checkpoint @ game=890 steps=890

training_log.txt

@@ -807,3 +807,13 @@
 [2026-06-13 04:42:51] game=  878 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=878 | loss=nan (p=nan v=0.5469) | game=24.3s train=35.2s
 [2026-06-13 04:43:50] game=  879 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=879 | loss=nan (p=nan v=0.6009) | game=24.7s train=34.1s
 [2026-06-13 04:44:51] game=  880 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=880 | loss=nan (p=nan v=0.4455) | game=24.2s train=36.0s
+[2026-06-13 04:45:52] game=  881 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=881 | loss=nan (p=nan v=0.5548) | game=24.4s train=35.1s
+[2026-06-13 04:46:54] game=  882 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=882 | loss=nan (p=nan v=0.5866) | game=24.3s train=37.4s
+[2026-06-13 04:47:54] game=  883 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=883 | loss=nan (p=nan v=0.5073) | game=24.4s train=36.2s
+[2026-06-13 04:48:57] game=  884 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=884 | loss=nan (p=nan v=0.4775) | game=24.3s train=38.6s
+[2026-06-13 04:49:59] game=  885 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=885 | loss=nan (p=nan v=0.5861) | game=24.5s train=37.5s
+[2026-06-13 04:51:02] game=  886 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=886 | loss=nan (p=nan v=0.4297) | game=24.4s train=38.1s
+[2026-06-13 04:52:07] game=  887 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=887 | loss=nan (p=nan v=0.5779) | game=26.2s train=38.9s
+[2026-06-13 04:53:11] game=  888 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=888 | loss=nan (p=nan v=0.4687) | game=24.4s train=39.4s
+[2026-06-13 04:54:17] game=  889 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=889 | loss=nan (p=nan v=0.4453) | game=26.2s train=39.8s
+[2026-06-13 04:55:23] game=  890 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=890 | loss=nan (p=nan v=0.5086) | game=24.5s train=40.7s