checkpoint @ game=1790 steps=1790

training_log.txt

@@ -2088,3 +2088,13 @@
 [2026-06-18 16:03:14] game= 1778 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=1,778 | loss=8.6691 (p=8.4493 v=0.2198) | game=5.3s train=89.8s
 [2026-06-18 16:04:56] game= 1779 | 1/2-1/2 | moves= 77 | buf=50,000 | steps=1,779 | loss=8.6542 (p=8.4493 v=0.2049) | game=7.8s train=94.6s
 [2026-06-18 16:06:32] game= 1780 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=1,780 | loss=8.6336 (p=8.4493 v=0.1843) | game=5.1s train=90.6s
+[2026-06-18 16:08:10] game= 1781 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,781 | loss=8.6179 (p=8.4493 v=0.1686) | game=6.1s train=89.8s
+[2026-06-18 16:09:48] game= 1782 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=1,782 | loss=8.6403 (p=8.4493 v=0.1911) | game=7.5s train=90.2s
+[2026-06-18 16:11:24] game= 1783 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,783 | loss=8.6006 (p=8.4493 v=0.1513) | game=5.3s train=90.5s
+[2026-06-18 16:13:00] game= 1784 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,784 | loss=8.6040 (p=8.4493 v=0.1547) | game=6.5s train=89.9s
+[2026-06-18 16:14:38] game= 1785 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,785 | loss=8.5793 (p=8.4493 v=0.1300) | game=7.3s train=90.4s
+[2026-06-18 16:16:18] game= 1786 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,786 | loss=8.5548 (p=8.4493 v=0.1055) | game=5.5s train=94.5s
+[2026-06-18 16:17:59] game= 1787 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,787 | loss=9.0049 (p=8.4493 v=0.5556) | game=10.4s train=90.6s
+[2026-06-18 16:19:35] game= 1788 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=1,788 | loss=8.9412 (p=8.4493 v=0.4919) | game=6.0s train=90.2s
+[2026-06-18 16:21:13] game= 1789 | 1/2-1/2 | moves= 75 | buf=50,000 | steps=1,789 | loss=8.8875 (p=8.4493 v=0.4382) | game=7.7s train=90.3s
+[2026-06-18 16:22:48] game= 1790 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=1,790 | loss=8.8377 (p=8.4493 v=0.3884) | game=4.8s train=90.2s