checkpoint @ game=2920 steps=2920

training_log.txt

@@ -3219,3 +3219,13 @@
 [2026-06-21 04:47:31] game= 2908 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=2,908 | loss=8.8794 (p=8.4493 v=0.4301) | game=5.9s train=94.3s
 [2026-06-21 04:49:11] game= 2909 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=2,909 | loss=8.8546 (p=8.4493 v=0.4053) | game=7.9s train=91.9s
 [2026-06-21 04:50:50] game= 2910 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=2,910 | loss=8.8032 (p=8.4493 v=0.3539) | game=6.9s train=92.0s
+[2026-06-21 04:52:30] game= 2911 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=2,911 | loss=8.7614 (p=8.4493 v=0.3121) | game=5.6s train=92.0s
+[2026-06-21 04:54:08] game= 2912 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=2,912 | loss=8.7152 (p=8.4493 v=0.2659) | game=5.8s train=92.0s
+[2026-06-21 04:55:47] game= 2913 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=2,913 | loss=8.7070 (p=8.4493 v=0.2577) | game=7.5s train=91.9s
+[2026-06-21 04:57:25] game= 2914 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=2,914 | loss=8.7106 (p=8.4493 v=0.2613) | game=5.5s train=92.0s
+[2026-06-21 04:59:03] game= 2915 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=2,915 | loss=8.7024 (p=8.4493 v=0.2531) | game=6.6s train=91.9s
+[2026-06-21 05:00:44] game= 2916 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=2,916 | loss=8.7593 (p=8.4493 v=0.3100) | game=6.5s train=94.5s
+[2026-06-21 05:02:23] game= 2917 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=2,917 | loss=8.6540 (p=8.4493 v=0.2047) | game=6.6s train=92.1s
+[2026-06-21 05:04:01] game= 2918 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=2,918 | loss=8.6709 (p=8.4493 v=0.2216) | game=5.6s train=92.1s
+[2026-06-21 05:05:38] game= 2919 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,919 | loss=8.7211 (p=8.4493 v=0.2718) | game=5.1s train=92.0s
+[2026-06-21 05:07:17] game= 2920 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=2,920 | loss=9.1793 (p=8.4493 v=0.7300) | game=7.4s train=92.0s