checkpoint @ game=1520 steps=1520

training_log.txt

@@ -1818,3 +1818,13 @@
 [2026-06-18 08:57:25] game= 1508 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,508 | loss=8.6270 (p=8.4493 v=0.1777) | game=5.0s train=85.6s
 [2026-06-18 08:58:57] game= 1509 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,509 | loss=8.6234 (p=8.4493 v=0.1741) | game=5.1s train=86.8s
 [2026-06-18 09:00:27] game= 1510 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,510 | loss=8.6196 (p=8.4493 v=0.1703) | game=4.7s train=85.5s
+[2026-06-18 09:02:03] game= 1511 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,511 | loss=8.6064 (p=8.4493 v=0.1571) | game=5.4s train=86.9s
+[2026-06-18 09:03:35] game= 1512 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,512 | loss=8.5764 (p=8.4493 v=0.1271) | game=7.1s train=85.6s
+[2026-06-18 09:05:07] game= 1513 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,513 | loss=8.5891 (p=8.4493 v=0.1398) | game=5.1s train=86.6s
+[2026-06-18 09:06:38] game= 1514 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,514 | loss=8.5606 (p=8.4493 v=0.1113) | game=5.8s train=85.6s
+[2026-06-18 09:08:16] game= 1515 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=1,515 | loss=8.9174 (p=8.4493 v=0.4681) | game=10.4s train=86.7s
+[2026-06-18 09:09:46] game= 1516 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,516 | loss=8.9108 (p=8.4493 v=0.4615) | game=5.0s train=85.7s
+[2026-06-18 09:11:18] game= 1517 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,517 | loss=8.8594 (p=8.4493 v=0.4101) | game=5.1s train=86.9s
+[2026-06-18 09:12:51] game= 1518 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,518 | loss=8.8160 (p=8.4493 v=0.3667) | game=7.3s train=85.7s
+[2026-06-18 09:14:23] game= 1519 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,519 | loss=8.7343 (p=8.4493 v=0.2850) | game=4.9s train=86.9s
+[2026-06-18 09:15:54] game= 1520 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,520 | loss=8.7320 (p=8.4493 v=0.2827) | game=4.7s train=85.7s