checkpoint @ game=1700 steps=1700

training_log.txt

@@ -1998,3 +1998,13 @@
 [2026-06-18 13:38:55] game= 1688 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=1,688 | loss=8.8520 (p=8.4493 v=0.4027) | game=4.7s train=88.3s
 [2026-06-18 13:40:32] game= 1689 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,689 | loss=8.8302 (p=8.4493 v=0.3809) | game=5.8s train=91.4s
 [2026-06-18 13:42:06] game= 1690 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,690 | loss=8.7636 (p=8.4493 v=0.3143) | game=5.2s train=88.3s
+[2026-06-18 13:43:42] game= 1691 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,691 | loss=8.7234 (p=8.4493 v=0.2741) | game=5.0s train=88.4s
+[2026-06-18 13:45:16] game= 1692 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,692 | loss=8.7220 (p=8.4493 v=0.2727) | game=5.4s train=88.2s
+[2026-06-18 13:46:52] game= 1693 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,693 | loss=8.7098 (p=8.4493 v=0.2605) | game=8.2s train=88.2s
+[2026-06-18 13:48:27] game= 1694 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,694 | loss=8.6800 (p=8.4493 v=0.2307) | game=6.0s train=88.3s
+[2026-06-18 13:50:02] game= 1695 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,695 | loss=8.6574 (p=8.4493 v=0.2081) | game=5.3s train=90.1s
+[2026-06-18 13:51:37] game= 1696 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,696 | loss=8.6262 (p=8.4493 v=0.1769) | game=5.7s train=88.8s
+[2026-06-18 13:53:12] game= 1697 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,697 | loss=8.6207 (p=8.4493 v=0.1714) | game=6.4s train=88.6s
+[2026-06-18 13:54:45] game= 1698 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,698 | loss=8.6175 (p=8.4493 v=0.1682) | game=5.2s train=88.5s
+[2026-06-18 13:56:19] game= 1699 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,699 | loss=8.6088 (p=8.4493 v=0.1595) | game=5.3s train=88.3s
+[2026-06-18 13:57:54] game= 1700 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,700 | loss=8.5946 (p=8.4493 v=0.1453) | game=6.6s train=88.4s