checkpoint @ game=970 steps=970

training_log.txt

@@ -887,3 +887,13 @@
 [2026-06-13 06:47:16] game=  958 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=958 | loss=nan (p=nan v=0.5164) | game=25.5s train=108.0s
 [2026-06-13 06:49:34] game=  959 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=959 | loss=nan (p=nan v=0.5624) | game=29.1s train=108.5s
 [2026-06-13 06:51:49] game=  960 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=960 | loss=nan (p=nan v=0.5156) | game=25.9s train=109.2s
+[2026-06-13 06:54:07] game=  961 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=961 | loss=nan (p=nan v=0.5630) | game=25.6s train=110.7s
+[2026-06-13 06:56:24] game=  962 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=962 | loss=nan (p=nan v=0.5235) | game=25.6s train=111.7s
+[2026-06-13 06:58:53] game=  963 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=963 | loss=nan (p=nan v=0.5625) | game=35.7s train=112.5s
+[2026-06-13 07:01:13] game=  964 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=964 | loss=nan (p=nan v=0.5621) | game=25.6s train=114.3s
+[2026-06-13 07:03:34] game=  965 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=965 | loss=nan (p=nan v=0.5378) | game=25.6s train=115.5s
+[2026-06-13 07:05:56] game=  966 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=966 | loss=nan (p=nan v=0.5635) | game=25.7s train=116.6s
+[2026-06-13 07:08:19] game=  967 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=967 | loss=nan (p=nan v=0.5156) | game=25.5s train=117.4s
+[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