checkpoint @ game=3910 steps=3910

training_log.txt

@@ -4209,3 +4209,13 @@
 [2026-06-23 07:46:57] game= 3898 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,898 | loss=8.6989 (p=8.4493 v=0.2496) | game=5.7s train=93.2s
 [2026-06-23 07:48:39] game= 3899 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,899 | loss=8.7771 (p=8.4493 v=0.3278) | game=8.9s train=92.4s
 [2026-06-23 07:50:17] game= 3900 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,900 | loss=8.6792 (p=8.4493 v=0.2299) | game=5.8s train=92.4s
+[2026-06-23 07:52:03] game= 3901 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,901 | loss=8.6788 (p=8.4493 v=0.2295) | game=6.2s train=96.0s
+[2026-06-23 07:53:42] game= 3902 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,902 | loss=8.6518 (p=8.4493 v=0.2025) | game=7.3s train=92.0s
+[2026-06-23 07:55:21] game= 3903 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,903 | loss=8.6284 (p=8.4493 v=0.1791) | game=6.3s train=92.0s
+[2026-06-23 07:56:59] game= 3904 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=3,904 | loss=8.6455 (p=8.4493 v=0.1962) | game=4.7s train=93.6s
+[2026-06-23 07:58:40] game= 3905 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=3,905 | loss=8.6193 (p=8.4493 v=0.1700) | game=8.3s train=92.3s
+[2026-06-23 08:00:19] game= 3906 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,906 | loss=8.6524 (p=8.4493 v=0.2032) | game=6.4s train=93.4s
+[2026-06-23 08:01:57] game= 3907 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,907 | loss=8.6022 (p=8.4493 v=0.1529) | game=5.6s train=92.5s
+[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