checkpoint @ game=4750 steps=4750

training_log.txt

@@ -5049,3 +5049,13 @@
 [2026-06-25 08:53:13] game= 4738 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,738 | loss=8.5229 (p=8.4493 v=0.0736) | game=5.2s train=94.2s
 [2026-06-25 08:54:51] game= 4739 | 1/2-1/2 | moves= 78 | buf=50,000 | steps=4,739 | loss=8.5491 (p=8.4493 v=0.0998) | game=8.0s train=90.1s
 [2026-06-25 08:56:28] game= 4740 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,740 | loss=8.5361 (p=8.4493 v=0.0868) | game=5.8s train=90.3s
+[2026-06-25 08:58:08] game= 4741 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,741 | loss=8.5409 (p=8.4493 v=0.0916) | game=6.4s train=90.2s
+[2026-06-25 08:59:43] game= 4742 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=4,742 | loss=8.5601 (p=8.4493 v=0.1108) | game=4.7s train=90.4s
+[2026-06-25 09:01:22] game= 4743 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,743 | loss=8.5372 (p=8.4493 v=0.0879) | game=5.7s train=93.8s
+[2026-06-25 09:02:58] game= 4744 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,744 | loss=8.5400 (p=8.4493 v=0.0907) | game=5.5s train=90.2s
+[2026-06-25 09:04:35] game= 4745 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,745 | loss=8.5594 (p=8.4493 v=0.1101) | game=6.8s train=90.5s
+[2026-06-25 09:06:14] game= 4746 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=4,746 | loss=8.5398 (p=8.4493 v=0.0905) | game=7.8s train=90.4s
+[2026-06-25 09:07:50] game= 4747 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,747 | loss=8.5261 (p=8.4493 v=0.0768) | game=6.2s train=90.4s
+[2026-06-25 09:09:29] game= 4748 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,748 | loss=8.5344 (p=8.4493 v=0.0851) | game=8.2s train=90.5s
+[2026-06-25 09:11:09] game= 4749 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,749 | loss=8.5190 (p=8.4493 v=0.0697) | game=5.6s train=94.7s
+[2026-06-25 09:12:47] game= 4750 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=4,750 | loss=8.5415 (p=8.4493 v=0.0922) | game=8.0s train=90.1s