checkpoint @ game=870 steps=870

training_log.txt

@@ -787,3 +787,13 @@
 [2026-06-13 04:24:59] game=  858 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=858 | loss=nan (p=nan v=0.5465) | game=23.9s train=25.0s
 [2026-06-13 04:25:47] game=  859 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=859 | loss=nan (p=nan v=0.5235) | game=23.9s train=24.4s
 [2026-06-13 04:26:38] game=  860 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=860 | loss=nan (p=nan v=0.5001) | game=25.0s train=24.9s
+[2026-06-13 04:27:30] game=  861 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=861 | loss=nan (p=nan v=0.5231) | game=24.0s train=26.5s
+[2026-06-13 04:28:20] game=  862 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=862 | loss=nan (p=nan v=0.6403) | game=24.0s train=25.7s
+[2026-06-13 04:29:11] game=  863 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=863 | loss=nan (p=nan v=0.5080) | game=25.2s train=26.2s
+[2026-06-13 04:30:03] game=  864 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=864 | loss=nan (p=nan v=0.5152) | game=24.0s train=27.8s
+[2026-06-13 04:30:55] game=  865 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=865 | loss=nan (p=nan v=0.5853) | game=24.3s train=27.3s
+[2026-06-13 04:31:48] game=  866 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=866 | loss=nan (p=nan v=0.6011) | game=24.0s train=28.8s
+[2026-06-13 04:32:46] game=  867 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=867 | loss=nan (p=nan v=0.5077) | game=30.5s train=27.8s
+[2026-06-13 04:33:40] game=  868 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=868 | loss=nan (p=nan v=0.5627) | game=25.4s train=28.2s
+[2026-06-13 04:34:34] game=  869 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=869 | loss=nan (p=nan v=0.5622) | game=24.0s train=30.3s
+[2026-06-13 04:35:28] game=  870 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=870 | loss=nan (p=nan v=0.5156) | game=24.2s train=29.4s