checkpoint @ game=990 steps=990

training_log.txt

@@ -907,3 +907,13 @@
 [2026-06-12 14:05:19] game=  978 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=978 | loss=nan (p=nan v=0.5118) | game=4.4s train=130.9s
 [2026-06-12 14:07:36] game=  979 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=979 | loss=nan (p=nan v=0.5430) | game=4.1s train=133.1s
 [2026-06-12 14:09:57] game=  980 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=980 | loss=nan (p=nan v=0.5096) | game=4.3s train=136.2s
+[2026-06-12 14:12:19] game=  981 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=981 | loss=nan (p=nan v=0.5900) | game=6.4s train=133.3s
+[2026-06-12 14:14:39] game=  982 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=982 | loss=nan (p=nan v=0.5564) | game=5.3s train=134.7s
+[2026-06-12 14:16:59] game=  983 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=983 | loss=nan (p=nan v=0.5425) | game=4.2s train=136.3s
+[2026-06-12 14:19:20] game=  984 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=984 | loss=nan (p=nan v=0.5188) | game=3.8s train=136.9s
+[2026-06-12 14:21:41] game=  985 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=985 | loss=nan (p=nan v=0.5333) | game=4.1s train=136.1s
+[2026-06-12 14:24:09] game=  986 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=986 | loss=nan (p=nan v=0.5331) | game=4.1s train=144.0s
+[2026-06-12 14:26:37] game=  987 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=987 | loss=nan (p=nan v=0.5199) | game=4.3s train=143.9s
+[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