checkpoint @ game=4670 steps=4670

training_log.txt

@@ -4969,3 +4969,13 @@
 [2026-06-25 06:44:07] game= 4658 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,658 | loss=8.5664 (p=8.4493 v=0.1171) | game=5.7s train=88.8s
 [2026-06-25 06:45:44] game= 4659 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,659 | loss=8.5731 (p=8.4493 v=0.1238) | game=5.1s train=91.9s
 [2026-06-25 06:47:18] game= 4660 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,660 | loss=8.5577 (p=8.4493 v=0.1084) | game=5.1s train=88.8s
+[2026-06-25 06:48:56] game= 4661 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,661 | loss=8.5677 (p=8.4493 v=0.1184) | game=5.0s train=88.9s
+[2026-06-25 06:50:31] game= 4662 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,662 | loss=8.5792 (p=8.4493 v=0.1299) | game=6.5s train=89.0s
+[2026-06-25 06:52:06] game= 4663 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,663 | loss=8.5603 (p=8.4493 v=0.1110) | game=5.9s train=88.7s
+[2026-06-25 06:53:46] game= 4664 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,664 | loss=8.5804 (p=8.4493 v=0.1311) | game=11.2s train=88.9s
+[2026-06-25 06:55:20] game= 4665 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,665 | loss=8.5543 (p=8.4493 v=0.1050) | game=5.1s train=89.0s
+[2026-06-25 06:56:54] game= 4666 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,666 | loss=8.5549 (p=8.4493 v=0.1056) | game=5.3s train=88.9s
+[2026-06-25 06:58:29] game= 4667 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,667 | loss=8.5630 (p=8.4493 v=0.1137) | game=5.5s train=89.0s
+[2026-06-25 07:00:06] game= 4668 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,668 | loss=8.5517 (p=8.4493 v=0.1024) | game=5.6s train=91.7s
+[2026-06-25 07:01:40] game= 4669 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=4,669 | loss=8.5707 (p=8.4493 v=0.1214) | game=4.6s train=89.1s
+[2026-06-25 07:03:17] game= 4670 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,670 | loss=8.5711 (p=8.4493 v=0.1218) | game=8.2s train=89.1s