checkpoint @ game=3430 steps=3430

training_log.txt

@@ -3729,3 +3729,13 @@
 [2026-06-22 08:38:50] game= 3418 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,418 | loss=9.1842 (p=8.4493 v=0.7349) | game=10.5s train=86.2s
 [2026-06-22 08:40:22] game= 3419 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=3,419 | loss=9.0415 (p=8.4493 v=0.5922) | game=6.6s train=85.4s
 [2026-06-22 08:41:53] game= 3420 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,420 | loss=8.9511 (p=8.4493 v=0.5018) | game=5.7s train=85.3s
+[2026-06-22 08:43:27] game= 3421 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,421 | loss=8.9329 (p=8.4493 v=0.4836) | game=4.8s train=86.4s
+[2026-06-22 08:44:59] game= 3422 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,422 | loss=8.8679 (p=8.4493 v=0.4186) | game=5.5s train=86.5s
+[2026-06-22 08:46:32] game= 3423 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,423 | loss=8.8047 (p=8.4493 v=0.3554) | game=8.1s train=85.5s
+[2026-06-22 08:48:07] game= 3424 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=3,424 | loss=8.7482 (p=8.4493 v=0.2989) | game=7.8s train=86.4s
+[2026-06-22 08:49:38] game= 3425 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,425 | loss=8.7670 (p=8.4493 v=0.3177) | game=5.9s train=85.4s
+[2026-06-22 08:51:11] game= 3426 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,426 | loss=8.7105 (p=8.4493 v=0.2613) | game=6.5s train=86.5s
+[2026-06-22 08:52:42] game= 3427 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=3,427 | loss=8.6918 (p=8.4493 v=0.2425) | game=5.8s train=85.4s
+[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