checkpoint @ game=3740 steps=3740

training_log.txt

@@ -4039,3 +4039,13 @@
 [2026-06-23 03:10:14] game= 3728 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,728 | loss=8.8439 (p=8.4493 v=0.3946) | game=5.7s train=87.4s
 [2026-06-23 03:11:49] game= 3729 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,729 | loss=8.6882 (p=8.4493 v=0.2389) | game=6.0s train=88.4s
 [2026-06-23 03:13:25] game= 3730 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,730 | loss=8.7169 (p=8.4493 v=0.2676) | game=5.8s train=90.1s
+[2026-06-23 03:15:02] game= 3731 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,731 | loss=8.6783 (p=8.4493 v=0.2290) | game=5.7s train=88.4s
+[2026-06-23 03:16:38] game= 3732 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,732 | loss=8.6589 (p=8.4493 v=0.2096) | game=5.8s train=89.6s
+[2026-06-23 03:18:12] game= 3733 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=3,733 | loss=8.6742 (p=8.4493 v=0.2249) | game=5.2s train=89.0s
+[2026-06-23 03:19:46] game= 3734 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,734 | loss=8.6609 (p=8.4493 v=0.2116) | game=5.4s train=88.7s
+[2026-06-23 03:21:23] game= 3735 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=3,735 | loss=8.6438 (p=8.4493 v=0.1945) | game=6.8s train=90.2s
+[2026-06-23 03:22:59] game= 3736 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=3,736 | loss=8.6567 (p=8.4493 v=0.2074) | game=7.3s train=88.2s
+[2026-06-23 03:24:35] game= 3737 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,737 | loss=8.6000 (p=8.4493 v=0.1507) | game=5.7s train=90.3s
+[2026-06-23 03:26:09] game= 3738 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,738 | loss=8.6515 (p=8.4493 v=0.2022) | game=6.5s train=88.3s
+[2026-06-23 03:27:47] game= 3739 | 1/2-1/2 | moves= 70 | buf=50,000 | steps=3,739 | loss=9.1536 (p=8.4493 v=0.7043) | game=10.6s train=87.4s
+[2026-06-23 03:29:21] game= 3740 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,740 | loss=9.0584 (p=8.4493 v=0.6091) | game=5.2s train=87.9s