checkpoint @ game=3220 steps=3220

training_log.txt

@@ -3519,3 +3519,13 @@
 [2026-06-22 03:04:32] game= 3208 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,208 | loss=8.8974 (p=8.4493 v=0.4481) | game=5.6s train=84.9s
 [2026-06-22 03:06:03] game= 3209 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,209 | loss=8.8394 (p=8.4493 v=0.3901) | game=5.7s train=85.1s
 [2026-06-22 03:07:34] game= 3210 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,210 | loss=8.8301 (p=8.4493 v=0.3808) | game=5.8s train=85.6s
+[2026-06-22 03:09:09] game= 3211 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,211 | loss=8.7822 (p=8.4493 v=0.3329) | game=6.5s train=85.6s
+[2026-06-22 03:10:42] game= 3212 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=3,212 | loss=8.7459 (p=8.4493 v=0.2966) | game=7.0s train=85.6s
+[2026-06-22 03:12:14] game= 3213 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=3,213 | loss=8.7456 (p=8.4493 v=0.2963) | game=6.6s train=85.0s
+[2026-06-22 03:13:47] game= 3214 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=3,214 | loss=8.7040 (p=8.4493 v=0.2547) | game=7.6s train=85.7s
+[2026-06-22 03:15:18] game= 3215 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,215 | loss=8.7084 (p=8.4493 v=0.2591) | game=5.0s train=85.7s
+[2026-06-22 03:16:48] game= 3216 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,216 | loss=8.6384 (p=8.4493 v=0.1891) | game=5.1s train=85.0s
+[2026-06-22 03:18:22] game= 3217 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,217 | loss=8.6459 (p=8.4493 v=0.1966) | game=8.7s train=85.1s
+[2026-06-22 03:19:54] game= 3218 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,218 | loss=8.6462 (p=8.4493 v=0.1969) | game=7.1s train=85.0s
+[2026-06-22 03:21:26] game= 3219 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,219 | loss=8.6184 (p=8.4493 v=0.1691) | game=6.0s train=85.8s
+[2026-06-22 03:22:56] game= 3220 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,220 | loss=8.6347 (p=8.4493 v=0.1854) | game=5.3s train=85.1s