checkpoint @ game=1020 steps=1020

training_log.txt

@@ -937,3 +937,13 @@
 [2026-06-12 15:22:03] game= 1008 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,008 | loss=nan (p=nan v=0.5933) | game=4.5s train=163.9s
 [2026-06-12 15:24:52] game= 1009 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,009 | loss=nan (p=nan v=0.6124) | game=3.7s train=165.4s
 [2026-06-12 15:27:44] game= 1010 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,010 | loss=nan (p=nan v=0.6296) | game=4.0s train=167.6s
+[2026-06-12 15:30:43] game= 1011 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=1,011 | loss=nan (p=nan v=0.6267) | game=3.7s train=171.3s
+[2026-06-12 15:33:38] game= 1012 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,012 | loss=nan (p=nan v=0.6092) | game=3.8s train=170.9s
+[2026-06-12 15:36:32] game= 1013 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,013 | loss=nan (p=nan v=0.6066) | game=4.6s train=169.9s
+[2026-06-12 15:39:28] game= 1014 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,014 | loss=nan (p=nan v=0.6095) | game=3.9s train=172.0s
+[2026-06-12 15:42:28] game= 1015 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,015 | loss=nan (p=nan v=0.6173) | game=5.2s train=174.5s
+[2026-06-12 15:45:27] game= 1016 | 1/2-1/2 | moves= 78 | buf=50,000 | steps=1,016 | loss=nan (p=nan v=0.6389) | game=6.2s train=172.6s
+[2026-06-12 15:48:25] game= 1017 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,017 | loss=nan (p=nan v=0.6113) | game=3.8s train=173.7s
+[2026-06-12 15:51:20] game= 1018 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,018 | loss=nan (p=nan v=0.5939) | game=4.0s train=171.6s
+[2026-06-12 15:54:24] game= 1019 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,019 | loss=nan (p=nan v=0.5806) | game=4.4s train=179.3s
+[2026-06-12 15:57:24] game= 1020 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,020 | loss=nan (p=nan v=0.6243) | game=4.5s train=175.1s