checkpoint @ game=4420 steps=4420

training_log.txt

@@ -4719,3 +4719,13 @@
 [2026-06-24 11:29:55] game= 4408 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,408 | loss=8.6568 (p=8.4493 v=0.2075) | game=5.8s train=94.9s
 [2026-06-24 11:31:36] game= 4409 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,409 | loss=8.6659 (p=8.4493 v=0.2166) | game=5.7s train=94.9s
 [2026-06-24 11:33:19] game= 4410 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,410 | loss=8.6766 (p=8.4493 v=0.2273) | game=5.9s train=97.4s
+[2026-06-24 11:35:05] game= 4411 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,411 | loss=8.6847 (p=8.4493 v=0.2354) | game=8.2s train=95.0s
+[2026-06-24 11:36:45] game= 4412 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,412 | loss=8.6147 (p=8.4493 v=0.1654) | game=5.1s train=95.0s
+[2026-06-24 11:38:29] game= 4413 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,413 | loss=8.6102 (p=8.4493 v=0.1609) | game=6.1s train=97.6s
+[2026-06-24 11:40:11] game= 4414 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,414 | loss=8.6172 (p=8.4493 v=0.1679) | game=7.0s train=95.0s
+[2026-06-24 11:41:51] game= 4415 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,415 | loss=8.6118 (p=8.4493 v=0.1625) | game=5.4s train=95.0s
+[2026-06-24 11:43:33] game= 4416 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,416 | loss=8.6077 (p=8.4493 v=0.1584) | game=6.5s train=95.0s
+[2026-06-24 11:45:16] game= 4417 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,417 | loss=9.1241 (p=8.4493 v=0.6748) | game=8.4s train=94.9s
+[2026-06-24 11:46:59] game= 4418 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,418 | loss=9.0575 (p=8.4493 v=0.6082) | game=4.9s train=97.5s
+[2026-06-24 11:48:39] game= 4419 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,419 | loss=8.9874 (p=8.4493 v=0.5381) | game=4.8s train=95.0s
+[2026-06-24 11:50:20] game= 4420 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,420 | loss=8.9275 (p=8.4493 v=0.4782) | game=6.0s train=95.1s