checkpoint @ game=930 steps=930

training_log.txt

@@ -847,3 +847,13 @@
 [2026-06-12 12:17:27] game=  918 | 1/2-1/2 | moves= 74 | buf=50,000 | steps=918 | loss=nan (p=nan v=0.5957) | game=5.8s train=70.1s
 [2026-06-12 12:18:45] game=  919 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=919 | loss=nan (p=nan v=0.5469) | game=6.1s train=71.4s
 [2026-06-12 12:20:04] game=  920 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=920 | loss=nan (p=nan v=0.5467) | game=6.3s train=72.5s
+[2026-06-12 12:21:29] game=  921 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=921 | loss=nan (p=nan v=0.5722) | game=10.0s train=73.7s
+[2026-06-12 12:22:47] game=  922 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=922 | loss=nan (p=nan v=0.5893) | game=4.1s train=73.7s
+[2026-06-12 12:24:06] game=  923 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=923 | loss=nan (p=nan v=0.5558) | game=3.7s train=75.0s
+[2026-06-12 12:25:29] game=  924 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=924 | loss=nan (p=nan v=0.5953) | game=5.7s train=77.0s
+[2026-06-12 12:26:53] game=  925 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=925 | loss=nan (p=nan v=0.6211) | game=4.3s train=80.1s
+[2026-06-12 12:28:19] game=  926 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=926 | loss=nan (p=nan v=0.5819) | game=6.4s train=79.2s
+[2026-06-12 12:29:45] game=  927 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=927 | loss=nan (p=nan v=0.6092) | game=4.2s train=81.5s
+[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