checkpoint @ game=4350 steps=4350

training_log.txt

@@ -4649,3 +4649,13 @@
 [2026-06-24 09:31:35] game= 4338 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,338 | loss=8.7912 (p=8.4493 v=0.3419) | game=5.9s train=94.0s
 [2026-06-24 09:33:15] game= 4339 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,339 | loss=8.6937 (p=8.4493 v=0.2444) | game=6.6s train=93.9s
 [2026-06-24 09:34:59] game= 4340 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,340 | loss=8.7081 (p=8.4493 v=0.2588) | game=8.1s train=95.3s
+[2026-06-24 09:36:41] game= 4341 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,341 | loss=8.6891 (p=8.4493 v=0.2398) | game=5.0s train=93.9s
+[2026-06-24 09:38:20] game= 4342 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,342 | loss=8.6685 (p=8.4493 v=0.2192) | game=5.2s train=94.0s
+[2026-06-24 09:40:01] game= 4343 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,343 | loss=8.6501 (p=8.4493 v=0.2008) | game=6.9s train=93.9s
+[2026-06-24 09:41:40] game= 4344 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,344 | loss=8.6075 (p=8.4493 v=0.1582) | game=5.3s train=93.9s
+[2026-06-24 09:43:23] game= 4345 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,345 | loss=8.6407 (p=8.4493 v=0.1914) | game=7.6s train=95.6s
+[2026-06-24 09:45:02] game= 4346 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,346 | loss=8.6314 (p=8.4493 v=0.1821) | game=4.8s train=94.0s
+[2026-06-24 09:46:45] game= 4347 | 1/2-1/2 | moves= 74 | buf=50,000 | steps=4,347 | loss=8.6215 (p=8.4493 v=0.1722) | game=7.4s train=95.6s
+[2026-06-24 09:48:24] game= 4348 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,348 | loss=8.6422 (p=8.4493 v=0.1929) | game=5.5s train=94.0s
+[2026-06-24 09:50:09] game= 4349 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=4,349 | loss=9.2133 (p=8.4493 v=0.7640) | game=10.4s train=94.0s
+[2026-06-24 09:51:49] game= 4350 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,350 | loss=9.0098 (p=8.4493 v=0.5605) | game=5.7s train=94.0s