checkpoint @ game=4520 steps=4520

training_log.txt

@@ -4819,3 +4819,13 @@
 [2026-06-25 02:43:23] game= 4508 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,508 | loss=8.6169 (p=8.4493 v=0.1676) | game=5.8s train=88.2s
 [2026-06-25 02:44:58] game= 4509 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,509 | loss=8.6157 (p=8.4493 v=0.1664) | game=6.8s train=88.2s
 [2026-06-25 02:46:33] game= 4510 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,510 | loss=8.6035 (p=8.4493 v=0.1542) | game=6.6s train=88.4s
+[2026-06-25 02:48:17] game= 4511 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,511 | loss=9.1511 (p=8.4493 v=0.7018) | game=11.8s train=88.8s
+[2026-06-25 02:49:54] game= 4512 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,512 | loss=9.0502 (p=8.4493 v=0.6009) | game=8.4s train=88.5s
+[2026-06-25 02:51:32] game= 4513 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,513 | loss=8.9578 (p=8.4493 v=0.5086) | game=8.9s train=89.3s
+[2026-06-25 02:53:06] game= 4514 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,514 | loss=8.8395 (p=8.4493 v=0.3902) | game=6.3s train=87.8s
+[2026-06-25 02:54:41] game= 4515 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,515 | loss=8.8111 (p=8.4493 v=0.3618) | game=6.1s train=88.7s
+[2026-06-25 02:56:16] game= 4516 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,516 | loss=8.8041 (p=8.4493 v=0.3548) | game=7.0s train=87.8s
+[2026-06-25 02:57:51] game= 4517 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,517 | loss=8.7442 (p=8.4493 v=0.2949) | game=6.9s train=88.1s
+[2026-06-25 02:59:25] game= 4518 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,518 | loss=8.7311 (p=8.4493 v=0.2818) | game=6.2s train=88.3s
+[2026-06-25 03:00:59] game= 4519 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,519 | loss=8.6655 (p=8.4493 v=0.2162) | game=5.3s train=88.8s
+[2026-06-25 03:02:34] game= 4520 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,520 | loss=8.6612 (p=8.4493 v=0.2119) | game=6.9s train=88.1s