checkpoint @ game=3920 steps=3920

training_log.txt

@@ -4219,3 +4219,13 @@
 [2026-06-23 08:03:40] game= 3908 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,908 | loss=8.6339 (p=8.4493 v=0.1846) | game=5.5s train=97.5s
 [2026-06-23 08:05:21] game= 3909 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,909 | loss=9.1313 (p=8.4493 v=0.6820) | game=8.6s train=91.5s
 [2026-06-23 08:06:59] game= 3910 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,910 | loss=9.0773 (p=8.4493 v=0.6280) | game=5.6s train=92.9s
+[2026-06-23 08:08:41] game= 3911 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,911 | loss=8.9522 (p=8.4493 v=0.5029) | game=6.1s train=92.4s
+[2026-06-23 08:10:18] game= 3912 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,912 | loss=8.9021 (p=8.4493 v=0.4528) | game=5.4s train=91.8s
+[2026-06-23 08:11:58] game= 3913 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,913 | loss=8.8195 (p=8.4493 v=0.3702) | game=6.4s train=93.8s
+[2026-06-23 08:13:38] game= 3914 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,914 | loss=8.8063 (p=8.4493 v=0.3570) | game=6.0s train=93.9s
+[2026-06-23 08:15:21] game= 3915 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,915 | loss=8.7840 (p=8.4493 v=0.3347) | game=6.6s train=96.1s
+[2026-06-23 08:17:02] game= 3916 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,916 | loss=8.7092 (p=8.4493 v=0.2599) | game=7.3s train=94.1s
+[2026-06-23 08:18:41] game= 3917 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=3,917 | loss=8.7007 (p=8.4493 v=0.2514) | game=4.7s train=94.5s
+[2026-06-23 08:20:24] game= 3918 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,918 | loss=8.6627 (p=8.4493 v=0.2135) | game=8.7s train=94.1s
+[2026-06-23 08:22:05] game= 3919 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,919 | loss=8.6702 (p=8.4493 v=0.2209) | game=6.3s train=94.5s
+[2026-06-23 08:23:48] game= 3920 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=3,920 | loss=8.6456 (p=8.4493 v=0.1963) | game=8.5s train=94.0s