checkpoint @ game=460 steps=460

training_log.txt

@@ -746,3 +746,10 @@
 [2026-06-12 03:13:56] game=  817 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=817 | loss=nan (p=nan v=0.5917) | game=10.8s train=162.4s
 [2026-06-12 03:16:54] game=  818 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=818 | loss=nan (p=nan v=0.5447) | game=11.5s train=165.9s
 [2026-06-12 03:19:54] game=  819 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=819 | loss=nan (p=nan v=0.5996) | game=13.1s train=166.5s
+[2026-06-14 02:22:40] game=  454 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=454 | loss=8.9857 (p=8.4493 v=0.5364) | game=6.3s train=95.2s
+[2026-06-14 02:24:09] game=  455 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=455 | loss=8.9931 (p=8.4493 v=0.5438) | game=4.9s train=84.9s
+[2026-06-14 02:25:42] game=  456 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=456 | loss=8.9456 (p=8.4493 v=0.4963) | game=8.0s train=84.8s
+[2026-06-14 02:27:13] game=  457 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=457 | loss=8.9527 (p=8.4493 v=0.5034) | game=5.2s train=85.2s
+[2026-06-14 02:28:45] game=  458 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=458 | loss=8.9265 (p=8.4493 v=0.4772) | game=7.5s train=84.9s
+[2026-06-14 02:30:16] game=  459 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=459 | loss=8.9630 (p=8.4493 v=0.5137) | game=6.2s train=84.6s
+[2026-06-14 02:31:48] game=  460 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=460 | loss=8.9633 (p=8.4493 v=0.5140) | game=7.2s train=85.1s