checkpoint @ game=2540 steps=2540

training_log.txt

@@ -2838,3 +2838,13 @@
 [2026-06-20 06:51:22] game= 2528 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=2,528 | loss=8.5954 (p=8.4493 v=0.1461) | game=5.6s train=96.4s
 [2026-06-20 06:53:04] game= 2529 | 1/2-1/2 | moves= 73 | buf=50,000 | steps=2,529 | loss=8.5985 (p=8.4493 v=0.1492) | game=7.3s train=94.0s
 [2026-06-20 06:54:43] game= 2530 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=2,530 | loss=8.5934 (p=8.4493 v=0.1441) | game=5.6s train=94.0s
+[2026-06-20 06:56:26] game= 2531 | 1/2-1/2 | moves= 64 | buf=50,000 | steps=2,531 | loss=8.5669 (p=8.4493 v=0.1177) | game=6.4s train=94.0s
+[2026-06-20 06:58:08] game= 2532 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=2,532 | loss=8.5508 (p=8.4493 v=0.1015) | game=4.7s train=96.6s
+[2026-06-20 06:59:47] game= 2533 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,533 | loss=8.5488 (p=8.4493 v=0.0995) | game=5.2s train=94.0s
+[2026-06-20 07:01:31] game= 2534 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,534 | loss=8.7121 (p=8.4493 v=0.2628) | game=9.8s train=94.2s
+[2026-06-20 07:03:10] game= 2535 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,535 | loss=8.6902 (p=8.4493 v=0.2410) | game=5.1s train=94.0s
+[2026-06-20 07:04:49] game= 2536 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,536 | loss=8.7071 (p=8.4493 v=0.2578) | game=5.1s train=94.0s
+[2026-06-20 07:06:32] game= 2537 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=2,537 | loss=8.6873 (p=8.4493 v=0.2380) | game=6.9s train=96.5s
+[2026-06-20 07:08:12] game= 2538 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=2,538 | loss=8.6529 (p=8.4493 v=0.2036) | game=5.3s train=94.2s
+[2026-06-20 07:09:54] game= 2539 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=2,539 | loss=8.6362 (p=8.4493 v=0.1869) | game=8.1s train=94.2s
+[2026-06-20 07:11:33] game= 2540 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,540 | loss=8.6150 (p=8.4493 v=0.1657) | game=5.1s train=94.1s