checkpoint @ game=1000 steps=1000

training_log.txt

@@ -917,3 +917,13 @@
 [2026-06-12 14:29:03] game=  988 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=988 | loss=nan (p=nan v=0.5213) | game=4.8s train=141.0s
 [2026-06-12 14:31:34] game=  989 | 0-1 | moves=  8 | buf=50,000 | steps=989 | loss=nan (p=nan v=0.5802) | game=5.1s train=145.6s
 [2026-06-12 14:34:05] game=  990 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=990 | loss=nan (p=nan v=0.5979) | game=4.8s train=146.1s
+[2026-06-12 14:36:39] game=  991 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=991 | loss=nan (p=nan v=0.6055) | game=5.5s train=145.8s
+[2026-06-12 14:39:13] game=  992 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=992 | loss=nan (p=nan v=0.6349) | game=4.6s train=149.7s
+[2026-06-12 14:41:47] game=  993 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=993 | loss=nan (p=nan v=0.6016) | game=6.0s train=148.1s
+[2026-06-12 14:44:22] game=  994 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=994 | loss=nan (p=nan v=0.5740) | game=4.7s train=150.5s
+[2026-06-12 14:46:55] game=  995 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=995 | loss=nan (p=nan v=0.5847) | game=4.6s train=147.4s
+[2026-06-12 14:49:28] game=  996 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=996 | loss=nan (p=nan v=0.6134) | game=4.1s train=149.0s
+[2026-06-12 14:52:03] game=  997 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=997 | loss=nan (p=nan v=0.5608) | game=4.5s train=150.8s
+[2026-06-12 14:54:41] game=  998 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=998 | loss=nan (p=nan v=0.5957) | game=4.2s train=153.3s
+[2026-06-12 14:57:23] game=  999 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=999 | loss=nan (p=nan v=0.5644) | game=7.8s train=154.3s
+[2026-06-12 15:00:04] game= 1000 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,000 | loss=nan (p=nan v=0.6013) | game=6.4s train=154.4s