checkpoint @ game=4700 steps=4700

training_log.txt

@@ -4999,3 +4999,13 @@
 [2026-06-25 07:32:24] game= 4688 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,688 | loss=8.5312 (p=8.4493 v=0.0819) | game=5.2s train=89.5s
 [2026-06-25 07:33:58] game= 4689 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,689 | loss=8.5782 (p=8.4493 v=0.1289) | game=5.1s train=89.2s
 [2026-06-25 07:35:34] game= 4690 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,690 | loss=8.5711 (p=8.4493 v=0.1218) | game=6.1s train=89.3s
+[2026-06-25 07:37:13] game= 4691 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,691 | loss=8.5455 (p=8.4493 v=0.0962) | game=5.5s train=89.3s
+[2026-06-25 07:38:51] game= 4692 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,692 | loss=8.5698 (p=8.4493 v=0.1205) | game=5.3s train=92.8s
+[2026-06-25 07:40:25] game= 4693 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,693 | loss=8.5488 (p=8.4493 v=0.0995) | game=5.0s train=89.4s
+[2026-06-25 07:42:01] game= 4694 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,694 | loss=8.5713 (p=8.4493 v=0.1220) | game=6.2s train=89.5s
+[2026-06-25 07:43:36] game= 4695 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,695 | loss=8.5784 (p=8.4493 v=0.1291) | game=5.8s train=89.4s
+[2026-06-25 07:45:14] game= 4696 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,696 | loss=8.5517 (p=8.4493 v=0.1024) | game=8.1s train=89.3s
+[2026-06-25 07:46:49] game= 4697 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,697 | loss=8.5635 (p=8.4493 v=0.1142) | game=5.8s train=89.5s
+[2026-06-25 07:48:26] game= 4698 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=4,698 | loss=8.5573 (p=8.4493 v=0.1080) | game=4.6s train=93.0s
+[2026-06-25 07:50:02] game= 4699 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,699 | loss=8.5806 (p=8.4493 v=0.1313) | game=5.6s train=89.6s
+[2026-06-25 07:51:37] game= 4700 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,700 | loss=8.5362 (p=8.4493 v=0.0869) | game=5.5s train=89.4s