checkpoint @ game=1600 steps=1600

training_log.txt

@@ -1898,3 +1898,13 @@
 [2026-06-18 11:01:22] game= 1588 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,588 | loss=8.7344 (p=8.4493 v=0.2851) | game=5.3s train=89.1s
 [2026-06-18 11:02:55] game= 1589 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=1,589 | loss=8.7180 (p=8.4493 v=0.2687) | game=6.8s train=86.8s
 [2026-06-18 11:04:29] game= 1590 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,590 | loss=8.6971 (p=8.4493 v=0.2478) | game=6.5s train=86.8s
+[2026-06-18 11:06:08] game= 1591 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=1,591 | loss=8.6631 (p=8.4493 v=0.2138) | game=7.5s train=89.2s
+[2026-06-18 11:07:41] game= 1592 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,592 | loss=8.6448 (p=8.4493 v=0.1955) | game=5.2s train=86.9s
+[2026-06-18 11:09:13] game= 1593 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,593 | loss=8.6491 (p=8.4493 v=0.1999) | game=5.5s train=86.8s
+[2026-06-18 11:10:47] game= 1594 | 1/2-1/2 | moves= 72 | buf=50,000 | steps=1,594 | loss=8.6111 (p=8.4493 v=0.1618) | game=7.2s train=86.8s
+[2026-06-18 11:12:21] game= 1595 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=1,595 | loss=8.6366 (p=8.4493 v=0.1873) | game=4.9s train=89.0s
+[2026-06-18 11:13:51] game= 1596 | 1-0 | moves= 33 | buf=50,000 | steps=1,596 | loss=8.6141 (p=8.4493 v=0.1648) | game=3.4s train=86.9s
+[2026-06-18 11:15:23] game= 1597 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,597 | loss=8.6089 (p=8.4493 v=0.1596) | game=5.4s train=86.7s
+[2026-06-18 11:16:58] game= 1598 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,598 | loss=8.5868 (p=8.4493 v=0.1375) | game=5.4s train=89.3s
+[2026-06-18 11:18:30] game= 1599 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,599 | loss=8.5963 (p=8.4493 v=0.1470) | game=5.4s train=86.9s
+[2026-06-18 11:20:07] game= 1600 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,600 | loss=8.9982 (p=8.4493 v=0.5489) | game=10.0s train=86.8s