checkpoint @ game=1850 steps=1850

training_log.txt

@@ -2148,3 +2148,13 @@
 [2026-06-18 17:42:04] game= 1838 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,838 | loss=8.9235 (p=8.4493 v=0.4742) | game=10.4s train=91.4s
 [2026-06-18 17:43:40] game= 1839 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,839 | loss=8.8817 (p=8.4493 v=0.4324) | game=5.6s train=90.7s
 [2026-06-18 17:45:16] game= 1840 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,840 | loss=8.8595 (p=8.4493 v=0.4102) | game=5.2s train=91.0s
+[2026-06-18 17:46:56] game= 1841 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=1,841 | loss=8.8032 (p=8.4493 v=0.3539) | game=6.6s train=90.8s
+[2026-06-18 17:48:33] game= 1842 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,842 | loss=8.7534 (p=8.4493 v=0.3041) | game=6.3s train=90.7s
+[2026-06-18 17:50:17] game= 1843 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,843 | loss=8.7281 (p=8.4493 v=0.2788) | game=12.2s train=91.6s
+[2026-06-18 17:51:56] game= 1844 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,844 | loss=8.6808 (p=8.4493 v=0.2315) | game=7.3s train=91.5s
+[2026-06-18 17:53:34] game= 1845 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,845 | loss=8.6860 (p=8.4493 v=0.2367) | game=6.5s train=91.2s
+[2026-06-18 17:55:10] game= 1846 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=1,846 | loss=8.6317 (p=8.4493 v=0.1824) | game=4.8s train=91.5s
+[2026-06-18 17:56:49] game= 1847 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=1,847 | loss=8.6374 (p=8.4493 v=0.1881) | game=7.7s train=91.5s
+[2026-06-18 17:58:26] game= 1848 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,848 | loss=8.6507 (p=8.4493 v=0.2014) | game=5.6s train=90.9s
+[2026-06-18 18:00:02] game= 1849 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,849 | loss=8.6096 (p=8.4493 v=0.1603) | game=4.8s train=91.4s
+[2026-06-18 18:01:40] game= 1850 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,850 | loss=8.5892 (p=8.4493 v=0.1399) | game=6.8s train=91.0s