checkpoint @ game=1870 steps=1870

training_log.txt

@@ -2168,3 +2168,13 @@
 [2026-06-18 18:14:55] game= 1858 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,858 | loss=8.8333 (p=8.4493 v=0.3840) | game=5.1s train=91.9s
 [2026-06-18 18:16:32] game= 1859 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,859 | loss=8.8122 (p=8.4493 v=0.3629) | game=5.6s train=91.9s
 [2026-06-18 18:18:15] game= 1860 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,860 | loss=8.7577 (p=8.4493 v=0.3084) | game=5.4s train=97.2s
+[2026-06-18 18:19:58] game= 1861 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,861 | loss=8.6991 (p=8.4493 v=0.2498) | game=8.4s train=91.7s
+[2026-06-18 18:21:35] game= 1862 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,862 | loss=8.6741 (p=8.4493 v=0.2248) | game=5.0s train=92.2s
+[2026-06-18 18:23:13] game= 1863 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,863 | loss=8.7113 (p=8.4493 v=0.2620) | game=5.4s train=92.0s
+[2026-06-18 18:24:53] game= 1864 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,864 | loss=8.6366 (p=8.4493 v=0.1873) | game=8.4s train=92.1s
+[2026-06-18 18:26:32] game= 1865 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=1,865 | loss=8.6350 (p=8.4493 v=0.1857) | game=6.8s train=91.9s
+[2026-06-18 18:28:12] game= 1866 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,866 | loss=8.6168 (p=8.4493 v=0.1675) | game=8.3s train=91.7s
+[2026-06-18 18:29:50] game= 1867 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,867 | loss=8.6283 (p=8.4493 v=0.1790) | game=6.1s train=91.7s
+[2026-06-18 18:31:27] game= 1868 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,868 | loss=8.6254 (p=8.4493 v=0.1761) | game=5.5s train=91.6s
+[2026-06-18 18:33:07] game= 1869 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,869 | loss=8.6234 (p=8.4493 v=0.1741) | game=8.3s train=92.0s
+[2026-06-18 18:34:51] game= 1870 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=1,870 | loss=8.5981 (p=8.4493 v=0.1488) | game=12.0s train=92.2s