checkpoint @ game=1240 steps=1240

training_log.txt

@@ -1538,3 +1538,13 @@
 [2026-06-17 13:10:49] game= 1228 | 1/2-1/2 | moves= 62 | buf=70,000 | steps=1,228 | loss=8.5549 (p=8.4493 v=0.1056) | game=6.0s train=160.6s
 [2026-06-17 13:13:38] game= 1229 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=1,229 | loss=8.5379 (p=8.4493 v=0.0886) | game=7.8s train=161.2s
 [2026-06-17 13:16:25] game= 1230 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=1,230 | loss=8.5474 (p=8.4493 v=0.0981) | game=5.6s train=161.8s
+[2026-06-17 13:19:20] game= 1231 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=1,231 | loss=8.9636 (p=8.4493 v=0.5143) | game=11.0s train=161.4s
+[2026-06-17 13:22:08] game= 1232 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=1,232 | loss=8.8934 (p=8.4493 v=0.4441) | game=5.6s train=161.7s
+[2026-06-17 13:24:56] game= 1233 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=1,233 | loss=8.8370 (p=8.4493 v=0.3877) | game=7.9s train=160.8s
+[2026-06-17 13:27:44] game= 1234 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=1,234 | loss=8.7428 (p=8.4493 v=0.2935) | game=7.0s train=160.8s
+[2026-06-17 13:30:31] game= 1235 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=1,235 | loss=8.7329 (p=8.4493 v=0.2836) | game=5.3s train=161.7s
+[2026-06-17 13:33:18] game= 1236 | 1/2-1/2 | moves= 62 | buf=70,000 | steps=1,236 | loss=8.6711 (p=8.4493 v=0.2218) | game=6.0s train=160.8s
+[2026-06-17 13:36:05] game= 1237 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=1,237 | loss=8.6396 (p=8.4493 v=0.1903) | game=5.9s train=160.8s
+[2026-06-17 13:38:51] game= 1238 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=1,238 | loss=8.6545 (p=8.4493 v=0.2052) | game=4.8s train=161.7s
+[2026-06-17 13:41:38] game= 1239 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=1,239 | loss=8.6258 (p=8.4493 v=0.1765) | game=5.0s train=161.7s
+[2026-06-17 13:44:25] game= 1240 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=1,240 | loss=8.6029 (p=8.4493 v=0.1536) | game=6.7s train=160.9s