checkpoint @ game=1540 steps=1540

training_log.txt

@@ -1838,3 +1838,13 @@
 [2026-06-18 09:28:12] game= 1528 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,528 | loss=8.5964 (p=8.4493 v=0.1471) | game=6.3s train=85.8s
 [2026-06-18 09:29:45] game= 1529 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,529 | loss=8.5597 (p=8.4493 v=0.1104) | game=5.5s train=87.2s
 [2026-06-18 09:31:17] game= 1530 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=1,530 | loss=8.5827 (p=8.4493 v=0.1334) | game=6.6s train=85.8s
+[2026-06-18 09:32:51] game= 1531 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,531 | loss=8.5783 (p=8.4493 v=0.1290) | game=5.4s train=85.8s
+[2026-06-18 09:34:28] game= 1532 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,532 | loss=9.0046 (p=8.4493 v=0.5553) | game=9.7s train=87.3s
+[2026-06-18 09:35:59] game= 1533 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,533 | loss=8.9449 (p=8.4493 v=0.4956) | game=5.7s train=85.9s
+[2026-06-18 09:37:33] game= 1534 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,534 | loss=8.8695 (p=8.4493 v=0.4202) | game=6.2s train=87.4s
+[2026-06-18 09:39:05] game= 1535 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,535 | loss=8.8469 (p=8.4493 v=0.3976) | game=6.3s train=85.9s
+[2026-06-18 09:40:36] game= 1536 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,536 | loss=8.7739 (p=8.4493 v=0.3246) | game=5.3s train=85.8s
+[2026-06-18 09:42:10] game= 1537 | 1/2-1/2 | moves= 62 | buf=50,000 | steps=1,537 | loss=8.7247 (p=8.4493 v=0.2754) | game=6.2s train=87.3s
+[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