checkpoint @ game=3240 steps=3240

training_log.txt

@@ -3539,3 +3539,13 @@
 [2026-06-22 03:35:13] game= 3228 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,228 | loss=8.7620 (p=8.4493 v=0.3127) | game=4.8s train=86.0s
 [2026-06-22 03:36:45] game= 3229 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,229 | loss=8.7347 (p=8.4493 v=0.2854) | game=5.6s train=86.0s
 [2026-06-22 03:38:15] game= 3230 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,230 | loss=8.7603 (p=8.4493 v=0.3110) | game=4.9s train=85.2s
+[2026-06-22 03:39:50] game= 3231 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,231 | loss=8.6913 (p=8.4493 v=0.2420) | game=5.2s train=86.0s
+[2026-06-22 03:41:22] game= 3232 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,232 | loss=8.7198 (p=8.4493 v=0.2705) | game=5.7s train=86.2s
+[2026-06-22 03:42:54] game= 3233 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=3,233 | loss=8.7137 (p=8.4493 v=0.2644) | game=5.9s train=86.1s
+[2026-06-22 03:44:25] game= 3234 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,234 | loss=8.6380 (p=8.4493 v=0.1887) | game=6.1s train=85.2s
+[2026-06-22 03:45:58] game= 3235 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=3,235 | loss=8.6520 (p=8.4493 v=0.2027) | game=7.2s train=86.2s
+[2026-06-22 03:47:30] game= 3236 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,236 | loss=8.6726 (p=8.4493 v=0.2233) | game=5.1s train=86.2s
+[2026-06-22 03:49:01] game= 3237 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,237 | loss=8.6273 (p=8.4493 v=0.1780) | game=6.3s train=85.2s
+[2026-06-22 03:50:35] game= 3238 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,238 | loss=9.1878 (p=8.4493 v=0.7385) | game=7.6s train=86.2s
+[2026-06-22 03:52:06] game= 3239 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,239 | loss=9.1449 (p=8.4493 v=0.6956) | game=5.9s train=85.4s
+[2026-06-22 03:53:37] game= 3240 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=3,240 | loss=8.9585 (p=8.4493 v=0.5092) | game=4.9s train=86.2s