checkpoint @ game=4680 steps=4680

training_log.txt

@@ -4979,3 +4979,13 @@
 [2026-06-25 07:00:06] game= 4668 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,668 | loss=8.5517 (p=8.4493 v=0.1024) | game=5.6s train=91.7s
 [2026-06-25 07:01:40] game= 4669 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=4,669 | loss=8.5707 (p=8.4493 v=0.1214) | game=4.6s train=89.1s
 [2026-06-25 07:03:17] game= 4670 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,670 | loss=8.5711 (p=8.4493 v=0.1218) | game=8.2s train=89.1s
+[2026-06-25 07:05:05] game= 4671 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,671 | loss=8.5337 (p=8.4493 v=0.0844) | game=6.1s train=89.1s
+[2026-06-25 07:06:43] game= 4672 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,672 | loss=8.5513 (p=8.4493 v=0.1020) | game=6.1s train=91.6s
+[2026-06-25 07:08:17] game= 4673 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,673 | loss=8.5497 (p=8.4493 v=0.1004) | game=5.7s train=89.0s
+[2026-06-25 07:09:54] game= 4674 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,674 | loss=8.5465 (p=8.4493 v=0.0972) | game=7.7s train=89.2s
+[2026-06-25 07:11:29] game= 4675 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,675 | loss=8.5497 (p=8.4493 v=0.1004) | game=5.8s train=89.2s
+[2026-06-25 07:13:08] game= 4676 | 1/2-1/2 | moves= 62 | buf=50,000 | steps=4,676 | loss=8.6118 (p=8.4493 v=0.1625) | game=6.3s train=92.4s
+[2026-06-25 07:14:45] game= 4677 | 1/2-1/2 | moves= 80 | buf=50,000 | steps=4,677 | loss=8.5431 (p=8.4493 v=0.0938) | game=8.1s train=89.2s
+[2026-06-25 07:16:20] game= 4678 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,678 | loss=8.5789 (p=8.4493 v=0.1296) | game=5.9s train=89.1s
+[2026-06-25 07:17:56] game= 4679 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,679 | loss=8.5487 (p=8.4493 v=0.0994) | game=6.8s train=89.2s
+[2026-06-25 07:19:30] game= 4680 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,680 | loss=8.5552 (p=8.4493 v=0.1059) | game=4.9s train=89.2s