checkpoint @ game=1800 steps=1800

training_log.txt

@@ -2098,3 +2098,13 @@
 [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
+[2026-06-18 16:24:28] game= 1791 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=1,791 | loss=8.7746 (p=8.4493 v=0.3253) | game=6.5s train=90.4s
+[2026-06-18 16:26:04] game= 1792 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=1,792 | loss=8.7467 (p=8.4493 v=0.2974) | game=5.6s train=90.7s
+[2026-06-18 16:27:41] game= 1793 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=1,793 | loss=8.6908 (p=8.4493 v=0.2415) | game=5.7s train=90.6s
+[2026-06-18 16:29:24] game= 1794 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=1,794 | loss=8.6984 (p=8.4493 v=0.2491) | game=8.3s train=95.0s
+[2026-06-18 16:31:00] game= 1795 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,795 | loss=8.6571 (p=8.4493 v=0.2078) | game=5.2s train=90.6s
+[2026-06-18 16:32:38] game= 1796 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,796 | loss=8.6568 (p=8.4493 v=0.2075) | game=7.3s train=90.7s
+[2026-06-18 16:34:15] game= 1797 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=1,797 | loss=8.6396 (p=8.4493 v=0.1903) | game=6.8s train=90.7s
+[2026-06-18 16:35:51] game= 1798 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=1,798 | loss=8.6400 (p=8.4493 v=0.1907) | game=5.5s train=90.4s
+[2026-06-18 16:37:27] game= 1799 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=1,799 | loss=8.6344 (p=8.4493 v=0.1851) | game=5.2s train=90.2s
+[2026-06-18 16:39:05] game= 1800 | 1/2-1/2 | moves= 71 | buf=50,000 | steps=1,800 | loss=8.6029 (p=8.4493 v=0.1536) | game=7.3s train=90.8s