checkpoint @ game=4330 steps=4330

training_log.txt

@@ -4629,3 +4629,13 @@
 [2026-06-24 08:57:55] game= 4318 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,318 | loss=8.8611 (p=8.4493 v=0.4118) | game=5.0s train=93.5s
 [2026-06-24 08:59:34] game= 4319 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,319 | loss=8.7990 (p=8.4493 v=0.3497) | game=5.5s train=93.6s
 [2026-06-24 09:01:14] game= 4320 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,320 | loss=8.7958 (p=8.4493 v=0.3465) | game=5.1s train=95.0s
+[2026-06-24 09:02:58] game= 4321 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,321 | loss=8.7383 (p=8.4493 v=0.2890) | game=6.1s train=93.6s
+[2026-06-24 09:04:39] game= 4322 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,322 | loss=8.6858 (p=8.4493 v=0.2365) | game=6.8s train=94.9s
+[2026-06-24 09:06:21] game= 4323 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,323 | loss=8.6769 (p=8.4493 v=0.2276) | game=8.1s train=93.6s
+[2026-06-24 09:08:02] game= 4324 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,324 | loss=8.6535 (p=8.4493 v=0.2042) | game=5.9s train=95.2s
+[2026-06-24 09:09:41] game= 4325 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,325 | loss=8.6823 (p=8.4493 v=0.2330) | game=5.2s train=93.7s
+[2026-06-24 09:11:22] game= 4326 | 1/2-1/2 | moves= 74 | buf=50,000 | steps=4,326 | loss=8.6256 (p=8.4493 v=0.1763) | game=7.4s train=93.9s
+[2026-06-24 09:13:05] game= 4327 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,327 | loss=8.6266 (p=8.4493 v=0.1773) | game=8.0s train=95.2s
+[2026-06-24 09:14:45] game= 4328 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,328 | loss=8.6356 (p=8.4493 v=0.1863) | game=5.9s train=93.7s
+[2026-06-24 09:16:26] game= 4329 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,329 | loss=8.6397 (p=8.4493 v=0.1904) | game=5.5s train=95.1s
+[2026-06-24 09:18:06] game= 4330 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,330 | loss=8.6243 (p=8.4493 v=0.1750) | game=6.3s train=93.7s