checkpoint @ game=3770 steps=3770

training_log.txt

@@ -4069,3 +4069,13 @@
 [2026-06-23 03:57:59] game= 3758 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,758 | loss=8.9562 (p=8.4493 v=0.5069) | game=5.5s train=88.2s
 [2026-06-23 03:59:38] game= 3759 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,759 | loss=8.8934 (p=8.4493 v=0.4441) | game=10.1s train=88.7s
 [2026-06-23 04:01:12] game= 3760 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,760 | loss=8.8079 (p=8.4493 v=0.3586) | game=5.8s train=88.8s
+[2026-06-23 04:02:51] game= 3761 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,761 | loss=8.7844 (p=8.4493 v=0.3351) | game=5.9s train=89.4s
+[2026-06-23 04:04:30] game= 3762 | 1/2-1/2 | moves= 68 | buf=50,000 | steps=3,762 | loss=8.7506 (p=8.4493 v=0.3013) | game=9.6s train=89.1s
+[2026-06-23 04:06:05] game= 3763 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,763 | loss=8.7217 (p=8.4493 v=0.2724) | game=6.2s train=88.6s
+[2026-06-23 04:07:40] game= 3764 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,764 | loss=8.7186 (p=8.4493 v=0.2693) | game=6.0s train=88.9s
+[2026-06-23 04:09:18] game= 3765 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,765 | loss=8.6588 (p=8.4493 v=0.2095) | game=7.3s train=91.3s
+[2026-06-23 04:10:53] game= 3766 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,766 | loss=8.6761 (p=8.4493 v=0.2268) | game=5.3s train=89.7s
+[2026-06-23 04:12:29] game= 3767 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,767 | loss=8.6646 (p=8.4493 v=0.2153) | game=5.8s train=89.6s
+[2026-06-23 04:14:08] game= 3768 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,768 | loss=8.6747 (p=8.4493 v=0.2254) | game=7.3s train=91.8s
+[2026-06-23 04:15:43] game= 3769 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,769 | loss=8.5873 (p=8.4493 v=0.1380) | game=5.9s train=89.5s
+[2026-06-23 04:17:18] game= 3770 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,770 | loss=8.6320 (p=8.4493 v=0.1827) | game=5.6s train=89.7s