checkpoint @ game=1010 steps=1010

training_log.txt

@@ -1303,3 +1303,13 @@
 [2026-06-16 04:20:46] game=  998 | 1/2-1/2 | moves= 46 | buf=70,000 | steps=998 | loss=8.6662 (p=8.4493 v=0.2169) | game=4.5s train=163.2s
 [2026-06-16 04:23:35] game=  999 | 1/2-1/2 | moves= 48 | buf=70,000 | steps=999 | loss=8.6454 (p=8.4493 v=0.1961) | game=4.7s train=164.2s
 [2026-06-16 04:26:23] game= 1000 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=1,000 | loss=8.6481 (p=8.4493 v=0.1988) | game=4.8s train=163.3s
+[2026-06-16 04:29:15] game= 1001 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=1,001 | loss=8.6191 (p=8.4493 v=0.1698) | game=5.3s train=164.3s
+[2026-06-16 04:32:03] game= 1002 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=1,002 | loss=8.5915 (p=8.4493 v=0.1422) | game=4.8s train=163.2s
+[2026-06-16 04:34:52] game= 1003 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=1,003 | loss=8.6044 (p=8.4493 v=0.1551) | game=5.1s train=163.3s
+[2026-06-16 04:37:42] game= 1004 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=1,004 | loss=8.5959 (p=8.4493 v=0.1466) | game=5.7s train=164.3s
+[2026-06-16 04:40:31] game= 1005 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,005 | loss=8.5768 (p=8.4493 v=0.1275) | game=6.3s train=163.2s
+[2026-06-16 04:43:20] game= 1006 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=1,006 | loss=8.5502 (p=8.4493 v=0.1009) | game=5.9s train=163.2s
+[2026-06-16 04:46:10] game= 1007 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=1,007 | loss=8.5633 (p=8.4493 v=0.1140) | game=5.1s train=164.1s
+[2026-06-16 04:49:05] game= 1008 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,008 | loss=8.9446 (p=8.4493 v=0.4953) | game=10.9s train=164.3s
+[2026-06-16 04:51:53] game= 1009 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=1,009 | loss=8.9277 (p=8.4493 v=0.4784) | game=4.8s train=163.4s
+[2026-06-16 04:54:43] game= 1010 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=1,010 | loss=8.8419 (p=8.4493 v=0.3927) | game=5.4s train=164.5s