checkpoint @ game=980 steps=980

training_log.txt

@@ -897,3 +897,13 @@
 [2026-06-13 07:10:47] game=  968 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=968 | loss=nan (p=nan v=0.5312) | game=29.4s train=118.5s
 [2026-06-13 07:13:13] game=  969 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=969 | loss=nan (p=nan v=0.5308) | game=25.7s train=119.7s
 [2026-06-13 07:15:39] game=  970 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=970 | loss=nan (p=nan v=0.4377) | game=25.7s train=120.6s
+[2026-06-13 07:18:07] game=  971 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=971 | loss=nan (p=nan v=0.5937) | game=25.7s train=120.1s
+[2026-06-13 07:20:34] game=  972 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=972 | loss=nan (p=nan v=0.4919) | game=25.8s train=121.2s
+[2026-06-13 07:23:07] game=  973 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=973 | loss=nan (p=nan v=0.6021) | game=29.6s train=122.8s
+[2026-06-13 07:25:37] game=  974 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=974 | loss=nan (p=nan v=0.5232) | game=25.6s train=124.4s
+[2026-06-13 07:28:09] game=  975 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=975 | loss=nan (p=nan v=0.4611) | game=25.7s train=126.5s
+[2026-06-13 07:30:42] game=  976 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=976 | loss=nan (p=nan v=0.5654) | game=25.8s train=126.6s
+[2026-06-13 07:33:15] game=  977 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=977 | loss=nan (p=nan v=0.5471) | game=25.8s train=127.7s
+[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