checkpoint @ game=4690 steps=4690

training_log.txt

@@ -4989,3 +4989,13 @@
 [2026-06-25 07:16:20] game= 4678 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,678 | loss=8.5789 (p=8.4493 v=0.1296) | game=5.9s train=89.1s
 [2026-06-25 07:17:56] game= 4679 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,679 | loss=8.5487 (p=8.4493 v=0.0994) | game=6.8s train=89.2s
 [2026-06-25 07:19:30] game= 4680 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,680 | loss=8.5552 (p=8.4493 v=0.1059) | game=4.9s train=89.2s
+[2026-06-25 07:21:15] game= 4681 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,681 | loss=8.5618 (p=8.4493 v=0.1125) | game=6.3s train=91.8s
+[2026-06-25 07:22:50] game= 4682 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,682 | loss=8.5422 (p=8.4493 v=0.0929) | game=6.1s train=89.1s
+[2026-06-25 07:24:26] game= 4683 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,683 | loss=8.5647 (p=8.4493 v=0.1154) | game=6.7s train=89.2s
+[2026-06-25 07:26:02] game= 4684 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,684 | loss=8.5593 (p=8.4493 v=0.1100) | game=6.7s train=89.1s
+[2026-06-25 07:27:37] game= 4685 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,685 | loss=8.5726 (p=8.4493 v=0.1233) | game=5.6s train=89.3s
+[2026-06-25 07:29:11] game= 4686 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,686 | loss=8.5717 (p=8.4493 v=0.1224) | game=4.9s train=89.4s
+[2026-06-25 07:30:49] game= 4687 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,687 | loss=8.5620 (p=8.4493 v=0.1127) | game=6.1s train=92.2s
+[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