checkpoint @ game=820 steps=820

training_log.txt

@@ -1111,3 +1111,13 @@
 [2026-06-15 06:51:06] game=  808 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=808 | loss=8.9659 (p=8.4493 v=0.5166) | game=12.5s train=179.2s
 [2026-06-15 06:54:10] game=  809 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=809 | loss=8.9736 (p=8.4493 v=0.5243) | game=5.5s train=179.0s
 [2026-06-15 06:57:14] game=  810 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=810 | loss=8.9027 (p=8.4493 v=0.4534) | game=5.4s train=178.2s
+[2026-06-15 07:00:21] game=  811 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=811 | loss=8.8633 (p=8.4493 v=0.4140) | game=4.8s train=179.2s
+[2026-06-15 07:03:24] game=  812 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=812 | loss=8.8275 (p=8.4493 v=0.3782) | game=5.6s train=178.3s
+[2026-06-15 07:06:29] game=  813 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=813 | loss=8.7789 (p=8.4493 v=0.3296) | game=6.1s train=178.2s
+[2026-06-15 07:09:33] game=  814 | 1/2-1/2 | moves= 64 | buf=70,000 | steps=814 | loss=8.7368 (p=8.4493 v=0.2875) | game=6.2s train=178.2s
+[2026-06-15 07:12:39] game=  815 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=815 | loss=8.7408 (p=8.4493 v=0.2915) | game=7.6s train=178.2s
+[2026-06-15 07:15:42] game=  816 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=816 | loss=8.7176 (p=8.4493 v=0.2683) | game=5.0s train=178.2s
+[2026-06-15 07:18:49] game=  817 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=817 | loss=8.6791 (p=8.4493 v=0.2298) | game=7.8s train=179.2s
+[2026-06-15 07:21:54] game=  818 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=818 | loss=8.6804 (p=8.4493 v=0.2311) | game=6.5s train=178.4s
+[2026-06-15 07:24:59] game=  819 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=819 | loss=8.6559 (p=8.4493 v=0.2066) | game=6.6s train=178.3s
+[2026-06-15 07:28:04] game=  820 | 1/2-1/2 | moves= 68 | buf=70,000 | steps=820 | loss=8.6454 (p=8.4493 v=0.1961) | game=6.5s train=179.1s