checkpoint @ game=3510 steps=3510

training_log.txt

@@ -3809,3 +3809,13 @@
 [2026-06-22 10:42:20] game= 3498 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,498 | loss=8.6908 (p=8.4493 v=0.2415) | game=5.1s train=86.3s
 [2026-06-22 10:43:54] game= 3499 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=3,499 | loss=8.6822 (p=8.4493 v=0.2330) | game=7.9s train=86.4s
 [2026-06-22 10:45:28] game= 3500 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,500 | loss=8.6502 (p=8.4493 v=0.2009) | game=5.2s train=88.2s
+[2026-06-22 10:47:02] game= 3501 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=3,501 | loss=8.6532 (p=8.4493 v=0.2039) | game=4.6s train=86.5s
+[2026-06-22 10:48:34] game= 3502 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=3,502 | loss=8.6405 (p=8.4493 v=0.1912) | game=5.4s train=86.4s
+[2026-06-22 10:50:10] game= 3503 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=3,503 | loss=9.1382 (p=8.4493 v=0.6889) | game=9.2s train=86.3s
+[2026-06-22 10:51:46] game= 3504 | 1/2-1/2 | moves= 80 | buf=50,000 | steps=3,504 | loss=9.0391 (p=8.4493 v=0.5898) | game=8.1s train=88.4s
+[2026-06-22 10:53:19] game= 3505 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=3,505 | loss=8.9631 (p=8.4493 v=0.5138) | game=6.1s train=86.5s
+[2026-06-22 10:54:50] game= 3506 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,506 | loss=8.8640 (p=8.4493 v=0.4147) | game=5.3s train=86.5s
+[2026-06-22 10:56:24] game= 3507 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=3,507 | loss=8.8662 (p=8.4493 v=0.4169) | game=5.6s train=88.4s
+[2026-06-22 10:57:59] game= 3508 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,508 | loss=8.7361 (p=8.4493 v=0.2868) | game=8.1s train=86.6s
+[2026-06-22 10:59:32] game= 3509 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,509 | loss=8.8170 (p=8.4493 v=0.3677) | game=6.5s train=86.6s
+[2026-06-22 11:01:06] game= 3510 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,510 | loss=8.7754 (p=8.4493 v=0.3261) | game=6.9s train=86.6s