checkpoint @ game=1720 steps=1720

training_log.txt

@@ -2018,3 +2018,13 @@
 [2026-06-18 14:10:44] game= 1708 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,708 | loss=8.6712 (p=8.4493 v=0.2219) | game=5.4s train=88.6s
 [2026-06-18 14:12:18] game= 1709 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,709 | loss=8.6632 (p=8.4493 v=0.2139) | game=5.4s train=88.8s
 [2026-06-18 14:13:53] game= 1710 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,710 | loss=8.6529 (p=8.4493 v=0.2036) | game=5.4s train=88.6s
+[2026-06-18 14:15:29] game= 1711 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,711 | loss=8.6149 (p=8.4493 v=0.1656) | game=4.9s train=88.6s
+[2026-06-18 14:17:07] game= 1712 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,712 | loss=8.6440 (p=8.4493 v=0.1947) | game=5.2s train=92.3s
+[2026-06-18 14:18:41] game= 1713 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,713 | loss=8.6224 (p=8.4493 v=0.1731) | game=5.3s train=89.0s
+[2026-06-18 14:20:16] game= 1714 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,714 | loss=8.6215 (p=8.4493 v=0.1722) | game=5.8s train=88.8s
+[2026-06-18 14:21:50] game= 1715 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,715 | loss=8.5921 (p=8.4493 v=0.1428) | game=5.6s train=88.9s
+[2026-06-18 14:23:27] game= 1716 | 1/2-1/2 | moves= 76 | buf=50,000 | steps=1,716 | loss=8.5888 (p=8.4493 v=0.1395) | game=7.7s train=88.9s
+[2026-06-18 14:25:01] game= 1717 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,717 | loss=8.6122 (p=8.4493 v=0.1629) | game=5.5s train=88.6s
+[2026-06-18 14:26:39] game= 1718 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,718 | loss=8.5807 (p=8.4493 v=0.1314) | game=6.2s train=92.2s
+[2026-06-18 14:28:18] game= 1719 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,719 | loss=8.9930 (p=8.4493 v=0.5437) | game=9.9s train=89.0s
+[2026-06-18 14:29:52] game= 1720 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,720 | loss=8.9361 (p=8.4493 v=0.4868) | game=5.2s train=88.7s