checkpoint @ game=4170 steps=4170

training_log.txt

@@ -4469,3 +4469,13 @@
 [2026-06-24 03:59:57] game= 4158 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,158 | loss=8.7139 (p=8.4493 v=0.2646) | game=6.6s train=87.8s
 [2026-06-24 04:01:29] game= 4159 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,159 | loss=8.6917 (p=8.4493 v=0.2424) | game=4.8s train=87.8s
 [2026-06-24 04:03:04] game= 4160 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,160 | loss=8.7179 (p=8.4493 v=0.2686) | game=5.1s train=89.4s
+[2026-06-24 04:04:44] game= 4161 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,161 | loss=8.6885 (p=8.4493 v=0.2393) | game=5.5s train=87.8s
+[2026-06-24 04:06:20] game= 4162 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=4,162 | loss=8.6382 (p=8.4493 v=0.1889) | game=6.3s train=89.4s
+[2026-06-24 04:07:53] game= 4163 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,163 | loss=8.6409 (p=8.4493 v=0.1916) | game=4.8s train=87.9s
+[2026-06-24 04:09:25] game= 4164 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,164 | loss=8.6229 (p=8.4493 v=0.1736) | game=4.9s train=87.8s
+[2026-06-24 04:11:00] game= 4165 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,165 | loss=8.6227 (p=8.4493 v=0.1734) | game=7.0s train=87.8s
+[2026-06-24 04:12:33] game= 4166 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,166 | loss=8.6314 (p=8.4493 v=0.1821) | game=5.3s train=87.8s
+[2026-06-24 04:14:08] game= 4167 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,167 | loss=8.6233 (p=8.4493 v=0.1740) | game=5.1s train=89.4s
+[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