checkpoint @ game=900 steps=900

training_log.txt

@@ -817,3 +817,13 @@
 [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
+[2026-06-13 04:56:39] game=  891 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=891 | loss=nan (p=nan v=0.5311) | game=32.7s train=41.1s
+[2026-06-13 04:57:46] game=  892 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=892 | loss=nan (p=nan v=0.6317) | game=24.7s train=42.1s
+[2026-06-13 04:58:55] game=  893 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=893 | loss=nan (p=nan v=0.6546) | game=24.5s train=44.7s
+[2026-06-13 05:00:03] game=  894 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=894 | loss=nan (p=nan v=0.6487) | game=24.9s train=43.3s
+[2026-06-13 05:01:12] game=  895 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=895 | loss=nan (p=nan v=0.6651) | game=24.5s train=44.0s
+[2026-06-13 05:02:24] game=  896 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=896 | loss=nan (p=nan v=0.6173) | game=24.5s train=46.8s
+[2026-06-13 05:03:35] game=  897 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=897 | loss=nan (p=nan v=0.6407) | game=24.9s train=46.0s
+[2026-06-13 05:04:46] game=  898 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=898 | loss=nan (p=nan v=0.5234) | game=24.6s train=46.5s
+[2026-06-13 05:05:45] game=  899 | 1-0 | moves= 33 | buf=50,000 | steps=899 | loss=nan (p=nan v=0.5938) | game=10.1s train=49.5s
+[2026-06-13 05:06:58] game=  900 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=900 | loss=nan (p=nan v=0.6173) | game=24.8s train=47.9s