checkpoint @ game=4630 steps=4630

training_log.txt

@@ -4929,3 +4929,13 @@
 [2026-06-25 05:40:12] game= 4618 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,618 | loss=8.6994 (p=8.4493 v=0.2501) | game=5.7s train=88.3s
 [2026-06-25 05:41:50] game= 4619 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,619 | loss=8.6614 (p=8.4493 v=0.2121) | game=8.1s train=90.4s
 [2026-06-25 05:43:23] game= 4620 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,620 | loss=8.6420 (p=8.4493 v=0.1927) | game=4.9s train=88.3s
+[2026-06-25 05:45:05] game= 4621 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,621 | loss=8.6668 (p=8.4493 v=0.2175) | game=4.8s train=88.4s
+[2026-06-25 05:46:39] game= 4622 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,622 | loss=8.6250 (p=8.4493 v=0.1757) | game=5.5s train=88.2s
+[2026-06-25 05:48:15] game= 4623 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,623 | loss=8.6280 (p=8.4493 v=0.1787) | game=7.9s train=88.3s
+[2026-06-25 05:49:50] game= 4624 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,624 | loss=8.5837 (p=8.4493 v=0.1344) | game=6.0s train=88.4s
+[2026-06-25 05:51:23] game= 4625 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,625 | loss=8.6321 (p=8.4493 v=0.1828) | game=5.1s train=88.4s
+[2026-06-25 05:53:00] game= 4626 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,626 | loss=8.5953 (p=8.4493 v=0.1460) | game=8.1s train=88.3s
+[2026-06-25 05:54:37] game= 4627 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,627 | loss=8.5709 (p=8.4493 v=0.1216) | game=5.9s train=91.0s
+[2026-06-25 05:56:13] game= 4628 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,628 | loss=8.6053 (p=8.4493 v=0.1560) | game=8.1s train=88.5s
+[2026-06-25 05:57:48] game= 4629 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,629 | loss=8.5828 (p=8.4493 v=0.1335) | game=6.1s train=88.5s
+[2026-06-25 05:59:22] game= 4630 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,630 | loss=8.5477 (p=8.4493 v=0.0984) | game=5.5s train=88.4s