checkpoint @ game=4430 steps=4430

training_log.txt

@@ -4729,3 +4729,13 @@
 [2026-06-24 11:46:59] game= 4418 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,418 | loss=9.0575 (p=8.4493 v=0.6082) | game=4.9s train=97.5s
 [2026-06-24 11:48:39] game= 4419 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,419 | loss=8.9874 (p=8.4493 v=0.5381) | game=4.8s train=95.0s
 [2026-06-24 11:50:20] game= 4420 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,420 | loss=8.9275 (p=8.4493 v=0.4782) | game=6.0s train=95.1s
+[2026-06-24 11:52:03] game= 4421 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,421 | loss=8.8277 (p=8.4493 v=0.3784) | game=5.2s train=95.1s
+[2026-06-24 11:53:44] game= 4422 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,422 | loss=8.7950 (p=8.4493 v=0.3457) | game=5.9s train=95.2s
+[2026-06-24 11:55:25] game= 4423 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,423 | loss=8.7417 (p=8.4493 v=0.2924) | game=5.9s train=95.2s
+[2026-06-24 11:57:07] game= 4424 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,424 | loss=8.6932 (p=8.4493 v=0.2439) | game=6.5s train=95.0s
+[2026-06-24 11:58:47] game= 4425 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,425 | loss=8.7021 (p=8.4493 v=0.2528) | game=5.0s train=95.1s
+[2026-06-24 12:00:28] game= 4426 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,426 | loss=8.6497 (p=8.4493 v=0.2004) | game=5.9s train=95.0s
+[2026-06-24 12:02:11] game= 4427 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,427 | loss=8.6090 (p=8.4493 v=0.1597) | game=5.8s train=97.6s
+[2026-06-24 12:03:53] game= 4428 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,428 | loss=8.6718 (p=8.4493 v=0.2225) | game=6.2s train=95.3s
+[2026-06-24 12:05:34] game= 4429 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=4,429 | loss=8.6144 (p=8.4493 v=0.1651) | game=6.4s train=95.2s
+[2026-06-24 12:07:15] game= 4430 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,430 | loss=8.6347 (p=8.4493 v=0.1854) | game=5.4s train=95.3s