checkpoint @ game=960 steps=960

training_log.txt

@@ -877,3 +877,13 @@
 [2026-06-13 06:25:44] game=  948 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=948 | loss=nan (p=nan v=0.5780) | game=25.5s train=95.9s
 [2026-06-13 06:27:47] game=  949 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=949 | loss=nan (p=nan v=0.5154) | game=25.3s train=97.3s
 [2026-06-13 06:29:55] game=  950 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=950 | loss=nan (p=nan v=0.5546) | game=25.3s train=102.3s
+[2026-06-13 06:32:03] game=  951 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=951 | loss=nan (p=nan v=0.5723) | game=25.5s train=100.9s
+[2026-06-13 06:34:09] game=  952 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=952 | loss=nan (p=nan v=0.5078) | game=25.7s train=100.4s
+[2026-06-13 06:36:16] game=  953 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=953 | loss=nan (p=nan v=0.5545) | game=25.4s train=101.7s
+[2026-06-13 06:38:25] game=  954 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=954 | loss=nan (p=nan v=0.5231) | game=25.5s train=103.6s
+[2026-06-13 06:40:40] game=  955 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=955 | loss=nan (p=nan v=0.5938) | game=29.0s train=105.0s
+[2026-06-13 06:42:51] game=  956 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=956 | loss=nan (p=nan v=0.5156) | game=25.8s train=105.5s
+[2026-06-13 06:45:03] game=  957 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=957 | loss=nan (p=nan v=0.4929) | game=25.4s train=106.0s
+[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