checkpoint @ game=1010 steps=1010

training_log.txt

@@ -927,3 +927,13 @@
 [2026-06-12 14:54:41] game=  998 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=998 | loss=nan (p=nan v=0.5957) | game=4.2s train=153.3s
 [2026-06-12 14:57:23] game=  999 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=999 | loss=nan (p=nan v=0.5644) | game=7.8s train=154.3s
 [2026-06-12 15:00:04] game= 1000 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,000 | loss=nan (p=nan v=0.6013) | game=6.4s train=154.4s
+[2026-06-12 15:02:48] game= 1001 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=1,001 | loss=nan (p=nan v=0.6112) | game=5.5s train=155.9s
+[2026-06-12 15:05:31] game= 1002 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=1,002 | loss=nan (p=nan v=0.5935) | game=5.3s train=157.6s
+[2026-06-12 15:08:14] game= 1003 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,003 | loss=nan (p=nan v=0.5783) | game=6.5s train=157.1s
+[2026-06-12 15:10:57] game= 1004 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,004 | loss=nan (p=nan v=0.5893) | game=4.1s train=158.1s
+[2026-06-12 15:13:44] game= 1005 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,005 | loss=nan (p=nan v=0.5898) | game=5.8s train=161.4s
+[2026-06-12 15:16:32] game= 1006 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,006 | loss=nan (p=nan v=0.5781) | game=8.2s train=159.8s
+[2026-06-12 15:19:15] game= 1007 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=1,007 | loss=nan (p=nan v=0.5781) | game=3.7s train=159.0s
+[2026-06-12 15:22:03] game= 1008 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,008 | loss=nan (p=nan v=0.5933) | game=4.5s train=163.9s
+[2026-06-12 15:24:52] game= 1009 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,009 | loss=nan (p=nan v=0.6124) | game=3.7s train=165.4s
+[2026-06-12 15:27:44] game= 1010 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,010 | loss=nan (p=nan v=0.6296) | game=4.0s train=167.6s