checkpoint @ game=4150 steps=4150

training_log.txt

@@ -4449,3 +4449,13 @@
 [2026-06-24 03:28:30] game= 4138 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,138 | loss=8.8573 (p=8.4493 v=0.4080) | game=6.4s train=87.5s
 [2026-06-24 03:30:03] game= 4139 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,139 | loss=8.8088 (p=8.4493 v=0.3595) | game=5.5s train=87.4s
 [2026-06-24 03:31:37] game= 4140 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,140 | loss=8.7684 (p=8.4493 v=0.3191) | game=5.4s train=88.8s
+[2026-06-24 03:33:17] game= 4141 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,141 | loss=8.7312 (p=8.4493 v=0.2820) | game=6.5s train=87.5s
+[2026-06-24 03:34:50] game= 4142 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,142 | loss=8.7164 (p=8.4493 v=0.2671) | game=5.8s train=87.4s
+[2026-06-24 03:36:23] game= 4143 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,143 | loss=8.6554 (p=8.4493 v=0.2061) | game=5.3s train=87.5s
+[2026-06-24 03:37:57] game= 4144 | 1/2-1/2 | moves= 68 | buf=50,000 | steps=4,144 | loss=8.6725 (p=8.4493 v=0.2232) | game=6.7s train=87.4s
+[2026-06-24 03:39:31] game= 4145 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=4,145 | loss=8.6654 (p=8.4493 v=0.2161) | game=5.8s train=89.0s
+[2026-06-24 03:41:04] game= 4146 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,146 | loss=8.6646 (p=8.4493 v=0.2153) | game=5.0s train=87.5s
+[2026-06-24 03:42:36] game= 4147 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,147 | loss=8.6035 (p=8.4493 v=0.1542) | game=5.1s train=87.6s
+[2026-06-24 03:44:09] game= 4148 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,148 | loss=8.6062 (p=8.4493 v=0.1570) | game=4.9s train=87.4s
+[2026-06-24 03:45:44] game= 4149 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,149 | loss=8.6320 (p=8.4493 v=0.1827) | game=6.0s train=88.9s
+[2026-06-24 03:47:18] game= 4150 | 1/2-1/2 | moves= 66 | buf=50,000 | steps=4,150 | loss=8.6421 (p=8.4493 v=0.1928) | game=6.7s train=87.5s