checkpoint @ game=1630 steps=1630

training_log.txt

@@ -1928,3 +1928,13 @@
 [2026-06-18 11:48:26] game= 1618 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=1,618 | loss=8.9491 (p=8.4493 v=0.4998) | game=7.7s train=89.5s
 [2026-06-18 11:50:00] game= 1619 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=1,619 | loss=8.8724 (p=8.4493 v=0.4231) | game=6.8s train=87.2s
 [2026-06-18 11:51:33] game= 1620 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,620 | loss=8.8195 (p=8.4493 v=0.3702) | game=5.5s train=87.3s
+[2026-06-18 11:53:09] game= 1621 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,621 | loss=8.7859 (p=8.4493 v=0.3366) | game=5.1s train=87.3s
+[2026-06-18 11:54:45] game= 1622 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,622 | loss=8.7243 (p=8.4493 v=0.2750) | game=6.2s train=89.8s
+[2026-06-18 11:56:19] game= 1623 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,623 | loss=8.6840 (p=8.4493 v=0.2347) | game=7.3s train=87.2s
+[2026-06-18 11:57:53] game= 1624 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=1,624 | loss=8.6599 (p=8.4493 v=0.2106) | game=6.5s train=87.4s
+[2026-06-18 11:59:26] game= 1625 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,625 | loss=8.6665 (p=8.4493 v=0.2172) | game=5.4s train=87.4s
+[2026-06-18 12:00:59] game= 1626 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,626 | loss=8.6218 (p=8.4493 v=0.1725) | game=5.7s train=87.2s
+[2026-06-18 12:02:34] game= 1627 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,627 | loss=8.6275 (p=8.4493 v=0.1782) | game=8.1s train=87.6s
+[2026-06-18 12:04:09] game= 1628 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=1,628 | loss=8.6276 (p=8.4493 v=0.1783) | game=7.6s train=87.3s
+[2026-06-18 12:05:43] game= 1629 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,629 | loss=8.5936 (p=8.4493 v=0.1443) | game=6.6s train=87.1s
+[2026-06-18 12:07:16] game= 1630 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,630 | loss=8.6064 (p=8.4493 v=0.1571) | game=5.9s train=87.3s