checkpoint @ game=4730 steps=4730

training_log.txt

@@ -5029,3 +5029,13 @@
 [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
+[2026-06-25 08:25:44] game= 4721 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,721 | loss=8.5381 (p=8.4493 v=0.0888) | game=6.0s train=90.0s
+[2026-06-25 08:27:20] game= 4722 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,722 | loss=8.5596 (p=8.4493 v=0.1103) | game=5.5s train=89.9s
+[2026-06-25 08:28:56] game= 4723 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,723 | loss=8.5304 (p=8.4493 v=0.0811) | game=6.5s train=89.7s
+[2026-06-25 08:30:31] game= 4724 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,724 | loss=8.5221 (p=8.4493 v=0.0728) | game=5.2s train=90.0s
+[2026-06-25 08:32:08] game= 4725 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,725 | loss=8.5640 (p=8.4493 v=0.1147) | game=6.9s train=89.8s
+[2026-06-25 08:33:47] game= 4726 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,726 | loss=8.5338 (p=8.4493 v=0.0845) | game=5.9s train=93.2s
+[2026-06-25 08:35:25] game= 4727 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,727 | loss=8.5416 (p=8.4493 v=0.0923) | game=8.2s train=89.9s
+[2026-06-25 08:37:02] game= 4728 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,728 | loss=8.5386 (p=8.4493 v=0.0893) | game=6.4s train=90.1s
+[2026-06-25 08:38:39] game= 4729 | 1/2-1/2 | moves= 74 | buf=50,000 | steps=4,729 | loss=8.5636 (p=8.4493 v=0.1143) | game=7.5s train=90.1s
+[2026-06-25 08:40:16] game= 4730 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,730 | loss=8.5280 (p=8.4493 v=0.0787) | game=6.6s train=90.1s