checkpoint @ game=910 steps=910

training_log.txt

@@ -827,3 +827,13 @@
 [2026-06-13 05:04:46] game=  898 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=898 | loss=nan (p=nan v=0.5234) | game=24.6s train=46.5s
 [2026-06-13 05:05:45] game=  899 | 1-0 | moves= 33 | buf=50,000 | steps=899 | loss=nan (p=nan v=0.5938) | game=10.1s train=49.5s
 [2026-06-13 05:06:58] game=  900 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=900 | loss=nan (p=nan v=0.6173) | game=24.8s train=47.9s
+[2026-06-13 05:08:15] game=  901 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=901 | loss=nan (p=nan v=0.5626) | game=24.6s train=48.8s
+[2026-06-13 05:09:32] game=  902 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=902 | loss=nan (p=nan v=0.6013) | game=26.9s train=49.6s
+[2026-06-13 05:10:47] game=  903 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=903 | loss=nan (p=nan v=0.6794) | game=24.7s train=50.0s
+[2026-06-13 05:12:05] game=  904 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=904 | loss=nan (p=nan v=0.6014) | game=24.6s train=53.6s
+[2026-06-13 05:13:23] game=  905 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=905 | loss=nan (p=nan v=0.5705) | game=24.7s train=53.0s
+[2026-06-13 05:14:41] game=  906 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=906 | loss=nan (p=nan v=0.5164) | game=24.6s train=53.2s
+[2026-06-13 05:15:59] game=  907 | 1-0 | moves= 69 | buf=50,000 | steps=907 | loss=nan (p=nan v=0.5231) | game=20.9s train=56.8s
+[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