checkpoint @ game=2000 steps=2000

training_log.txt

@@ -2298,3 +2298,13 @@
 [2026-06-19 03:07:43] game= 1988 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,988 | loss=8.7318 (p=8.4493 v=0.2825) | game=5.7s train=85.7s
 [2026-06-19 03:09:16] game= 1989 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=1,989 | loss=8.6691 (p=8.4493 v=0.2198) | game=6.0s train=87.3s
 [2026-06-19 03:10:50] game= 1990 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,990 | loss=8.6885 (p=8.4493 v=0.2392) | game=8.1s train=85.7s
+[2026-06-19 03:12:25] game= 1991 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,991 | loss=8.6468 (p=8.4493 v=0.1975) | game=5.1s train=87.2s
+[2026-06-19 03:13:57] game= 1992 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,992 | loss=8.6116 (p=8.4493 v=0.1623) | game=6.2s train=85.8s
+[2026-06-19 03:15:31] game= 1993 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,993 | loss=8.6063 (p=8.4493 v=0.1570) | game=8.0s train=85.9s
+[2026-06-19 03:17:03] game= 1994 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,994 | loss=8.5896 (p=8.4493 v=0.1403) | game=6.7s train=85.8s
+[2026-06-19 03:18:35] game= 1995 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=1,995 | loss=8.6108 (p=8.4493 v=0.1615) | game=6.0s train=85.9s
+[2026-06-19 03:20:10] game= 1996 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=1,996 | loss=8.6178 (p=8.4493 v=0.1685) | game=6.9s train=87.5s
+[2026-06-19 03:21:43] game= 1997 | 1/2-1/2 | moves= 78 | buf=50,000 | steps=1,997 | loss=8.5954 (p=8.4493 v=0.1461) | game=7.8s train=85.9s
+[2026-06-19 03:23:15] game= 1998 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,998 | loss=8.5886 (p=8.4493 v=0.1393) | game=6.3s train=85.9s
+[2026-06-19 03:24:53] game= 1999 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=1,999 | loss=8.9804 (p=8.4493 v=0.5311) | game=10.1s train=87.5s
+[2026-06-19 03:26:24] game= 2000 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=2,000 | loss=8.9148 (p=8.4493 v=0.4655) | game=4.7s train=86.0s