checkpoint @ game=790 steps=790

training_log.txt

@@ -1081,3 +1081,13 @@
 [2026-06-15 05:18:37] game=  778 | 1/2-1/2 | moves= 77 | buf=70,000 | steps=778 | loss=8.8105 (p=8.4493 v=0.3612) | game=7.4s train=177.7s
 [2026-06-15 05:21:42] game=  779 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=779 | loss=8.7743 (p=8.4493 v=0.3250) | game=5.8s train=178.4s
 [2026-06-15 05:24:45] game=  780 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=780 | loss=8.7229 (p=8.4493 v=0.2736) | game=4.9s train=178.5s
+[2026-06-15 05:27:52] game=  781 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=781 | loss=8.7041 (p=8.4493 v=0.2548) | game=6.0s train=178.5s
+[2026-06-15 05:30:57] game=  782 | 1/2-1/2 | moves= 60 | buf=70,000 | steps=782 | loss=8.6862 (p=8.4493 v=0.2369) | game=5.8s train=178.4s
+[2026-06-15 05:34:02] game=  783 | 1/2-1/2 | moves= 69 | buf=70,000 | steps=783 | loss=8.6890 (p=8.4493 v=0.2397) | game=6.6s train=178.4s
+[2026-06-15 05:37:05] game=  784 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=784 | loss=8.6706 (p=8.4493 v=0.2213) | game=4.7s train=178.6s
+[2026-06-15 05:40:09] game=  785 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=785 | loss=8.6359 (p=8.4493 v=0.1866) | game=6.0s train=177.9s
+[2026-06-15 05:43:15] game=  786 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=786 | loss=8.6494 (p=8.4493 v=0.2001) | game=8.6s train=177.9s
+[2026-06-15 05:46:22] game=  787 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=787 | loss=8.6163 (p=8.4493 v=0.1670) | game=8.5s train=177.8s
+[2026-06-15 05:49:27] game=  788 | 1/2-1/2 | moves= 73 | buf=70,000 | steps=788 | loss=8.6163 (p=8.4493 v=0.1670) | game=7.0s train=178.7s
+[2026-06-15 05:52:32] game=  789 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=789 | loss=8.5818 (p=8.4493 v=0.1325) | game=5.6s train=178.8s
+[2026-06-15 05:55:37] game=  790 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=790 | loss=8.5963 (p=8.4493 v=0.1470) | game=7.8s train=177.9s