checkpoint @ game=4550 steps=4550

training_log.txt

@@ -4849,3 +4849,13 @@
 [2026-06-25 03:31:20] game= 4538 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,538 | loss=8.6839 (p=8.4493 v=0.2346) | game=6.1s train=88.4s
 [2026-06-25 03:32:58] game= 4539 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,539 | loss=8.6227 (p=8.4493 v=0.1734) | game=8.0s train=89.9s
 [2026-06-25 03:34:35] game= 4540 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,540 | loss=8.6657 (p=8.4493 v=0.2164) | game=8.8s train=87.9s
+[2026-06-25 03:36:23] game= 4541 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,541 | loss=8.5864 (p=8.4493 v=0.1371) | game=6.7s train=89.4s
+[2026-06-25 03:37:58] game= 4542 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,542 | loss=8.6304 (p=8.4493 v=0.1811) | game=6.1s train=88.5s
+[2026-06-25 03:39:33] game= 4543 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,543 | loss=8.6681 (p=8.4493 v=0.2188) | game=5.3s train=89.9s
+[2026-06-25 03:41:10] game= 4544 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,544 | loss=8.5719 (p=8.4493 v=0.1226) | game=8.2s train=89.3s
+[2026-06-25 03:42:49] game= 4545 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,545 | loss=9.1370 (p=8.4493 v=0.6877) | game=8.7s train=89.9s
+[2026-06-25 03:44:25] game= 4546 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,546 | loss=9.1008 (p=8.4493 v=0.6515) | game=8.1s train=88.6s
+[2026-06-25 03:46:01] game= 4547 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,547 | loss=8.9821 (p=8.4493 v=0.5328) | game=5.9s train=89.7s
+[2026-06-25 03:47:35] game= 4548 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,548 | loss=8.9392 (p=8.4493 v=0.4899) | game=5.5s train=88.5s
+[2026-06-25 03:49:13] game= 4549 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,549 | loss=8.8401 (p=8.4493 v=0.3908) | game=8.3s train=89.2s
+[2026-06-25 03:50:48] game= 4550 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,550 | loss=8.7864 (p=8.4493 v=0.3371) | game=7.4s train=88.4s