checkpoint @ game=3440 steps=3440

training_log.txt

@@ -3739,3 +3739,13 @@
 [2026-06-22 08:54:14] game= 3428 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,428 | loss=8.6624 (p=8.4493 v=0.2131) | game=6.1s train=85.5s
 [2026-06-22 08:55:45] game= 3429 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,429 | loss=8.6581 (p=8.4493 v=0.2088) | game=5.1s train=86.4s
 [2026-06-22 08:57:16] game= 3430 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,430 | loss=8.6975 (p=8.4493 v=0.2482) | game=5.8s train=85.5s
+[2026-06-22 08:58:52] game= 3431 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,431 | loss=8.6851 (p=8.4493 v=0.2358) | game=6.5s train=86.5s
+[2026-06-22 09:00:22] game= 3432 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,432 | loss=8.6486 (p=8.4493 v=0.1993) | game=4.9s train=85.5s
+[2026-06-22 09:01:54] game= 3433 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,433 | loss=8.6472 (p=8.4493 v=0.1979) | game=5.5s train=86.6s
+[2026-06-22 09:03:25] game= 3434 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,434 | loss=8.6326 (p=8.4493 v=0.1833) | game=5.3s train=85.4s
+[2026-06-22 09:04:58] game= 3435 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,435 | loss=9.0938 (p=8.4493 v=0.6445) | game=8.1s train=85.5s
+[2026-06-22 09:06:31] game= 3436 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,436 | loss=9.0202 (p=8.4493 v=0.5709) | game=5.9s train=86.8s
+[2026-06-22 09:08:02] game= 3437 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,437 | loss=8.9163 (p=8.4493 v=0.4670) | game=5.9s train=85.5s
+[2026-06-22 09:09:35] game= 3438 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,438 | loss=8.8777 (p=8.4493 v=0.4284) | game=5.7s train=86.7s
+[2026-06-22 09:11:08] game= 3439 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,439 | loss=8.8019 (p=8.4493 v=0.3526) | game=7.6s train=85.6s
+[2026-06-22 09:12:40] game= 3440 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,440 | loss=8.7831 (p=8.4493 v=0.3338) | game=5.7s train=86.6s