:28:50] game=  916 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=916 | loss=nan (p=nan v=0.5477) | game=24.8s train=63.2s
+[2026-06-13 05:30:20] game=  917 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=917 | loss=nan (p=nan v=0.5710) | game=24.8s train=64.5s
+[2026-06-13 05:31:52] game=  918 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=918 | loss=nan (p=nan v=0.5787) | game=24.9s train=67.6s
+[2026-06-13 05:33:24] game=  919 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=919 | loss=nan (p=nan v=0.5780) | game=25.2s train=65.8s
+[2026-06-13 05:34:57] game=  920 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=920 | loss=nan (p=nan v=0.4928) | game=24.9s train=68.0s