checkpoint @ game=3600 steps=3600

training_log.txt

@@ -3899,3 +3899,13 @@
 [2026-06-22 13:03:42] game= 3588 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,588 | loss=9.1449 (p=8.4493 v=0.6956) | game=7.4s train=87.7s
 [2026-06-22 13:05:15] game= 3589 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,589 | loss=9.0030 (p=8.4493 v=0.5537) | game=5.5s train=88.0s
 [2026-06-22 13:06:51] game= 3590 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,590 | loss=8.9226 (p=8.4493 v=0.4733) | game=8.1s train=87.8s
+[2026-06-22 13:08:29] game= 3591 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,591 | loss=8.8971 (p=8.4493 v=0.4478) | game=5.7s train=87.8s
+[2026-06-22 13:10:06] game= 3592 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,592 | loss=8.7961 (p=8.4493 v=0.3468) | game=5.3s train=91.7s
+[2026-06-22 13:11:39] game= 3593 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,593 | loss=8.7741 (p=8.4493 v=0.3248) | game=4.9s train=87.8s
+[2026-06-22 13:13:12] game= 3594 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,594 | loss=8.7357 (p=8.4493 v=0.2864) | game=5.1s train=87.9s
+[2026-06-22 13:14:46] game= 3595 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,595 | loss=8.6921 (p=8.4493 v=0.2428) | game=5.8s train=88.1s
+[2026-06-22 13:16:18] game= 3596 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,596 | loss=8.7203 (p=8.4493 v=0.2710) | game=4.9s train=87.9s
+[2026-06-22 13:17:52] game= 3597 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,597 | loss=8.7269 (p=8.4493 v=0.2776) | game=5.6s train=88.1s
+[2026-06-22 13:19:28] game= 3598 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,598 | loss=8.6580 (p=8.4493 v=0.2087) | game=7.7s train=88.0s
+[2026-06-22 13:21:02] game= 3599 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,599 | loss=8.6793 (p=8.4493 v=0.2300) | game=5.9s train=88.3s
+[2026-06-22 13:22:36] game= 3600 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,600 | loss=8.6066 (p=8.4493 v=0.1573) | game=5.6s train=88.1s