checkpoint @ game=4200 steps=4200

training_log.txt

@@ -4499,3 +4499,13 @@
 [2026-06-24 04:47:29] game= 4188 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,188 | loss=8.9025 (p=8.4493 v=0.4532) | game=8.1s train=88.2s
 [2026-06-24 04:49:03] game= 4189 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,189 | loss=8.8901 (p=8.4493 v=0.4408) | game=5.4s train=88.1s
 [2026-06-24 04:50:38] game= 4190 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,190 | loss=8.8277 (p=8.4493 v=0.3784) | game=5.7s train=90.0s
+[2026-06-24 04:52:21] game= 4191 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,191 | loss=8.7794 (p=8.4493 v=0.3301) | game=6.7s train=88.2s
+[2026-06-24 04:53:54] game= 4192 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,192 | loss=8.7230 (p=8.4493 v=0.2737) | game=4.8s train=88.1s
+[2026-06-24 04:55:30] game= 4193 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,193 | loss=8.7092 (p=8.4493 v=0.2600) | game=8.1s train=88.1s
+[2026-06-24 04:57:07] game= 4194 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,194 | loss=8.6884 (p=8.4493 v=0.2391) | game=6.5s train=90.2s
+[2026-06-24 04:58:43] game= 4195 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,195 | loss=8.6486 (p=8.4493 v=0.1993) | game=7.5s train=88.4s
+[2026-06-24 05:00:16] game= 4196 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,196 | loss=8.6683 (p=8.4493 v=0.2190) | game=4.8s train=88.1s
+[2026-06-24 05:01:52] game= 4197 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,197 | loss=8.6300 (p=8.4493 v=0.1807) | game=5.5s train=90.4s
+[2026-06-24 05:03:25] game= 4198 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,198 | loss=8.6242 (p=8.4493 v=0.1749) | game=5.0s train=88.4s
+[2026-06-24 05:04:58] game= 4199 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,199 | loss=8.6544 (p=8.4493 v=0.2051) | game=5.0s train=88.2s
+[2026-06-24 05:06:31] game= 4200 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,200 | loss=8.6114 (p=8.4493 v=0.1621) | game=4.7s train=88.4s