checkpoint @ game=880 steps=880

training_log.txt

@@ -797,3 +797,13 @@
 [2026-06-13 04:33:40] game=  868 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=868 | loss=nan (p=nan v=0.5627) | game=25.4s train=28.2s
 [2026-06-13 04:34:34] game=  869 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=869 | loss=nan (p=nan v=0.5622) | game=24.0s train=30.3s
 [2026-06-13 04:35:28] game=  870 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=870 | loss=nan (p=nan v=0.5156) | game=24.2s train=29.4s
+[2026-06-13 04:36:26] game=  871 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=871 | loss=nan (p=nan v=0.5393) | game=25.5s train=30.1s
+[2026-06-13 04:37:22] game=  872 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=872 | loss=nan (p=nan v=0.6015) | game=24.1s train=31.5s
+[2026-06-13 04:38:17] game=  873 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=873 | loss=nan (p=nan v=0.5703) | game=24.2s train=30.9s
+[2026-06-13 04:39:14] game=  874 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=874 | loss=nan (p=nan v=0.4456) | game=24.1s train=32.9s
+[2026-06-13 04:40:10] game=  875 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=875 | loss=nan (p=nan v=0.5234) | game=24.4s train=32.0s
+[2026-06-13 04:40:54] game=  876 | 1-0 | moves= 33 | buf=50,000 | steps=876 | loss=nan (p=nan v=0.5550) | game=9.9s train=34.0s
+[2026-06-13 04:41:52] game=  877 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=877 | loss=nan (p=nan v=0.5078) | game=24.3s train=33.0s
+[2026-06-13 04:42:51] game=  878 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=878 | loss=nan (p=nan v=0.5469) | game=24.3s train=35.2s
+[2026-06-13 04:43:50] game=  879 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=879 | loss=nan (p=nan v=0.6009) | game=24.7s train=34.1s
+[2026-06-13 04:44:51] game=  880 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=880 | loss=nan (p=nan v=0.4455) | game=24.2s train=36.0s