checkpoint @ game=4440 steps=4440

training_log.txt

@@ -4739,3 +4739,13 @@
 [2026-06-24 12:03:53] game= 4428 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,428 | loss=8.6718 (p=8.4493 v=0.2225) | game=6.2s train=95.3s
 [2026-06-24 12:05:34] game= 4429 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=4,429 | loss=8.6144 (p=8.4493 v=0.1651) | game=6.4s train=95.2s
 [2026-06-24 12:07:15] game= 4430 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,430 | loss=8.6347 (p=8.4493 v=0.1854) | game=5.4s train=95.3s
+[2026-06-24 12:09:09] game= 4431 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,431 | loss=8.6281 (p=8.4493 v=0.1788) | game=5.7s train=95.1s
+[2026-06-24 12:10:53] game= 4432 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,432 | loss=8.5876 (p=8.4493 v=0.1383) | game=5.7s train=98.1s
+[2026-06-24 12:12:33] game= 4433 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,433 | loss=8.6048 (p=8.4493 v=0.1555) | game=5.0s train=95.1s
+[2026-06-24 12:14:16] game= 4434 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,434 | loss=9.1158 (p=8.4493 v=0.6665) | game=7.6s train=95.3s
+[2026-06-24 12:15:57] game= 4435 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,435 | loss=9.0520 (p=8.4493 v=0.6027) | game=5.5s train=95.2s
+[2026-06-24 12:17:39] game= 4436 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,436 | loss=8.9358 (p=8.4493 v=0.4865) | game=6.9s train=95.1s
+[2026-06-24 12:19:22] game= 4437 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,437 | loss=8.8708 (p=8.4493 v=0.4215) | game=5.0s train=97.9s
+[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