checkpoint @ game=3830 steps=3830

training_log.txt

@@ -4129,3 +4129,13 @@
 [2026-06-23 05:34:51] game= 3818 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,818 | loss=8.6385 (p=8.4493 v=0.1892) | game=8.3s train=89.7s
 [2026-06-23 05:36:27] game= 3819 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,819 | loss=8.6434 (p=8.4493 v=0.1941) | game=6.1s train=89.7s
 [2026-06-23 05:38:03] game= 3820 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,820 | loss=8.6114 (p=8.4493 v=0.1621) | game=5.5s train=90.3s
+[2026-06-23 05:39:43] game= 3821 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,821 | loss=8.6124 (p=8.4493 v=0.1631) | game=7.1s train=90.7s
+[2026-06-23 05:41:22] game= 3822 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,822 | loss=8.6505 (p=8.4493 v=0.2012) | game=8.8s train=89.5s
+[2026-06-23 05:43:04] game= 3823 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=3,823 | loss=8.6577 (p=8.4493 v=0.2084) | game=11.2s train=91.6s
+[2026-06-23 05:44:46] game= 3824 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=3,824 | loss=9.1685 (p=8.4493 v=0.7192) | game=9.8s train=91.6s
+[2026-06-23 05:46:26] game= 3825 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=3,825 | loss=9.0764 (p=8.4493 v=0.6271) | game=8.7s train=91.0s
+[2026-06-23 05:48:07] game= 3826 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,826 | loss=8.9871 (p=8.4493 v=0.5378) | game=8.3s train=93.5s
+[2026-06-23 05:49:47] game= 3827 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=3,827 | loss=8.8342 (p=8.4493 v=0.3849) | game=8.8s train=90.6s
+[2026-06-23 05:51:23] game= 3828 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,828 | loss=8.8045 (p=8.4493 v=0.3552) | game=6.6s train=89.8s
+[2026-06-23 05:52:59] game= 3829 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,829 | loss=8.7778 (p=8.4493 v=0.3285) | game=5.5s train=90.5s
+[2026-06-23 05:54:35] game= 3830 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,830 | loss=8.7572 (p=8.4493 v=0.3079) | game=5.7s train=90.6s