checkpoint @ game=1550 steps=1550

training_log.txt

@@ -1848,3 +1848,13 @@
 [2026-06-18 09:43:44] game= 1538 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,538 | loss=8.7061 (p=8.4493 v=0.2568) | game=8.1s train=85.9s
 [2026-06-18 09:45:17] game= 1539 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,539 | loss=8.6915 (p=8.4493 v=0.2422) | game=5.6s train=87.5s
 [2026-06-18 09:46:48] game= 1540 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,540 | loss=8.6904 (p=8.4493 v=0.2411) | game=5.2s train=86.0s
+[2026-06-18 09:48:25] game= 1541 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,541 | loss=8.6603 (p=8.4493 v=0.2110) | game=7.1s train=87.5s
+[2026-06-18 09:49:57] game= 1542 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,542 | loss=8.6431 (p=8.4493 v=0.1938) | game=5.9s train=86.1s
+[2026-06-18 09:51:28] game= 1543 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,543 | loss=8.6475 (p=8.4493 v=0.1982) | game=4.9s train=86.0s
+[2026-06-18 09:53:03] game= 1544 | 1/2-1/2 | moves= 70 | buf=50,000 | steps=1,544 | loss=8.6114 (p=8.4493 v=0.1621) | game=7.0s train=87.8s
+[2026-06-18 09:54:34] game= 1545 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,545 | loss=8.6118 (p=8.4493 v=0.1625) | game=4.9s train=86.0s
+[2026-06-18 09:56:08] game= 1546 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,546 | loss=8.5995 (p=8.4493 v=0.1502) | game=6.3s train=87.8s
+[2026-06-18 09:57:39] game= 1547 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,547 | loss=8.5810 (p=8.4493 v=0.1317) | game=5.0s train=86.0s
+[2026-06-18 09:59:10] game= 1548 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,548 | loss=8.5760 (p=8.4493 v=0.1267) | game=5.1s train=86.0s
+[2026-06-18 10:00:51] game= 1549 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,549 | loss=8.9161 (p=8.4493 v=0.4668) | game=12.8s train=87.8s
+[2026-06-18 10:02:22] game= 1550 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,550 | loss=8.9122 (p=8.4493 v=0.4629) | game=5.1s train=86.2s