checkpoint @ game=4620 steps=4620

training_log.txt

@@ -4919,3 +4919,13 @@
 [2026-06-25 05:24:22] game= 4608 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,608 | loss=8.6484 (p=8.4493 v=0.1991) | game=6.5s train=88.1s
 [2026-06-25 05:25:56] game= 4609 | 1-0 | moves= 31 | buf=50,000 | steps=4,609 | loss=8.6255 (p=8.4493 v=0.1762) | game=3.1s train=90.0s
 [2026-06-25 05:27:30] game= 4610 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,610 | loss=8.6299 (p=8.4493 v=0.1806) | game=5.7s train=88.3s
+[2026-06-25 05:29:10] game= 4611 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,611 | loss=8.6036 (p=8.4493 v=0.1543) | game=7.7s train=88.3s
+[2026-06-25 05:30:45] game= 4612 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,612 | loss=8.6439 (p=8.4493 v=0.1946) | game=5.0s train=90.6s
+[2026-06-25 05:32:20] game= 4613 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,613 | loss=8.9448 (p=8.4493 v=0.4955) | game=6.2s train=88.2s
+[2026-06-25 05:33:54] game= 4614 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,614 | loss=8.8321 (p=8.4493 v=0.3828) | game=6.1s train=88.2s
+[2026-06-25 05:35:27] game= 4615 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,615 | loss=8.7756 (p=8.4493 v=0.3263) | game=4.8s train=88.2s
+[2026-06-25 05:37:03] game= 4616 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,616 | loss=8.7124 (p=8.4493 v=0.2631) | game=5.2s train=90.8s
+[2026-06-25 05:38:37] game= 4617 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,617 | loss=8.7361 (p=8.4493 v=0.2868) | game=6.0s train=88.3s
+[2026-06-25 05:40:12] game= 4618 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,618 | loss=8.6994 (p=8.4493 v=0.2501) | game=5.7s train=88.3s
+[2026-06-25 05:41:50] game= 4619 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,619 | loss=8.6614 (p=8.4493 v=0.2121) | game=8.1s train=90.4s
+[2026-06-25 05:43:23] game= 4620 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,620 | loss=8.6420 (p=8.4493 v=0.1927) | game=4.9s train=88.3s