checkpoint @ game=3650 steps=3650

training_log.txt

@@ -3949,3 +3949,13 @@
 [2026-06-23 00:48:56] game= 3638 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,638 | loss=9.0996 (p=8.4493 v=0.6503) | game=5.4s train=86.0s
 [2026-06-23 00:50:29] game= 3639 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,639 | loss=8.9368 (p=8.4493 v=0.4875) | game=5.9s train=86.7s
 [2026-06-23 00:52:01] game= 3640 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,640 | loss=8.8722 (p=8.4493 v=0.4229) | game=5.9s train=85.9s
+[2026-06-23 00:53:35] game= 3641 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,641 | loss=8.8491 (p=8.4493 v=0.3998) | game=5.9s train=85.7s
+[2026-06-23 00:55:07] game= 3642 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=3,642 | loss=8.7891 (p=8.4493 v=0.3398) | game=5.0s train=86.6s
+[2026-06-23 00:56:44] game= 3643 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,643 | loss=8.7352 (p=8.4493 v=0.2859) | game=9.1s train=87.3s
+[2026-06-23 00:58:17] game= 3644 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,644 | loss=8.7529 (p=8.4493 v=0.3036) | game=5.8s train=87.4s
+[2026-06-23 00:59:48] game= 3645 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=3,645 | loss=8.6811 (p=8.4493 v=0.2318) | game=5.0s train=86.3s
+[2026-06-23 01:01:22] game= 3646 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,646 | loss=8.6453 (p=8.4493 v=0.1960) | game=7.0s train=86.9s
+[2026-06-23 01:02:56] game= 3647 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,647 | loss=8.6647 (p=8.4493 v=0.2154) | game=7.2s train=86.6s
+[2026-06-23 01:04:29] game= 3648 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=3,648 | loss=8.6819 (p=8.4493 v=0.2326) | game=6.9s train=86.8s
+[2026-06-23 01:06:03] game= 3649 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,649 | loss=8.6389 (p=8.4493 v=0.1897) | game=6.7s train=87.0s
+[2026-06-23 01:07:32] game= 3650 | 1-0 | moves= 13 | buf=50,000 | steps=3,650 | loss=8.6444 (p=8.4493 v=0.1951) | game=2.0s train=86.8s