checkpoint @ game=4740 steps=4740

training_log.txt

@@ -5039,3 +5039,13 @@
 [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
+[2026-06-25 08:42:00] game= 4731 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,731 | loss=8.5355 (p=8.4493 v=0.0862) | game=7.3s train=93.7s
+[2026-06-25 08:43:35] game= 4732 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,732 | loss=8.5356 (p=8.4493 v=0.0863) | game=4.8s train=89.9s
+[2026-06-25 08:45:10] game= 4733 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,733 | loss=8.5618 (p=8.4493 v=0.1125) | game=5.2s train=90.3s
+[2026-06-25 08:46:45] game= 4734 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,734 | loss=8.5345 (p=8.4493 v=0.0852) | game=5.0s train=90.0s
+[2026-06-25 08:48:21] game= 4735 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,735 | loss=8.5601 (p=8.4493 v=0.1108) | game=5.2s train=90.1s
+[2026-06-25 08:49:59] game= 4736 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,736 | loss=8.5490 (p=8.4493 v=0.0997) | game=8.2s train=90.0s
+[2026-06-25 08:51:34] game= 4737 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,737 | loss=8.5294 (p=8.4493 v=0.0801) | game=4.9s train=90.2s
+[2026-06-25 08:53:13] game= 4738 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,738 | loss=8.5229 (p=8.4493 v=0.0736) | game=5.2s train=94.2s
+[2026-06-25 08:54:51] game= 4739 | 1/2-1/2 | moves= 78 | buf=50,000 | steps=4,739 | loss=8.5491 (p=8.4493 v=0.0998) | game=8.0s train=90.1s
+[2026-06-25 08:56:28] game= 4740 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,740 | loss=8.5361 (p=8.4493 v=0.0868) | game=5.8s train=90.3s