checkpoint @ game=980 steps=980

training_log.txt

@@ -897,3 +897,13 @@
 [2026-06-12 13:43:03] game=  968 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=968 | loss=nan (p=nan v=0.5704) | game=4.1s train=124.3s
 [2026-06-12 13:45:11] game=  969 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=969 | loss=nan (p=nan v=0.5629) | game=3.9s train=124.3s
 [2026-06-12 13:47:20] game=  970 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=970 | loss=nan (p=nan v=0.5858) | game=3.9s train=124.4s
+[2026-06-12 13:49:32] game=  971 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=971 | loss=nan (p=nan v=0.5840) | game=4.4s train=126.5s
+[2026-06-12 13:51:47] game=  972 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=972 | loss=nan (p=nan v=0.5733) | game=8.1s train=126.6s
+[2026-06-12 13:53:58] game=  973 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=973 | loss=nan (p=nan v=0.5553) | game=4.3s train=126.5s
+[2026-06-12 13:56:16] game=  974 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=974 | loss=nan (p=nan v=0.5391) | game=6.4s train=131.6s
+[2026-06-12 13:58:31] game=  975 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=975 | loss=nan (p=nan v=0.5179) | game=4.2s train=130.3s
+[2026-06-12 14:00:47] game=  976 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=976 | loss=nan (p=nan v=0.5665) | game=4.1s train=132.2s
+[2026-06-12 14:03:04] game=  977 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=977 | loss=nan (p=nan v=0.5197) | game=5.0s train=131.3s
+[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