checkpoint @ game=3400 steps=3400

training_log.txt

@@ -3699,3 +3699,13 @@
 [2026-06-22 07:52:46] game= 3388 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,388 | loss=8.8680 (p=8.4493 v=0.4187) | game=5.6s train=85.7s
 [2026-06-22 07:54:16] game= 3389 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,389 | loss=8.7614 (p=8.4493 v=0.3121) | game=4.9s train=85.6s
 [2026-06-22 07:55:47] game= 3390 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,390 | loss=8.7735 (p=8.4493 v=0.3242) | game=5.0s train=85.6s
+[2026-06-22 07:57:21] game= 3391 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,391 | loss=8.7353 (p=8.4493 v=0.2860) | game=5.9s train=85.1s
+[2026-06-22 07:58:54] game= 3392 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=3,392 | loss=8.7231 (p=8.4493 v=0.2738) | game=7.7s train=85.1s
+[2026-06-22 08:00:25] game= 3393 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,393 | loss=8.6918 (p=8.4493 v=0.2425) | game=5.6s train=85.7s
+[2026-06-22 08:01:56] game= 3394 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,394 | loss=8.6496 (p=8.4493 v=0.2003) | game=5.9s train=85.7s
+[2026-06-22 08:03:26] game= 3395 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,395 | loss=8.6867 (p=8.4493 v=0.2374) | game=4.9s train=85.1s
+[2026-06-22 08:04:58] game= 3396 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,396 | loss=8.6632 (p=8.4493 v=0.2139) | game=6.4s train=85.1s
+[2026-06-22 08:06:29] game= 3397 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,397 | loss=8.6869 (p=8.4493 v=0.2376) | game=5.1s train=85.9s
+[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