checkpoint @ game=1820 steps=1820

training_log.txt

@@ -2118,3 +2118,13 @@
 [2026-06-18 16:52:42] game= 1808 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=1,808 | loss=8.8013 (p=8.4493 v=0.3520) | game=8.2s train=91.0s
 [2026-06-18 16:54:24] game= 1809 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,809 | loss=8.7755 (p=8.4493 v=0.3262) | game=6.4s train=95.5s
 [2026-06-18 16:56:03] game= 1810 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=1,810 | loss=8.7051 (p=8.4493 v=0.2559) | game=7.7s train=91.1s
+[2026-06-18 16:57:43] game= 1811 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,811 | loss=8.7028 (p=8.4493 v=0.2535) | game=6.1s train=91.1s
+[2026-06-18 16:59:20] game= 1812 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,812 | loss=8.6868 (p=8.4493 v=0.2375) | game=5.4s train=90.8s
+[2026-06-18 17:00:59] game= 1813 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,813 | loss=8.6754 (p=8.4493 v=0.2261) | game=7.6s train=91.6s
+[2026-06-18 17:02:35] game= 1814 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,814 | loss=8.6230 (p=8.4493 v=0.1737) | game=5.2s train=91.0s
+[2026-06-18 17:04:12] game= 1815 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,815 | loss=8.6100 (p=8.4493 v=0.1607) | game=5.6s train=91.0s
+[2026-06-18 17:05:48] game= 1816 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,816 | loss=8.6165 (p=8.4493 v=0.1672) | game=5.7s train=90.8s
+[2026-06-18 17:07:28] game= 1817 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,817 | loss=8.6078 (p=8.4493 v=0.1585) | game=8.8s train=91.3s
+[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