checkpoint @ game=4140 steps=4140

training_log.txt

@@ -4439,3 +4439,13 @@
 [2026-06-24 03:12:41] game= 4128 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,128 | loss=8.6860 (p=8.4493 v=0.2367) | game=5.6s train=87.3s
 [2026-06-24 03:14:15] game= 4129 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,129 | loss=8.6313 (p=8.4493 v=0.1820) | game=6.3s train=87.4s
 [2026-06-24 03:15:49] game= 4130 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,130 | loss=8.6444 (p=8.4493 v=0.1951) | game=7.1s train=87.4s
+[2026-06-24 03:17:30] game= 4131 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,131 | loss=8.6288 (p=8.4493 v=0.1795) | game=8.0s train=87.4s
+[2026-06-24 03:19:04] game= 4132 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,132 | loss=8.6476 (p=8.4493 v=0.1983) | game=6.9s train=87.3s
+[2026-06-24 03:20:40] game= 4133 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,133 | loss=8.6234 (p=8.4493 v=0.1741) | game=8.0s train=88.6s
+[2026-06-24 03:22:13] game= 4134 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,134 | loss=8.5683 (p=8.4493 v=0.1190) | game=4.9s train=87.5s
+[2026-06-24 03:23:48] game= 4135 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,135 | loss=9.1149 (p=8.4493 v=0.6656) | game=7.4s train=87.5s
+[2026-06-24 03:25:24] game= 4136 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,136 | loss=9.0294 (p=8.4493 v=0.5801) | game=8.5s train=87.5s
+[2026-06-24 03:26:56] game= 4137 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,137 | loss=8.9504 (p=8.4493 v=0.5011) | game=5.2s train=87.4s
+[2026-06-24 03:28:30] game= 4138 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,138 | loss=8.8573 (p=8.4493 v=0.4080) | game=6.4s train=87.5s
+[2026-06-24 03:30:03] game= 4139 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,139 | loss=8.8088 (p=8.4493 v=0.3595) | game=5.5s train=87.4s
+[2026-06-24 03:31:37] game= 4140 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,140 | loss=8.7684 (p=8.4493 v=0.3191) | game=5.4s train=88.8s