checkpoint @ game=960 steps=960

training_log.txt

@@ -877,3 +877,13 @@
 [2026-06-12 13:03:31] game=  948 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=948 | loss=nan (p=nan v=0.5330) | game=5.0s train=98.4s
 [2026-06-12 13:05:19] game=  949 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=949 | loss=nan (p=nan v=0.5666) | game=5.0s train=102.1s
 [2026-06-12 13:07:07] game=  950 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=950 | loss=nan (p=nan v=0.5650) | game=4.1s train=104.4s
+[2026-06-12 13:09:01] game=  951 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=951 | loss=nan (p=nan v=0.5490) | game=6.4s train=104.9s
+[2026-06-12 13:10:52] game=  952 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=952 | loss=nan (p=nan v=0.5684) | game=4.0s train=106.9s
+[2026-06-12 13:12:43] game=  953 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=953 | loss=nan (p=nan v=0.5523) | game=4.6s train=106.0s
+[2026-06-12 13:14:34] game=  954 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=954 | loss=nan (p=nan v=0.5589) | game=4.3s train=107.2s
+[2026-06-12 13:16:33] game=  955 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=955 | loss=nan (p=nan v=0.5541) | game=8.3s train=110.2s
+[2026-06-12 13:18:28] game=  956 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=956 | loss=nan (p=nan v=0.6229) | game=5.5s train=109.6s
+[2026-06-12 13:20:25] game=  957 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=957 | loss=nan (p=nan v=0.6112) | game=4.2s train=112.9s
+[2026-06-12 13:22:24] game=  958 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=958 | loss=nan (p=nan v=0.5625) | game=4.6s train=113.5s
+[2026-06-12 13:24:22] game=  959 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=959 | loss=nan (p=nan v=0.5976) | game=3.8s train=113.9s
+[2026-06-12 13:26:21] game=  960 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=960 | loss=nan (p=nan v=0.5507) | game=4.2s train=115.3s