checkpoint @ game=3810 steps=3810

training_log.txt

@@ -4109,3 +4109,13 @@
 [2026-06-23 05:02:27] game= 3798 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,798 | loss=8.6797 (p=8.4493 v=0.2304) | game=6.0s train=89.8s
 [2026-06-23 05:04:02] game= 3799 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,799 | loss=8.6761 (p=8.4493 v=0.2268) | game=5.4s train=89.4s
 [2026-06-23 05:05:39] game= 3800 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,800 | loss=8.6809 (p=8.4493 v=0.2316) | game=6.0s train=90.9s
+[2026-06-23 05:07:17] game= 3801 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,801 | loss=8.6398 (p=8.4493 v=0.1905) | game=5.2s train=89.9s
+[2026-06-23 05:08:52] game= 3802 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,802 | loss=8.6483 (p=8.4493 v=0.1990) | game=6.3s train=89.1s
+[2026-06-23 05:10:29] game= 3803 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,803 | loss=8.6265 (p=8.4493 v=0.1772) | game=5.9s train=91.5s
+[2026-06-23 05:12:07] game= 3804 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=3,804 | loss=8.6257 (p=8.4493 v=0.1765) | game=7.9s train=89.6s
+[2026-06-23 05:13:47] game= 3805 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,805 | loss=8.6926 (p=8.4493 v=0.2433) | game=9.8s train=90.5s
+[2026-06-23 05:15:25] game= 3806 | 1/2-1/2 | moves= 76 | buf=50,000 | steps=3,806 | loss=8.6261 (p=8.4493 v=0.1768) | game=8.3s train=89.6s
+[2026-06-23 05:17:03] game= 3807 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,807 | loss=9.1227 (p=8.4493 v=0.6734) | game=8.4s train=89.3s
+[2026-06-23 05:18:38] game= 3808 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,808 | loss=9.0167 (p=8.4493 v=0.5674) | game=6.4s train=89.0s
+[2026-06-23 05:20:15] game= 3809 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,809 | loss=8.9793 (p=8.4493 v=0.5300) | game=5.5s train=91.7s
+[2026-06-23 05:21:50] game= 3810 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,810 | loss=8.8803 (p=8.4493 v=0.4310) | game=6.0s train=89.1s