checkpoint @ game=4500 steps=4500

training_log.txt

@@ -4799,3 +4799,13 @@
 [2026-06-25 02:11:34] game= 4488 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,488 | loss=8.6132 (p=8.4493 v=0.1639) | game=6.6s train=88.5s
 [2026-06-25 02:13:08] game= 4489 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,489 | loss=8.6361 (p=8.4493 v=0.1868) | game=6.2s train=88.0s
 [2026-06-25 02:14:41] game= 4490 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=4,490 | loss=8.6364 (p=8.4493 v=0.1871) | game=5.3s train=88.5s
+[2026-06-25 02:16:20] game= 4491 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,491 | loss=8.5853 (p=8.4493 v=0.1360) | game=7.2s train=88.2s
+[2026-06-25 02:17:54] game= 4492 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,492 | loss=8.5924 (p=8.4493 v=0.1431) | game=6.9s train=87.9s
+[2026-06-25 02:19:30] game= 4493 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=4,493 | loss=8.6129 (p=8.4493 v=0.1636) | game=8.6s train=87.1s
+[2026-06-25 02:21:06] game= 4494 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,494 | loss=9.1370 (p=8.4493 v=0.6877) | game=8.0s train=87.7s
+[2026-06-25 02:22:40] game= 4495 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,495 | loss=9.0746 (p=8.4493 v=0.6253) | game=6.1s train=88.4s
+[2026-06-25 02:24:14] game= 4496 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,496 | loss=8.9539 (p=8.4493 v=0.5046) | game=5.3s train=88.5s
+[2026-06-25 02:25:48] game= 4497 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,497 | loss=8.8667 (p=8.4493 v=0.4174) | game=5.6s train=88.1s
+[2026-06-25 02:27:23] game= 4498 | 1/2-1/2 | moves= 69 | buf=50,000 | steps=4,498 | loss=8.8597 (p=8.4493 v=0.4105) | game=7.4s train=87.6s
+[2026-06-25 02:29:00] game= 4499 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,499 | loss=8.7914 (p=8.4493 v=0.3421) | game=8.8s train=88.4s
+[2026-06-25 02:30:35] game= 4500 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,500 | loss=8.7396 (p=8.4493 v=0.2903) | game=6.1s train=89.0s