checkpoint @ game=890 steps=890

training_log.txt

@@ -807,3 +807,13 @@
 [2026-06-12 11:38:49] game=  878 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=878 | loss=nan (p=nan v=0.5254) | game=4.1s train=36.6s
 [2026-06-12 11:39:33] game=  879 | 1/2-1/2 | moves= 70 | buf=50,000 | steps=879 | loss=nan (p=nan v=0.5775) | game=5.4s train=38.1s
 [2026-06-12 11:40:15] game=  880 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=880 | loss=nan (p=nan v=0.4665) | game=3.9s train=37.6s
+[2026-06-12 11:40:58] game=  881 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=881 | loss=nan (p=nan v=0.4937) | game=4.0s train=38.1s
+[2026-06-12 11:41:43] game=  882 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=882 | loss=nan (p=nan v=0.4961) | game=4.3s train=39.7s
+[2026-06-12 11:42:29] game=  883 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=883 | loss=nan (p=nan v=0.5625) | game=6.3s train=39.8s
+[2026-06-12 11:43:16] game=  884 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=884 | loss=nan (p=nan v=0.5527) | game=5.0s train=41.7s
+[2026-06-12 11:44:03] game=  885 | 1/2-1/2 | moves= 76 | buf=50,000 | steps=885 | loss=nan (p=nan v=0.5078) | game=5.9s train=41.0s
+[2026-06-12 11:44:50] game=  886 | 1/2-1/2 | moves= 68 | buf=50,000 | steps=886 | loss=nan (p=nan v=0.5192) | game=5.3s train=41.5s
+[2026-06-12 11:45:43] game=  887 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=887 | loss=nan (p=nan v=0.6428) | game=9.7s train=43.7s
+[2026-06-12 11:46:30] game=  888 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=888 | loss=nan (p=nan v=0.6581) | game=3.7s train=43.3s
+[2026-06-12 11:47:19] game=  889 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=889 | loss=nan (p=nan v=0.6800) | game=4.3s train=44.2s
+[2026-06-12 11:48:10] game=  890 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=890 | loss=nan (p=nan v=0.6699) | game=5.0s train=45.9s