checkpoint @ game=4320 steps=4320

training_log.txt

@@ -4619,3 +4619,13 @@
 [2026-06-24 08:41:08] game= 4308 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,308 | loss=8.6784 (p=8.4493 v=0.2291) | game=7.0s train=93.4s
 [2026-06-24 08:42:48] game= 4309 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,309 | loss=8.6362 (p=8.4493 v=0.1869) | game=4.7s train=94.8s
 [2026-06-24 08:44:26] game= 4310 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,310 | loss=8.6499 (p=8.4493 v=0.2006) | game=5.0s train=93.5s
+[2026-06-24 08:46:10] game= 4311 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=4,311 | loss=8.6063 (p=8.4493 v=0.1570) | game=6.4s train=94.7s
+[2026-06-24 08:47:51] game= 4312 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,312 | loss=8.6045 (p=8.4493 v=0.1552) | game=7.5s train=93.5s
+[2026-06-24 08:49:31] game= 4313 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,313 | loss=8.6135 (p=8.4493 v=0.1642) | game=5.4s train=94.8s
+[2026-06-24 08:51:13] game= 4314 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,314 | loss=8.6359 (p=8.4493 v=0.1866) | game=8.1s train=93.6s
+[2026-06-24 08:52:56] game= 4315 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,315 | loss=9.1480 (p=8.4493 v=0.6987) | game=8.1s train=94.8s
+[2026-06-24 08:54:35] game= 4316 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,316 | loss=9.0229 (p=8.4493 v=0.5736) | game=5.9s train=93.5s
+[2026-06-24 08:56:16] game= 4317 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,317 | loss=8.9562 (p=8.4493 v=0.5069) | game=6.3s train=94.8s
+[2026-06-24 08:57:55] game= 4318 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,318 | loss=8.8611 (p=8.4493 v=0.4118) | game=5.0s train=93.5s
+[2026-06-24 08:59:34] game= 4319 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,319 | loss=8.7990 (p=8.4493 v=0.3497) | game=5.5s train=93.6s
+[2026-06-24 09:01:14] game= 4320 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,320 | loss=8.7958 (p=8.4493 v=0.3465) | game=5.1s train=95.0s