checkpoint @ game=4450 steps=4450

training_log.txt

@@ -4749,3 +4749,13 @@
 [2026-06-24 12:21:03] game= 4438 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,438 | loss=8.8060 (p=8.4493 v=0.3567) | game=6.0s train=95.3s
 [2026-06-24 12:22:44] game= 4439 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,439 | loss=8.7131 (p=8.4493 v=0.2638) | game=5.4s train=95.4s
 [2026-06-24 12:24:26] game= 4440 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,440 | loss=8.7402 (p=8.4493 v=0.2909) | game=6.6s train=95.4s
+[2026-06-24 12:26:11] game= 4441 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,441 | loss=8.7128 (p=8.4493 v=0.2635) | game=6.7s train=95.2s
+[2026-06-24 12:27:55] game= 4442 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,442 | loss=8.7277 (p=8.4493 v=0.2784) | game=9.1s train=95.3s
+[2026-06-24 12:29:36] game= 4443 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,443 | loss=8.6583 (p=8.4493 v=0.2090) | game=5.5s train=95.4s
+[2026-06-24 12:31:18] game= 4444 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,444 | loss=8.6704 (p=8.4493 v=0.2211) | game=6.6s train=95.5s
+[2026-06-24 12:32:59] game= 4445 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,445 | loss=8.7060 (p=8.4493 v=0.2567) | game=5.2s train=95.5s
+[2026-06-24 12:34:42] game= 4446 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,446 | loss=8.6189 (p=8.4493 v=0.1696) | game=8.1s train=95.5s
+[2026-06-24 12:36:24] game= 4447 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,447 | loss=8.6213 (p=8.4493 v=0.1720) | game=5.9s train=95.4s
+[2026-06-24 12:38:06] game= 4448 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=4,448 | loss=8.6198 (p=8.4493 v=0.1705) | game=6.5s train=95.5s
+[2026-06-24 12:39:47] game= 4449 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,449 | loss=8.6141 (p=8.4493 v=0.1648) | game=6.3s train=95.4s
+[2026-06-24 12:41:31] game= 4450 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,450 | loss=8.6305 (p=8.4493 v=0.1812) | game=5.7s train=98.4s