checkpoint @ game=4380 steps=4380

training_log.txt

@@ -4679,3 +4679,13 @@
 [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
+[2026-06-24 10:27:23] game= 4371 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,371 | loss=8.8246 (p=8.4493 v=0.3753) | game=5.3s train=96.2s
+[2026-06-24 10:29:04] game= 4372 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,372 | loss=8.7677 (p=8.4493 v=0.3184) | game=6.5s train=94.3s
+[2026-06-24 10:30:43] game= 4373 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,373 | loss=8.7102 (p=8.4493 v=0.2609) | game=5.0s train=94.3s
+[2026-06-24 10:32:24] game= 4374 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,374 | loss=8.7126 (p=8.4493 v=0.2633) | game=6.9s train=94.3s
+[2026-06-24 10:34:06] game= 4375 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,375 | loss=8.6754 (p=8.4493 v=0.2261) | game=5.1s train=96.3s
+[2026-06-24 10:35:46] game= 4376 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,376 | loss=8.6379 (p=8.4493 v=0.1886) | game=5.5s train=94.5s
+[2026-06-24 10:37:28] game= 4377 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,377 | loss=8.6090 (p=8.4493 v=0.1597) | game=7.7s train=94.6s
+[2026-06-24 10:39:08] game= 4378 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,378 | loss=8.6180 (p=8.4493 v=0.1687) | game=5.3s train=94.4s
+[2026-06-24 10:40:52] game= 4379 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=4,379 | loss=8.6486 (p=8.4493 v=0.1993) | game=9.5s train=94.5s
+[2026-06-24 10:42:31] game= 4380 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,380 | loss=8.6653 (p=8.4493 v=0.2160) | game=5.1s train=94.4s