checkpoint @ game=940 steps=940

training_log.txt

@@ -857,3 +857,13 @@
 [2026-06-13 05:47:59] game=  928 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=928 | loss=nan (p=nan v=0.6171) | game=24.9s train=75.0s
 [2026-06-13 05:49:43] game=  929 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=929 | loss=nan (p=nan v=0.5445) | game=27.9s train=75.9s
 [2026-06-13 05:51:26] game=  930 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=930 | loss=nan (p=nan v=0.5153) | game=25.4s train=77.5s
+[2026-06-13 05:53:12] game=  931 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=931 | loss=nan (p=nan v=0.5008) | game=25.1s train=79.6s
+[2026-06-13 05:55:01] game=  932 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=932 | loss=nan (p=nan v=0.5306) | game=25.1s train=82.9s
+[2026-06-13 05:56:47] game=  933 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=933 | loss=nan (p=nan v=0.6116) | game=25.1s train=80.8s
+[2026-06-13 05:58:33] game=  934 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=934 | loss=nan (p=nan v=0.5009) | game=25.2s train=81.5s
+[2026-06-13 06:00:20] game=  935 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=935 | loss=nan (p=nan v=0.6092) | game=25.1s train=81.9s
+[2026-06-13 06:02:13] game=  936 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=936 | loss=nan (p=nan v=0.5707) | game=28.2s train=83.9s
+[2026-06-13 06:04:04] game=  937 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=937 | loss=nan (p=nan v=0.5475) | game=25.2s train=85.6s
+[2026-06-13 06:05:55] game=  938 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=938 | loss=nan (p=nan v=0.5078) | game=25.3s train=85.9s
+[2026-06-13 06:07:57] game=  939 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=939 | loss=nan (p=nan v=0.6094) | game=31.6s train=90.3s
+[2026-06-13 06:09:51] game=  940 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=940 | loss=nan (p=nan v=0.5312) | game=25.4s train=88.4s