checkpoint @ game=1980 steps=1980

training_log.txt

@@ -2278,3 +2278,13 @@
 [2026-06-19 02:36:56] game= 1968 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,968 | loss=8.7942 (p=8.4493 v=0.3449) | game=5.6s train=86.8s
 [2026-06-19 02:38:27] game= 1969 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,969 | loss=8.7519 (p=8.4493 v=0.3026) | game=5.7s train=85.4s
 [2026-06-19 02:40:01] game= 1970 | 1/2-1/2 | moves= 68 | buf=50,000 | steps=1,970 | loss=8.7456 (p=8.4493 v=0.2963) | game=6.7s train=86.8s
+[2026-06-19 02:41:34] game= 1971 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,971 | loss=8.7081 (p=8.4493 v=0.2588) | game=5.1s train=85.4s
+[2026-06-19 02:43:06] game= 1972 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,972 | loss=8.7015 (p=8.4493 v=0.2522) | game=4.7s train=86.8s
+[2026-06-19 02:44:38] game= 1973 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,973 | loss=8.6467 (p=8.4493 v=0.1974) | game=6.5s train=85.5s
+[2026-06-19 02:46:11] game= 1974 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,974 | loss=8.6538 (p=8.4493 v=0.2045) | game=6.2s train=86.8s
+[2026-06-19 02:47:41] game= 1975 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=1,975 | loss=8.6180 (p=8.4493 v=0.1687) | game=4.8s train=85.5s
+[2026-06-19 02:49:12] game= 1976 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,976 | loss=8.6002 (p=8.4493 v=0.1509) | game=4.9s train=85.5s
+[2026-06-19 02:50:45] game= 1977 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=1,977 | loss=8.6056 (p=8.4493 v=0.1563) | game=6.0s train=87.0s
+[2026-06-19 02:52:16] game= 1978 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=1,978 | loss=8.6374 (p=8.4493 v=0.1881) | game=6.0s train=85.5s
+[2026-06-19 02:53:48] game= 1979 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=1,979 | loss=8.5860 (p=8.4493 v=0.1367) | game=5.7s train=85.5s
+[2026-06-19 02:55:21] game= 1980 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=1,980 | loss=8.5729 (p=8.4493 v=0.1236) | game=7.8s train=85.6s