checkpoint @ game=1020 steps=1020

training_log.txt

@@ -1313,3 +1313,13 @@
 [2026-06-16 04:49:05] game= 1008 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,008 | loss=8.9446 (p=8.4493 v=0.4953) | game=10.9s train=164.3s
 [2026-06-16 04:51:53] game= 1009 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=1,009 | loss=8.9277 (p=8.4493 v=0.4784) | game=4.8s train=163.4s
 [2026-06-16 04:54:43] game= 1010 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=1,010 | loss=8.8419 (p=8.4493 v=0.3927) | game=5.4s train=164.5s
+[2026-06-16 04:57:35] game= 1011 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,011 | loss=8.7725 (p=8.4493 v=0.3232) | game=6.3s train=163.4s
+[2026-06-16 05:00:25] game= 1012 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=1,012 | loss=8.7232 (p=8.4493 v=0.2739) | game=4.8s train=164.3s
+[2026-06-16 05:03:14] game= 1013 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=1,013 | loss=8.6966 (p=8.4493 v=0.2473) | game=5.6s train=163.4s
+[2026-06-16 05:06:03] game= 1014 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=1,014 | loss=8.6698 (p=8.4493 v=0.2205) | game=6.4s train=163.5s
+[2026-06-16 05:08:53] game= 1015 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=1,015 | loss=8.6756 (p=8.4493 v=0.2263) | game=5.1s train=164.7s
+[2026-06-16 05:11:42] game= 1016 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=1,016 | loss=8.6406 (p=8.4493 v=0.1913) | game=5.5s train=163.5s
+[2026-06-16 05:14:32] game= 1017 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=1,017 | loss=8.6136 (p=8.4493 v=0.1643) | game=6.0s train=163.5s
+[2026-06-16 05:17:23] game= 1018 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=1,018 | loss=8.6185 (p=8.4493 v=0.1692) | game=6.5s train=164.5s
+[2026-06-16 05:20:14] game= 1019 | 1/2-1/2 | moves= 80 | buf=70,000 | steps=1,019 | loss=8.6015 (p=8.4493 v=0.1522) | game=7.8s train=163.5s
+[2026-06-16 05:23:05] game= 1020 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,020 | loss=8.5917 (p=8.4493 v=0.1424) | game=7.6s train=163.5s