checkpoint @ game=1000 steps=1000

training_log.txt

@@ -917,3 +917,13 @@
 [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
+[2026-06-13 08:11:17] game=  991 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=991 | loss=nan (p=nan v=0.5858) | game=26.5s train=142.3s
+[2026-06-13 08:14:06] game=  992 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=992 | loss=nan (p=nan v=0.5859) | game=26.0s train=142.2s
+[2026-06-13 08:16:56] game=  993 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=993 | loss=nan (p=nan v=0.6406) | game=26.0s train=144.0s
+[2026-06-13 08:19:47] game=  994 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=994 | loss=nan (p=nan v=0.5938) | game=26.1s train=145.3s
+[2026-06-13 08:22:45] game=  995 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=995 | loss=nan (p=nan v=0.6245) | game=30.7s train=146.8s
+[2026-06-13 08:25:38] game=  996 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=996 | loss=nan (p=nan v=0.5781) | game=26.3s train=146.6s
+[2026-06-13 08:28:34] game=  997 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=997 | loss=nan (p=nan v=0.5626) | game=26.3s train=149.4s
+[2026-06-13 08:31:30] game=  998 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=998 | loss=nan (p=nan v=0.5236) | game=26.3s train=149.9s
+[2026-06-13 08:34:27] game=  999 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=999 | loss=nan (p=nan v=0.5699) | game=26.2s train=150.9s
+[2026-06-13 08:37:31] game= 1000 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,000 | loss=nan (p=nan v=0.5545) | game=31.0s train=152.3s