checkpoint @ game=3470 steps=3470

training_log.txt

@@ -3769,3 +3769,13 @@
 [2026-06-22 09:40:14] game= 3458 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,458 | loss=8.7832 (p=8.4493 v=0.3339) | game=5.6s train=87.3s
 [2026-06-22 09:41:46] game= 3459 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,459 | loss=8.7362 (p=8.4493 v=0.2869) | game=5.7s train=85.8s
 [2026-06-22 09:43:19] game= 3460 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=3,460 | loss=8.7283 (p=8.4493 v=0.2790) | game=7.5s train=85.8s
+[2026-06-22 09:44:55] game= 3461 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,461 | loss=8.6741 (p=8.4493 v=0.2248) | game=6.4s train=87.3s
+[2026-06-22 09:46:30] game= 3462 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,462 | loss=8.7129 (p=8.4493 v=0.2636) | game=8.2s train=85.9s
+[2026-06-22 09:48:01] game= 3463 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,463 | loss=8.7084 (p=8.4493 v=0.2591) | game=5.1s train=85.9s
+[2026-06-22 09:49:33] game= 3464 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=3,464 | loss=8.6861 (p=8.4493 v=0.2368) | game=5.5s train=87.3s
+[2026-06-22 09:51:05] game= 3465 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,465 | loss=8.6563 (p=8.4493 v=0.2070) | game=5.2s train=85.9s
+[2026-06-22 09:52:36] game= 3466 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=3,466 | loss=8.6505 (p=8.4493 v=0.2012) | game=5.7s train=85.8s
+[2026-06-22 09:54:07] game= 3467 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=3,467 | loss=8.6709 (p=8.4493 v=0.2217) | game=4.7s train=85.8s
+[2026-06-22 09:55:41] game= 3468 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,468 | loss=8.6316 (p=8.4493 v=0.1823) | game=8.1s train=86.0s
+[2026-06-22 09:57:18] game= 3469 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,469 | loss=9.1578 (p=8.4493 v=0.7085) | game=9.3s train=87.6s
+[2026-06-22 09:58:50] game= 3470 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=3,470 | loss=9.1192 (p=8.4493 v=0.6699) | game=6.0s train=86.0s