checkpoint @ game=3760 steps=3760

training_log.txt

@@ -4059,3 +4059,13 @@
 [2026-06-23 03:42:05] game= 3748 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,748 | loss=8.7214 (p=8.4493 v=0.2721) | game=5.8s train=90.7s
 [2026-06-23 03:43:41] game= 3749 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=3,749 | loss=8.6853 (p=8.4493 v=0.2360) | game=6.9s train=89.0s
 [2026-06-23 03:45:15] game= 3750 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,750 | loss=8.6465 (p=8.4493 v=0.1972) | game=5.6s train=87.9s
+[2026-06-23 03:46:54] game= 3751 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,751 | loss=8.6709 (p=8.4493 v=0.2216) | game=5.6s train=88.9s
+[2026-06-23 03:48:28] game= 3752 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,752 | loss=8.6496 (p=8.4493 v=0.2003) | game=5.4s train=88.1s
+[2026-06-23 03:50:02] game= 3753 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,753 | loss=8.6156 (p=8.4493 v=0.1663) | game=5.7s train=88.7s
+[2026-06-23 03:51:38] game= 3754 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,754 | loss=8.6062 (p=8.4493 v=0.1569) | game=6.6s train=88.8s
+[2026-06-23 03:53:14] game= 3755 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,755 | loss=8.6102 (p=8.4493 v=0.1609) | game=6.6s train=89.9s
+[2026-06-23 03:54:50] game= 3756 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,756 | loss=9.0667 (p=8.4493 v=0.6174) | game=8.0s train=88.0s
+[2026-06-23 03:56:25] game= 3757 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=3,757 | loss=9.0649 (p=8.4493 v=0.6156) | game=7.1s train=87.7s
+[2026-06-23 03:57:59] game= 3758 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,758 | loss=8.9562 (p=8.4493 v=0.5069) | game=5.5s train=88.2s
+[2026-06-23 03:59:38] game= 3759 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,759 | loss=8.8934 (p=8.4493 v=0.4441) | game=10.1s train=88.7s
+[2026-06-23 04:01:12] game= 3760 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,760 | loss=8.8079 (p=8.4493 v=0.3586) | game=5.8s train=88.8s