checkpoint @ game=4400 steps=4400

training_log.txt

@@ -4699,3 +4699,13 @@
 [2026-06-24 10:56:04] game= 4388 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,388 | loss=8.7248 (p=8.4493 v=0.2755) | game=5.6s train=94.6s
 [2026-06-24 10:57:45] game= 4389 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,389 | loss=8.7602 (p=8.4493 v=0.3109) | game=6.9s train=94.5s
 [2026-06-24 10:59:27] game= 4390 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,390 | loss=8.7084 (p=8.4493 v=0.2591) | game=4.7s train=96.8s
+[2026-06-24 11:01:10] game= 4391 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,391 | loss=8.6657 (p=8.4493 v=0.2165) | game=4.9s train=94.7s
+[2026-06-24 11:02:51] game= 4392 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,392 | loss=8.6590 (p=8.4493 v=0.2097) | game=6.1s train=94.8s
+[2026-06-24 11:04:31] game= 4393 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,393 | loss=8.6473 (p=8.4493 v=0.1980) | game=4.7s train=94.7s
+[2026-06-24 11:06:12] game= 4394 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,394 | loss=8.6217 (p=8.4493 v=0.1724) | game=6.3s train=94.7s
+[2026-06-24 11:07:52] game= 4395 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,395 | loss=8.6515 (p=8.4493 v=0.2022) | game=5.5s train=94.7s
+[2026-06-24 11:09:32] game= 4396 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,396 | loss=8.6480 (p=8.4493 v=0.1987) | game=5.2s train=94.7s
+[2026-06-24 11:11:12] game= 4397 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,397 | loss=8.5999 (p=8.4493 v=0.1506) | game=5.1s train=94.7s
+[2026-06-24 11:12:56] game= 4398 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=4,398 | loss=8.6388 (p=8.4493 v=0.1895) | game=7.1s train=97.4s
+[2026-06-24 11:14:38] game= 4399 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,399 | loss=8.5686 (p=8.4493 v=0.1193) | game=6.9s train=94.7s
+[2026-06-24 11:16:20] game= 4400 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,400 | loss=9.1367 (p=8.4493 v=0.6874) | game=7.5s train=94.8s