checkpoint @ game=730 steps=730

training_log.txt

@@ -1021,3 +1021,13 @@
 [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
+[2026-06-15 02:20:52] game=  721 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=721 | loss=8.6193 (p=8.4493 v=0.1700) | game=4.8s train=178.4s
+[2026-06-15 02:23:57] game=  722 | 1/2-1/2 | moves= 77 | buf=70,000 | steps=722 | loss=8.6004 (p=8.4493 v=0.1511) | game=7.4s train=178.2s
+[2026-06-15 02:27:02] game=  723 | 1/2-1/2 | moves= 68 | buf=70,000 | steps=723 | loss=8.5929 (p=8.4493 v=0.1436) | game=7.2s train=177.8s
+[2026-06-15 02:30:12] game=  724 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=724 | loss=9.0011 (p=8.4493 v=0.5518) | game=10.5s train=178.5s
+[2026-06-15 02:33:16] game=  725 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=725 | loss=8.9511 (p=8.4493 v=0.5018) | game=5.5s train=178.6s
+[2026-06-15 02:36:20] game=  726 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=726 | loss=8.9105 (p=8.4493 v=0.4612) | game=6.5s train=177.9s
+[2026-06-15 02:39:25] game=  727 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=727 | loss=8.8650 (p=8.4493 v=0.4157) | game=6.7s train=178.4s
+[2026-06-15 02:42:28] game=  728 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=728 | loss=8.8287 (p=8.4493 v=0.3794) | game=5.3s train=177.9s
+[2026-06-15 02:45:33] game=  729 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=729 | loss=8.7729 (p=8.4493 v=0.3236) | game=6.3s train=177.9s
+[2026-06-15 02:48:36] game=  730 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=730 | loss=8.7747 (p=8.4493 v=0.3254) | game=5.4s train=177.9s