checkpoint @ game=4720 steps=4720

training_log.txt

@@ -5019,3 +5019,13 @@
 [2026-06-25 08:04:46] game= 4708 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,708 | loss=8.5637 (p=8.4493 v=0.1144) | game=5.1s train=92.6s
 [2026-06-25 08:06:21] game= 4709 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,709 | loss=8.5647 (p=8.4493 v=0.1155) | game=5.3s train=89.5s
 [2026-06-25 08:07:57] game= 4710 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,710 | loss=8.5400 (p=8.4493 v=0.0907) | game=6.8s train=89.7s
+[2026-06-25 08:09:37] game= 4711 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,711 | loss=8.5622 (p=8.4493 v=0.1129) | game=5.6s train=89.6s
+[2026-06-25 08:11:12] game= 4712 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,712 | loss=8.5659 (p=8.4493 v=0.1166) | game=5.4s train=89.7s
+[2026-06-25 08:12:49] game= 4713 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,713 | loss=8.5390 (p=8.4493 v=0.0897) | game=8.1s train=89.5s
+[2026-06-25 08:14:28] game= 4714 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,714 | loss=8.5622 (p=8.4493 v=0.1129) | game=5.8s train=93.0s
+[2026-06-25 08:16:03] game= 4715 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,715 | loss=8.5453 (p=8.4493 v=0.0960) | game=5.1s train=90.0s
+[2026-06-25 08:17:38] game= 4716 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,716 | loss=8.5653 (p=8.4493 v=0.1160) | game=5.0s train=89.8s
+[2026-06-25 08:19:13] game= 4717 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,717 | loss=8.5450 (p=8.4493 v=0.0957) | game=4.9s train=89.9s
+[2026-06-25 08:20:49] game= 4718 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,718 | loss=8.5647 (p=8.4493 v=0.1154) | game=5.9s train=89.7s
+[2026-06-25 08:22:26] game= 4719 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,719 | loss=8.5510 (p=8.4493 v=0.1017) | game=7.4s train=89.9s
+[2026-06-25 08:24:05] game= 4720 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,720 | loss=8.5666 (p=8.4493 v=0.1173) | game=5.1s train=93.7s