checkpoint @ game=4180 steps=4180

training_log.txt

@@ -4479,3 +4479,13 @@
 [2026-06-24 04:15:41] game= 4168 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,168 | loss=8.5934 (p=8.4493 v=0.1441) | game=4.9s train=88.0s
 [2026-06-24 04:17:16] game= 4169 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,169 | loss=9.0804 (p=8.4493 v=0.6311) | game=7.8s train=87.9s
 [2026-06-24 04:18:50] game= 4170 | 1/2-1/2 | moves= 62 | buf=50,000 | steps=4,170 | loss=9.0769 (p=8.4493 v=0.6276) | game=6.1s train=87.8s
+[2026-06-24 04:20:30] game= 4171 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,171 | loss=8.9742 (p=8.4493 v=0.5249) | game=7.7s train=88.0s
+[2026-06-24 04:22:04] game= 4172 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,172 | loss=8.9557 (p=8.4493 v=0.5064) | game=5.7s train=87.9s
+[2026-06-24 04:23:36] game= 4173 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=4,173 | loss=8.8281 (p=8.4493 v=0.3788) | game=4.6s train=87.9s
+[2026-06-24 04:25:12] game= 4174 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,174 | loss=8.8164 (p=8.4493 v=0.3671) | game=5.7s train=89.7s
+[2026-06-24 04:26:45] game= 4175 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,175 | loss=8.7486 (p=8.4493 v=0.2994) | game=5.7s train=88.1s
+[2026-06-24 04:28:21] game= 4176 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,176 | loss=8.6937 (p=8.4493 v=0.2444) | game=5.7s train=89.8s
+[2026-06-24 04:29:55] game= 4177 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,177 | loss=8.6785 (p=8.4493 v=0.2292) | game=6.5s train=88.1s
+[2026-06-24 04:31:29] game= 4178 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,178 | loss=8.6837 (p=8.4493 v=0.2344) | game=5.4s train=88.1s
+[2026-06-24 04:33:04] game= 4179 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,179 | loss=8.6490 (p=8.4493 v=0.1997) | game=5.8s train=89.9s
+[2026-06-24 04:34:38] game= 4180 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,180 | loss=8.6397 (p=8.4493 v=0.1904) | game=5.4s train=88.0s