checkpoint @ game=1950 steps=1950

training_log.txt

@@ -2248,3 +2248,13 @@
 [2026-06-19 01:50:45] game= 1938 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,938 | loss=8.7403 (p=8.4493 v=0.2910) | game=4.8s train=86.0s
 [2026-06-19 01:52:18] game= 1939 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,939 | loss=8.7353 (p=8.4493 v=0.2860) | game=8.0s train=85.0s
 [2026-06-19 01:53:50] game= 1940 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=1,940 | loss=8.6863 (p=8.4493 v=0.2370) | game=6.5s train=85.9s
+[2026-06-19 01:55:25] game= 1941 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=1,941 | loss=8.6424 (p=8.4493 v=0.1931) | game=6.9s train=85.1s
+[2026-06-19 01:56:57] game= 1942 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,942 | loss=8.6635 (p=8.4493 v=0.2142) | game=6.6s train=86.1s
+[2026-06-19 01:58:29] game= 1943 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,943 | loss=8.6152 (p=8.4493 v=0.1659) | game=5.4s train=86.0s
+[2026-06-19 02:00:00] game= 1944 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,944 | loss=8.6355 (p=8.4493 v=0.1862) | game=5.8s train=85.0s
+[2026-06-19 02:01:32] game= 1945 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,945 | loss=8.6251 (p=8.4493 v=0.1758) | game=6.4s train=86.0s
+[2026-06-19 02:03:05] game= 1946 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,946 | loss=8.6002 (p=8.4493 v=0.1509) | game=6.3s train=86.2s
+[2026-06-19 02:04:35] game= 1947 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,947 | loss=8.6434 (p=8.4493 v=0.1941) | game=5.0s train=85.2s
+[2026-06-19 02:06:11] game= 1948 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,948 | loss=8.9253 (p=8.4493 v=0.4760) | game=9.9s train=86.2s
+[2026-06-19 02:07:43] game= 1949 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,949 | loss=8.9326 (p=8.4493 v=0.4833) | game=6.4s train=85.1s
+[2026-06-19 02:09:14] game= 1950 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,950 | loss=8.8635 (p=8.4493 v=0.4142) | game=4.8s train=86.2s