checkpoint @ game=720 steps=720

training_log.txt

@@ -1011,3 +1011,13 @@
 [2026-06-15 01:40:58] game=  708 | 1/2-1/2 | moves= 75 | buf=70,000 | steps=708 | loss=8.9375 (p=8.4493 v=0.4882) | game=7.3s train=178.0s
 [2026-06-15 01:44:01] game=  709 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=709 | loss=8.8942 (p=8.4493 v=0.4449) | game=4.8s train=178.1s
 [2026-06-15 01:47:05] game=  710 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=710 | loss=8.8585 (p=8.4493 v=0.4092) | game=5.3s train=178.1s
+[2026-06-15 01:50:11] game=  711 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=711 | loss=8.8376 (p=8.4493 v=0.3883) | game=5.4s train=178.1s
+[2026-06-15 01:53:15] game=  712 | 1/2-1/2 | moves= 60 | buf=70,000 | steps=712 | loss=8.7981 (p=8.4493 v=0.3488) | game=5.9s train=178.2s
+[2026-06-15 01:56:19] game=  713 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=713 | loss=8.7403 (p=8.4493 v=0.2910) | game=6.0s train=177.7s
+[2026-06-15 01:59:23] game=  714 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=714 | loss=8.7322 (p=8.4493 v=0.2829) | game=6.5s train=178.0s
+[2026-06-15 02:02:26] game=  715 | 1/2-1/2 | moves= 47 | buf=70,000 | steps=715 | loss=8.7071 (p=8.4493 v=0.2578) | game=5.0s train=178.2s
+[2026-06-15 02:05:32] game=  716 | 1/2-1/2 | moves= 72 | buf=70,000 | steps=716 | loss=8.7068 (p=8.4493 v=0.2575) | game=6.9s train=178.2s
+[2026-06-15 02:08:35] game=  717 | 1/2-1/2 | moves= 53 | buf=70,000 | steps=717 | loss=8.6606 (p=8.4493 v=0.2113) | game=5.1s train=178.3s
+[2026-06-15 02:11:39] game=  718 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=718 | loss=8.6504 (p=8.4493 v=0.2011) | game=5.7s train=178.4s
+[2026-06-15 02:14:42] game=  719 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=719 | loss=8.6479 (p=8.4493 v=0.1986) | game=4.8s train=178.1s
+[2026-06-15 02:17:45] game=  720 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=720 | loss=8.6037 (p=8.4493 v=0.1544) | game=5.3s train=177.8s