checkpoint @ game=3630 steps=3630

training_log.txt

@@ -3929,3 +3929,13 @@
 [2026-06-22 13:51:08] game= 3618 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,618 | loss=8.6523 (p=8.4493 v=0.2030) | game=6.5s train=88.5s
 [2026-06-22 13:52:43] game= 3619 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=3,619 | loss=8.6309 (p=8.4493 v=0.1816) | game=6.6s train=88.3s
 [2026-06-22 13:54:21] game= 3620 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,620 | loss=8.5982 (p=8.4493 v=0.1489) | game=9.2s train=88.4s
+[2026-06-23 00:22:36] game= 3621 | 1/2-1/2 | moves= 81 | buf=34,482 | steps=3,621 | loss=9.2978 (p=8.4493 v=0.8485) | game=9.6s train=98.2s
+[2026-06-23 00:24:08] game= 3622 | 1/2-1/2 | moves= 55 | buf=34,537 | steps=3,622 | loss=9.1793 (p=8.4493 v=0.7300) | game=5.9s train=86.0s
+[2026-06-23 00:25:40] game= 3623 | 1/2-1/2 | moves= 51 | buf=34,588 | steps=3,623 | loss=9.0452 (p=8.4493 v=0.5959) | game=5.5s train=86.1s
+[2026-06-23 00:27:11] game= 3624 | 1/2-1/2 | moves= 55 | buf=34,643 | steps=3,624 | loss=8.8950 (p=8.4493 v=0.4457) | game=6.0s train=85.9s
+[2026-06-23 00:28:45] game= 3625 | 1/2-1/2 | moves= 62 | buf=34,705 | steps=3,625 | loss=8.7589 (p=8.4493 v=0.3096) | game=6.5s train=86.8s
+[2026-06-23 00:30:19] game= 3626 | 1/2-1/2 | moves= 81 | buf=34,786 | steps=3,626 | loss=8.7012 (p=8.4493 v=0.2519) | game=8.2s train=85.9s
+[2026-06-23 00:31:53] game= 3627 | 1/2-1/2 | moves= 73 | buf=34,859 | steps=3,627 | loss=8.7765 (p=8.4493 v=0.3272) | game=7.6s train=86.2s
+[2026-06-23 00:33:25] game= 3628 | 1/2-1/2 | moves= 62 | buf=34,921 | steps=3,628 | loss=8.7350 (p=8.4493 v=0.2857) | game=6.4s train=85.8s
+[2026-06-23 00:34:57] game= 3629 | 1/2-1/2 | moves= 53 | buf=34,974 | steps=3,629 | loss=8.7020 (p=8.4493 v=0.2528) | game=5.7s train=86.1s
+[2026-06-23 00:36:29] game= 3630 | 1/2-1/2 | moves= 60 | buf=35,034 | steps=3,630 | loss=8.6581 (p=8.4493 v=0.2088) | game=6.0s train=86.5s