checkpoint @ game=940 steps=940

training_log.txt

@@ -857,3 +857,13 @@
 [2026-06-12 12:31:11] game=  928 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=928 | loss=nan (p=nan v=0.5799) | game=4.3s train=81.4s
 [2026-06-12 12:32:40] game=  929 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=929 | loss=nan (p=nan v=0.5410) | game=4.8s train=84.4s
 [2026-06-12 12:34:08] game=  930 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=930 | loss=nan (p=nan v=0.5783) | game=4.2s train=83.4s
+[2026-06-12 12:35:38] game=  931 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=931 | loss=nan (p=nan v=0.5940) | game=4.5s train=83.3s
+[2026-06-12 12:37:07] game=  932 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=932 | loss=nan (p=nan v=0.6135) | game=4.5s train=85.2s
+[2026-06-12 12:38:43] game=  933 | 1/2-1/2 | moves= 74 | buf=50,000 | steps=933 | loss=nan (p=nan v=0.5821) | game=5.8s train=90.1s
+[2026-06-12 12:40:16] game=  934 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=934 | loss=nan (p=nan v=0.5606) | game=5.1s train=87.5s
+[2026-06-12 12:41:48] game=  935 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=935 | loss=nan (p=nan v=0.5605) | game=4.4s train=87.2s
+[2026-06-12 12:43:21] game=  936 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=936 | loss=nan (p=nan v=0.5430) | game=4.3s train=88.8s
+[2026-06-12 12:44:55] game=  937 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=937 | loss=nan (p=nan v=0.5836) | game=4.0s train=90.3s
+[2026-06-12 12:46:38] game=  938 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=938 | loss=nan (p=nan v=0.5164) | game=11.5s train=90.7s
+[2026-06-12 12:48:16] game=  939 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=939 | loss=nan (p=nan v=0.5877) | game=5.2s train=92.6s
+[2026-06-12 12:49:53] game=  940 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=940 | loss=nan (p=nan v=0.5685) | game=5.4s train=91.5s