checkpoint @ game=990 steps=990

training_log.txt

@@ -907,3 +907,13 @@
 [2026-06-13 07:35:54] game=  978 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=978 | loss=nan (p=nan v=0.5079) | game=25.8s train=132.3s
 [2026-06-13 07:38:29] game=  979 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=979 | loss=nan (p=nan v=0.4851) | game=25.9s train=129.4s
 [2026-06-13 07:41:06] game=  980 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=980 | loss=nan (p=nan v=0.5142) | game=26.1s train=130.7s
+[2026-06-13 07:43:45] game=  981 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=981 | loss=nan (p=nan v=0.5227) | game=25.8s train=131.4s
+[2026-06-13 07:46:23] game=  982 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=982 | loss=nan (p=nan v=0.5233) | game=25.8s train=132.4s
+[2026-06-13 07:49:03] game=  983 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=983 | loss=nan (p=nan v=0.5857) | game=25.9s train=134.0s
+[2026-06-13 07:51:49] game=  984 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=984 | loss=nan (p=nan v=0.5551) | game=30.2s train=135.5s
+[2026-06-13 07:54:31] game=  985 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=985 | loss=nan (p=nan v=0.4600) | game=25.9s train=135.6s
+[2026-06-13 07:57:14] game=  986 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=986 | loss=nan (p=nan v=0.6258) | game=26.1s train=137.7s
+[2026-06-13 08:00:04] game=  987 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=987 | loss=nan (p=nan v=0.6015) | game=32.2s train=137.2s
+[2026-06-13 08:02:49] game=  988 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=988 | loss=nan (p=nan v=0.5703) | game=26.0s train=138.7s
+[2026-06-13 08:05:40] game=  989 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=989 | loss=nan (p=nan v=0.6328) | game=30.6s train=140.2s
+[2026-06-13 08:08:27] game=  990 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=990 | loss=nan (p=nan v=0.5467) | game=26.3s train=140.4s