checkpoint @ game=4010 steps=4010

training_log.txt

@@ -4309,3 +4309,13 @@
 [2026-06-23 10:35:39] game= 3998 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,998 | loss=8.8067 (p=8.4493 v=0.3574) | game=4.9s train=90.8s
 [2026-06-23 10:37:16] game= 3999 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,999 | loss=8.7946 (p=8.4493 v=0.3453) | game=5.7s train=90.8s
 [2026-06-23 10:38:53] game= 4000 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,000 | loss=8.7273 (p=8.4493 v=0.2780) | game=5.9s train=91.1s
+[2026-06-23 10:40:34] game= 4001 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,001 | loss=8.6909 (p=8.4493 v=0.2416) | game=7.0s train=91.0s
+[2026-06-23 10:42:15] game= 4002 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,002 | loss=8.7065 (p=8.4493 v=0.2572) | game=5.8s train=95.6s
+[2026-06-23 10:43:53] game= 4003 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,003 | loss=8.6776 (p=8.4493 v=0.2283) | game=6.6s train=91.0s
+[2026-06-23 10:45:29] game= 4004 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,004 | loss=8.6455 (p=8.4493 v=0.1962) | game=5.1s train=91.3s
+[2026-06-23 10:47:06] game= 4005 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,005 | loss=8.6630 (p=8.4493 v=0.2137) | game=5.9s train=90.9s
+[2026-06-23 10:48:45] game= 4006 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,006 | loss=8.6505 (p=8.4493 v=0.2012) | game=8.2s train=91.3s
+[2026-06-23 10:50:23] game= 4007 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,007 | loss=8.6220 (p=8.4493 v=0.1727) | game=5.9s train=91.4s
+[2026-06-23 10:52:00] game= 4008 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,008 | loss=8.6621 (p=8.4493 v=0.2128) | game=5.6s train=91.4s
+[2026-06-23 10:53:36] game= 4009 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,009 | loss=8.6425 (p=8.4493 v=0.1932) | game=5.0s train=91.0s
+[2026-06-23 10:55:18] game= 4010 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,010 | loss=8.6179 (p=8.4493 v=0.1686) | game=5.2s train=97.4s