checkpoint @ game=3210 steps=3210

training_log.txt

@@ -3509,3 +3509,13 @@
 [2026-06-22 02:49:15] game= 3198 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,198 | loss=8.6601 (p=8.4493 v=0.2108) | game=8.0s train=85.3s
 [2026-06-22 02:50:48] game= 3199 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,199 | loss=8.6946 (p=8.4493 v=0.2453) | game=8.0s train=85.3s
 [2026-06-22 02:52:19] game= 3200 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,200 | loss=8.6492 (p=8.4493 v=0.1999) | game=5.1s train=85.9s
+[2026-06-22 02:53:55] game= 3201 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,201 | loss=8.6610 (p=8.4493 v=0.2117) | game=5.0s train=85.3s
+[2026-06-22 02:55:25] game= 3202 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=3,202 | loss=8.6750 (p=8.4493 v=0.2257) | game=4.8s train=85.5s
+[2026-06-22 02:56:55] game= 3203 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,203 | loss=8.6464 (p=8.4493 v=0.1971) | game=5.0s train=85.4s
+[2026-06-22 02:58:28] game= 3204 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,204 | loss=9.1739 (p=8.4493 v=0.7247) | game=7.6s train=85.4s
+[2026-06-22 02:59:59] game= 3205 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,205 | loss=9.0939 (p=8.4493 v=0.6446) | game=5.0s train=85.5s
+[2026-06-22 03:01:30] game= 3206 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,206 | loss=9.0167 (p=8.4493 v=0.5674) | game=6.1s train=85.0s
+[2026-06-22 03:03:02] game= 3207 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,207 | loss=8.8913 (p=8.4493 v=0.4420) | game=7.2s train=84.9s
+[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