checkpoint @ game=3720 steps=3720

training_log.txt

@@ -4019,3 +4019,13 @@
 [2026-06-23 02:38:33] game= 3708 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,708 | loss=8.8481 (p=8.4493 v=0.3988) | game=5.8s train=88.2s
 [2026-06-23 02:40:06] game= 3709 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,709 | loss=8.8733 (p=8.4493 v=0.4240) | game=5.8s train=87.4s
 [2026-06-23 02:41:41] game= 3710 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,710 | loss=8.7599 (p=8.4493 v=0.3106) | game=6.3s train=88.6s
+[2026-06-23 02:43:18] game= 3711 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,711 | loss=8.7292 (p=8.4493 v=0.2799) | game=5.5s train=88.0s
+[2026-06-23 02:44:55] game= 3712 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,712 | loss=8.7258 (p=8.4493 v=0.2765) | game=8.6s train=88.8s
+[2026-06-23 02:46:29] game= 3713 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,713 | loss=8.7068 (p=8.4493 v=0.2575) | game=6.1s train=87.5s
+[2026-06-23 02:48:05] game= 3714 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=3,714 | loss=8.7422 (p=8.4493 v=0.2929) | game=7.3s train=88.5s
+[2026-06-23 02:49:37] game= 3715 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,715 | loss=8.7008 (p=8.4493 v=0.2515) | game=5.5s train=87.0s
+[2026-06-23 02:51:11] game= 3716 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,716 | loss=8.6706 (p=8.4493 v=0.2214) | game=5.5s train=87.7s
+[2026-06-23 02:52:48] game= 3717 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,717 | loss=8.6488 (p=8.4493 v=0.1995) | game=9.0s train=88.7s
+[2026-06-23 02:54:23] game= 3718 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,718 | loss=8.6695 (p=8.4493 v=0.2203) | game=6.9s train=88.0s
+[2026-06-23 02:56:00] game= 3719 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,719 | loss=8.6181 (p=8.4493 v=0.1688) | game=7.0s train=89.6s
+[2026-06-23 02:57:33] game= 3720 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,720 | loss=8.6115 (p=8.4493 v=0.1622) | game=5.8s train=87.6s