checkpoint @ game=950 steps=950

training_log.txt

@@ -867,3 +867,13 @@
 [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
+[2026-06-13 06:11:47] game=  941 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=941 | loss=nan (p=nan v=0.6248) | game=25.3s train=88.9s
+[2026-06-13 06:13:42] game=  942 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=942 | loss=nan (p=nan v=0.5313) | game=25.2s train=89.9s
+[2026-06-13 06:15:42] game=  943 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=943 | loss=nan (p=nan v=0.5856) | game=28.4s train=91.4s
+[2026-06-13 06:17:40] game=  944 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=944 | loss=nan (p=nan v=0.5380) | game=25.4s train=92.4s
+[2026-06-13 06:19:39] game=  945 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=945 | loss=nan (p=nan v=0.5695) | game=25.2s train=93.3s
+[2026-06-13 06:21:42] game=  946 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=946 | loss=nan (p=nan v=0.5778) | game=25.1s train=97.5s
+[2026-06-13 06:23:43] game=  947 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=947 | loss=nan (p=nan v=0.6184) | game=25.5s train=95.7s
+[2026-06-13 06:25:44] game=  948 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=948 | loss=nan (p=nan v=0.5780) | game=25.5s train=95.9s
+[2026-06-13 06:27:47] game=  949 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=949 | loss=nan (p=nan v=0.5154) | game=25.3s train=97.3s
+[2026-06-13 06:29:55] game=  950 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=950 | loss=nan (p=nan v=0.5546) | game=25.3s train=102.3s