checkpoint @ game=1050 steps=1050

training_log.txt

@@ -1343,3 +1343,13 @@
 [2026-06-16 06:14:27] game= 1038 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=1,038 | loss=8.5639 (p=8.4493 v=0.1146) | game=5.6s train=165.2s
 [2026-06-16 06:17:16] game= 1039 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=1,039 | loss=8.5613 (p=8.4493 v=0.1120) | game=4.9s train=163.8s
 [2026-06-16 06:20:08] game= 1040 | 1/2-1/2 | moves= 71 | buf=70,000 | steps=1,040 | loss=8.5503 (p=8.4493 v=0.1010) | game=6.9s train=165.4s
+[2026-06-16 06:23:01] game= 1041 | 1/2-1/2 | moves= 68 | buf=70,000 | steps=1,041 | loss=8.5422 (p=8.4493 v=0.0929) | game=6.7s train=163.8s
+[2026-06-16 06:25:55] game= 1042 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=1,042 | loss=8.9861 (p=8.4493 v=0.5368) | game=10.2s train=163.9s
+[2026-06-16 06:28:46] game= 1043 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=1,043 | loss=8.9757 (p=8.4493 v=0.5264) | game=7.0s train=163.9s
+[2026-06-16 06:31:35] game= 1044 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=1,044 | loss=8.8442 (p=8.4493 v=0.3949) | game=5.0s train=163.9s
+[2026-06-16 06:34:28] game= 1045 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=1,045 | loss=8.8120 (p=8.4493 v=0.3627) | game=7.9s train=165.4s
+[2026-06-16 06:37:17] game= 1046 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=1,046 | loss=8.7612 (p=8.4493 v=0.3119) | game=5.1s train=163.8s
+[2026-06-16 06:40:06] game= 1047 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=1,047 | loss=8.7009 (p=8.4493 v=0.2516) | game=5.0s train=164.0s
+[2026-06-16 06:42:58] game= 1048 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=1,048 | loss=8.6726 (p=8.4493 v=0.2233) | game=6.2s train=165.5s
+[2026-06-16 06:45:47] game= 1049 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=1,049 | loss=8.6722 (p=8.4493 v=0.2229) | game=5.6s train=163.9s
+[2026-06-16 06:48:38] game= 1050 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=1,050 | loss=8.6575 (p=8.4493 v=0.2082) | game=5.7s train=165.3s