checkpoint @ game=4230 steps=4230

training_log.txt

@@ -4529,3 +4529,13 @@
 [2026-06-24 05:35:02] game= 4218 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,218 | loss=8.6240 (p=8.4493 v=0.1747) | game=8.0s train=88.6s
 [2026-06-24 05:36:37] game= 4219 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,219 | loss=8.6200 (p=8.4493 v=0.1707) | game=6.7s train=88.6s
 [2026-06-24 05:38:13] game= 4220 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,220 | loss=9.1666 (p=8.4493 v=0.7173) | game=7.8s train=88.6s
+[2026-06-24 05:39:53] game= 4221 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,221 | loss=9.0861 (p=8.4493 v=0.6368) | game=5.0s train=90.9s
+[2026-06-24 05:41:27] game= 4222 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,222 | loss=8.9307 (p=8.4493 v=0.4814) | game=5.2s train=88.7s
+[2026-06-24 05:43:00] game= 4223 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,223 | loss=8.8793 (p=8.4493 v=0.4300) | game=4.9s train=88.5s
+[2026-06-24 05:44:38] game= 4224 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,224 | loss=8.7955 (p=8.4493 v=0.3462) | game=6.3s train=91.1s
+[2026-06-24 05:46:13] game= 4225 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,225 | loss=8.7631 (p=8.4493 v=0.3138) | game=6.3s train=88.6s
+[2026-06-24 05:47:47] game= 4226 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,226 | loss=8.7457 (p=8.4493 v=0.2964) | game=6.2s train=88.7s
+[2026-06-24 05:49:24] game= 4227 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,227 | loss=8.7517 (p=8.4493 v=0.3024) | game=7.5s train=88.7s
+[2026-06-24 05:51:00] game= 4228 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,228 | loss=8.7033 (p=8.4493 v=0.2540) | game=5.5s train=91.1s
+[2026-06-24 05:52:34] game= 4229 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,229 | loss=8.7307 (p=8.4493 v=0.2814) | game=5.2s train=88.8s
+[2026-06-24 05:54:08] game= 4230 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,230 | loss=8.6586 (p=8.4493 v=0.2093) | game=4.9s train=88.7s