checkpoint @ game=4710 steps=4710

training_log.txt

@@ -5009,3 +5009,13 @@
 [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
+[2026-06-25 07:53:32] game= 4701 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,701 | loss=8.5544 (p=8.4493 v=0.1051) | game=5.3s train=89.6s
+[2026-06-25 07:55:06] game= 4702 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,702 | loss=8.5690 (p=8.4493 v=0.1197) | game=5.1s train=89.5s
+[2026-06-25 07:56:47] game= 4703 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=4,703 | loss=8.5910 (p=8.4493 v=0.1417) | game=7.9s train=92.6s
+[2026-06-25 07:58:22] game= 4704 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,704 | loss=8.5435 (p=8.4493 v=0.0942) | game=5.8s train=89.6s
+[2026-06-25 07:59:57] game= 4705 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,705 | loss=8.5667 (p=8.4493 v=0.1174) | game=4.8s train=89.6s
+[2026-06-25 08:01:32] game= 4706 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,706 | loss=8.5940 (p=8.4493 v=0.1447) | game=5.8s train=89.4s
+[2026-06-25 08:03:08] game= 4707 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,707 | loss=8.5424 (p=8.4493 v=0.0931) | game=6.6s train=89.6s
+[2026-06-25 08:04:46] game= 4708 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,708 | loss=8.5637 (p=8.4493 v=0.1144) | game=5.1s train=92.6s
+[2026-06-25 08:06:21] game= 4709 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,709 | loss=8.5647 (p=8.4493 v=0.1155) | game=5.3s train=89.5s
+[2026-06-25 08:07:57] game= 4710 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,710 | loss=8.5400 (p=8.4493 v=0.0907) | game=6.8s train=89.7s