checkpoint @ game=650 steps=650

training_log.txt

@@ -941,3 +941,13 @@
 [2026-06-14 11:32:26] game=  638 | 1/2-1/2 | moves= 48 | buf=70,000 | steps=638 | loss=8.6435 (p=8.4493 v=0.1942) | game=4.7s train=162.2s
 [2026-06-14 11:35:13] game=  639 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=639 | loss=8.6119 (p=8.4493 v=0.1626) | game=5.2s train=162.2s
 [2026-06-14 11:38:02] game=  640 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=640 | loss=8.6130 (p=8.4493 v=0.1637) | game=6.4s train=162.2s
+[2026-06-14 11:40:54] game=  641 | 1/2-1/2 | moves= 70 | buf=70,000 | steps=641 | loss=8.5978 (p=8.4493 v=0.1485) | game=6.8s train=162.1s
+[2026-06-14 11:43:48] game=  642 | 1/2-1/2 | moves= 53 | buf=70,000 | steps=642 | loss=8.9778 (p=8.4493 v=0.5285) | game=9.8s train=163.7s
+[2026-06-14 11:46:34] game=  643 | 1/2-1/2 | moves= 46 | buf=70,000 | steps=643 | loss=8.9542 (p=8.4493 v=0.5049) | game=4.5s train=162.1s
+[2026-06-14 11:49:23] game=  644 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=644 | loss=8.9401 (p=8.4493 v=0.4908) | game=5.4s train=163.5s
+[2026-06-14 11:52:13] game=  645 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=645 | loss=8.8718 (p=8.4493 v=0.4225) | game=7.9s train=162.3s
+[2026-06-14 11:55:04] game=  646 | 1/2-1/2 | moves= 75 | buf=70,000 | steps=646 | loss=8.8252 (p=8.4493 v=0.3759) | game=7.3s train=163.7s
+[2026-06-14 11:57:55] game=  647 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=647 | loss=8.8273 (p=8.4493 v=0.3780) | game=7.9s train=162.3s
+[2026-06-14 12:00:43] game=  648 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=648 | loss=8.7640 (p=8.4493 v=0.3147) | game=5.0s train=163.7s
+[2026-06-14 12:03:32] game=  649 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=649 | loss=8.7678 (p=8.4493 v=0.3185) | game=6.5s train=162.2s
+[2026-06-14 12:06:19] game=  650 | 1/2-1/2 | moves= 47 | buf=70,000 | steps=650 | loss=8.7100 (p=8.4493 v=0.2608) | game=4.6s train=162.2s