checkpoint @ game=4600 steps=4600

training_log.txt

@@ -4899,3 +4899,13 @@
 [2026-06-25 04:52:29] game= 4588 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=4,588 | loss=8.6548 (p=8.4493 v=0.2055) | game=8.4s train=91.4s
 [2026-06-25 04:54:05] game= 4589 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,589 | loss=8.6818 (p=8.4493 v=0.2326) | game=6.1s train=90.2s
 [2026-06-25 04:55:41] game= 4590 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,590 | loss=8.6164 (p=8.4493 v=0.1671) | game=7.2s train=88.7s
+[2026-06-25 04:57:21] game= 4591 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,591 | loss=8.6361 (p=8.4493 v=0.1868) | game=5.7s train=89.9s
+[2026-06-25 04:58:56] game= 4592 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,592 | loss=8.6225 (p=8.4493 v=0.1732) | game=6.9s train=87.8s
+[2026-06-25 05:00:30] game= 4593 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,593 | loss=8.6110 (p=8.4493 v=0.1617) | game=6.7s train=87.9s
+[2026-06-25 05:02:08] game= 4594 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,594 | loss=8.6099 (p=8.4493 v=0.1606) | game=9.8s train=87.8s
+[2026-06-25 05:03:41] game= 4595 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,595 | loss=8.6191 (p=8.4493 v=0.1698) | game=5.3s train=88.0s
+[2026-06-25 05:05:17] game= 4596 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,596 | loss=9.1507 (p=8.4493 v=0.7014) | game=7.5s train=87.8s
+[2026-06-25 05:06:51] game= 4597 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,597 | loss=9.0989 (p=8.4493 v=0.6496) | game=6.5s train=88.2s
+[2026-06-25 05:08:24] game= 4598 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,598 | loss=8.9032 (p=8.4493 v=0.4539) | game=4.9s train=87.9s
+[2026-06-25 05:09:58] game= 4599 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,599 | loss=8.8847 (p=8.4493 v=0.4354) | game=6.5s train=87.9s
+[2026-06-25 05:11:35] game= 4600 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,600 | loss=8.8408 (p=8.4493 v=0.3915) | game=8.4s train=88.0s