checkpoint @ game=3410 steps=3410

training_log.txt

@@ -3709,3 +3709,13 @@
 [2026-06-22 08:07:59] game= 3398 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,398 | loss=8.6644 (p=8.4493 v=0.2151) | game=4.9s train=85.8s
 [2026-06-22 08:09:29] game= 3399 | 1-0 | moves= 33 | buf=50,000 | steps=3,399 | loss=8.6592 (p=8.4493 v=0.2099) | game=3.3s train=85.9s
 [2026-06-22 08:11:01] game= 3400 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=3,400 | loss=8.6384 (p=8.4493 v=0.1891) | game=7.4s train=85.0s
+[2026-06-22 08:12:38] game= 3401 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,401 | loss=9.1702 (p=8.4493 v=0.7209) | game=7.9s train=85.8s
+[2026-06-22 08:14:09] game= 3402 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,402 | loss=9.0919 (p=8.4493 v=0.6427) | game=5.2s train=85.9s
+[2026-06-22 08:15:39] game= 3403 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,403 | loss=8.9656 (p=8.4493 v=0.5163) | game=5.1s train=85.2s
+[2026-06-22 08:17:10] game= 3404 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,404 | loss=8.8943 (p=8.4493 v=0.4450) | game=5.1s train=85.1s
+[2026-06-22 08:18:41] game= 3405 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,405 | loss=8.8937 (p=8.4493 v=0.4444) | game=6.2s train=85.2s
+[2026-06-22 08:20:15] game= 3406 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,406 | loss=8.8721 (p=8.4493 v=0.4228) | game=8.8s train=85.1s
+[2026-06-22 08:21:49] game= 3407 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,407 | loss=8.8526 (p=8.4493 v=0.4033) | game=8.0s train=86.1s
+[2026-06-22 08:23:21] game= 3408 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,408 | loss=8.7570 (p=8.4493 v=0.3077) | game=5.2s train=86.5s
+[2026-06-22 08:24:52] game= 3409 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,409 | loss=8.7230 (p=8.4493 v=0.2737) | game=5.1s train=86.3s
+[2026-06-22 08:26:24] game= 3410 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,410 | loss=8.7224 (p=8.4493 v=0.2731) | game=6.2s train=85.4s