checkpoint @ game=830 steps=830

training_log.txt

@@ -747,3 +747,13 @@
 [2026-06-12 03:16:54] game=  818 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=818 | loss=nan (p=nan v=0.5447) | game=11.5s train=165.9s
 [2026-06-12 03:19:54] game=  819 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=819 | loss=nan (p=nan v=0.5996) | game=13.1s train=166.5s
 [2026-06-12 11:10:31] game=  820 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=820 | loss=nan (p=nan v=0.5529) | game=6.1s train=13.5s
+[2026-06-12 11:10:50] game=  821 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=821 | loss=nan (p=nan v=0.5508) | game=4.2s train=12.7s
+[2026-06-12 11:11:08] game=  822 | 1/2-1/2 | moves= 62 | buf=50,000 | steps=822 | loss=nan (p=nan v=0.5703) | game=4.8s train=13.0s
+[2026-06-12 11:11:26] game=  823 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=823 | loss=nan (p=nan v=0.5449) | game=4.6s train=13.4s
+[2026-06-12 11:11:46] game=  824 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=824 | loss=nan (p=nan v=0.5608) | game=5.3s train=13.7s
+[2026-06-12 11:12:04] game=  825 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=825 | loss=nan (p=nan v=0.5703) | game=4.2s train=14.1s
+[2026-06-12 11:12:23] game=  826 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=826 | loss=nan (p=nan v=0.5604) | game=4.5s train=14.4s
+[2026-06-12 11:12:45] game=  827 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=827 | loss=nan (p=nan v=0.5468) | game=6.5s train=14.9s
+[2026-06-12 11:13:04] game=  828 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=828 | loss=nan (p=nan v=0.5544) | game=4.2s train=15.2s
+[2026-06-12 11:13:24] game=  829 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=829 | loss=nan (p=nan v=0.5403) | game=3.9s train=15.6s
+[2026-06-12 11:13:44] game=  830 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=830 | loss=nan (p=nan v=0.5839) | game=3.8s train=16.0s