checkpoint @ game=4240 steps=4240

training_log.txt

@@ -4539,3 +4539,13 @@
 [2026-06-24 05:51:00] game= 4228 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,228 | loss=8.7033 (p=8.4493 v=0.2540) | game=5.5s train=91.1s
 [2026-06-24 05:52:34] game= 4229 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,229 | loss=8.7307 (p=8.4493 v=0.2814) | game=5.2s train=88.8s
 [2026-06-24 05:54:08] game= 4230 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,230 | loss=8.6586 (p=8.4493 v=0.2093) | game=4.9s train=88.7s
+[2026-06-24 06:32:48] game= 4231 | 1/2-1/2 | moves= 56 | buf=31,902 | steps=4,231 | loss=9.3267 (p=8.4493 v=0.8774) | game=6.6s train=103.9s
+[2026-06-24 06:34:26] game= 4232 | 1/2-1/2 | moves= 46 | buf=31,948 | steps=4,232 | loss=9.1728 (p=8.4493 v=0.7235) | game=4.7s train=92.9s
+[2026-06-24 06:36:04] game= 4233 | 1/2-1/2 | moves= 60 | buf=32,008 | steps=4,233 | loss=9.0058 (p=8.4493 v=0.5565) | game=5.9s train=92.4s
+[2026-06-24 06:37:43] game= 4234 | 1/2-1/2 | moves= 59 | buf=32,067 | steps=4,234 | loss=8.9102 (p=8.4493 v=0.4609) | game=5.8s train=92.8s
+[2026-06-24 06:39:21] game= 4235 | 1/2-1/2 | moves= 55 | buf=32,122 | steps=4,235 | loss=8.7636 (p=8.4493 v=0.3144) | game=5.6s train=92.6s
+[2026-06-24 06:40:59] game= 4236 | 1/2-1/2 | moves= 55 | buf=32,177 | steps=4,236 | loss=8.6939 (p=8.4493 v=0.2446) | game=5.6s train=92.5s
+[2026-06-24 06:42:39] game= 4237 | 1/2-1/2 | moves= 68 | buf=32,245 | steps=4,237 | loss=8.7260 (p=8.4493 v=0.2767) | game=6.9s train=92.7s
+[2026-06-24 06:44:17] game= 4238 | 1/2-1/2 | moves= 52 | buf=32,297 | steps=4,238 | loss=8.7077 (p=8.4493 v=0.2584) | game=5.1s train=92.7s
+[2026-06-24 06:45:57] game= 4239 | 1/2-1/2 | moves= 79 | buf=32,376 | steps=4,239 | loss=8.6226 (p=8.4493 v=0.1733) | game=8.0s train=92.8s
+[2026-06-24 06:47:32] game= 4240 | 1-0 | moves= 15 | buf=32,391 | steps=4,240 | loss=8.6255 (p=8.4493 v=0.1762) | game=1.7s train=93.1s