checkpoint @ game=1830 steps=1830

training_log.txt

@@ -2128,3 +2128,13 @@
 [2026-06-18 17:09:09] game= 1818 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,818 | loss=8.5941 (p=8.4493 v=0.1448) | game=5.0s train=95.8s
 [2026-06-18 17:10:46] game= 1819 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,819 | loss=8.5811 (p=8.4493 v=0.1318) | game=5.4s train=91.1s
 [2026-06-18 17:12:22] game= 1820 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,820 | loss=8.5742 (p=8.4493 v=0.1249) | game=5.2s train=91.6s
+[2026-06-18 17:14:08] game= 1821 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,821 | loss=8.9969 (p=8.4493 v=0.5476) | game=10.7s train=91.9s
+[2026-06-18 17:15:48] game= 1822 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,822 | loss=8.9218 (p=8.4493 v=0.4725) | game=8.8s train=92.0s
+[2026-06-18 17:17:27] game= 1823 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,823 | loss=8.9147 (p=8.4493 v=0.4654) | game=7.5s train=91.2s
+[2026-06-18 17:19:04] game= 1824 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,824 | loss=8.8447 (p=8.4493 v=0.3954) | game=5.7s train=91.0s
+[2026-06-18 17:20:41] game= 1825 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,825 | loss=8.7516 (p=8.4493 v=0.3024) | game=5.6s train=91.9s
+[2026-06-18 17:22:24] game= 1826 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,826 | loss=8.7566 (p=8.4493 v=0.3073) | game=10.5s train=91.8s
+[2026-06-18 17:24:03] game= 1827 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,827 | loss=8.6890 (p=8.4493 v=0.2397) | game=7.5s train=91.3s
+[2026-06-18 17:25:35] game= 1828 | 0-1 | moves= 18 | buf=50,000 | steps=1,828 | loss=8.6817 (p=8.4493 v=0.2324) | game=1.9s train=90.9s
+[2026-06-18 17:27:13] game= 1829 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,829 | loss=8.6853 (p=8.4493 v=0.2360) | game=6.4s train=91.1s
+[2026-06-18 17:28:51] game= 1830 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,830 | loss=8.6566 (p=8.4493 v=0.2073) | game=6.4s train=91.4s