checkpoint @ game=4370 steps=4370

training_log.txt

@@ -4669,3 +4669,13 @@
 [2026-06-24 10:05:18] game= 4358 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,358 | loss=8.6665 (p=8.4493 v=0.2172) | game=5.5s train=94.3s
 [2026-06-24 10:07:02] game= 4359 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,359 | loss=8.6506 (p=8.4493 v=0.2013) | game=7.3s train=96.1s
 [2026-06-24 10:08:43] game= 4360 | 1/2-1/2 | moves= 70 | buf=50,000 | steps=4,360 | loss=8.6813 (p=8.4493 v=0.2320) | game=7.1s train=94.3s
+[2026-06-24 10:10:25] game= 4361 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,361 | loss=8.6194 (p=8.4493 v=0.1701) | game=4.8s train=94.2s
+[2026-06-24 10:12:05] game= 4362 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,362 | loss=8.6328 (p=8.4493 v=0.1835) | game=5.1s train=94.2s
+[2026-06-24 10:13:47] game= 4363 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,363 | loss=8.6893 (p=8.4493 v=0.2400) | game=8.4s train=94.2s
+[2026-06-24 10:15:26] game= 4364 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,364 | loss=8.5922 (p=8.4493 v=0.1430) | game=5.0s train=94.3s
+[2026-06-24 10:17:09] game= 4365 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,365 | loss=8.6056 (p=8.4493 v=0.1564) | game=6.5s train=96.2s
+[2026-06-24 10:18:52] game= 4366 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,366 | loss=9.1644 (p=8.4493 v=0.7151) | game=8.5s train=94.4s
+[2026-06-24 10:20:31] game= 4367 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,367 | loss=9.1003 (p=8.4493 v=0.6510) | game=5.0s train=94.4s
+[2026-06-24 10:22:11] game= 4368 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,368 | loss=8.9643 (p=8.4493 v=0.5150) | game=5.3s train=94.2s
+[2026-06-24 10:23:56] game= 4369 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,369 | loss=8.8263 (p=8.4493 v=0.3770) | game=10.1s train=94.5s
+[2026-06-24 10:25:37] game= 4370 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,370 | loss=8.8495 (p=8.4493 v=0.4002) | game=6.9s train=94.3s