checkpoint @ game=3290 steps=3290

training_log.txt

@@ -3589,3 +3589,13 @@
 [2026-06-22 04:52:50] game= 3278 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,278 | loss=8.7723 (p=8.4493 v=0.3230) | game=5.9s train=85.7s
 [2026-06-22 04:54:22] game= 3279 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,279 | loss=8.7430 (p=8.4493 v=0.2937) | game=5.2s train=87.0s
 [2026-06-22 04:55:54] game= 3280 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,280 | loss=8.7614 (p=8.4493 v=0.3121) | game=6.3s train=85.8s
+[2026-06-22 04:57:29] game= 3281 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=3,281 | loss=8.7129 (p=8.4493 v=0.2636) | game=6.5s train=85.9s
+[2026-06-22 04:59:02] game= 3282 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=3,282 | loss=8.7024 (p=8.4493 v=0.2531) | game=7.2s train=86.0s
+[2026-06-22 05:00:33] game= 3283 | 1/2-1/2 | moves= 46 | buf=50,000 | steps=3,283 | loss=8.6237 (p=8.4493 v=0.1744) | game=4.6s train=85.9s
+[2026-06-22 05:02:08] game= 3284 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=3,284 | loss=8.6557 (p=8.4493 v=0.2064) | game=8.0s train=87.3s
+[2026-06-22 05:03:39] game= 3285 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=3,285 | loss=8.6370 (p=8.4493 v=0.1877) | game=5.1s train=85.8s
+[2026-06-22 05:05:12] game= 3286 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=3,286 | loss=8.6514 (p=8.4493 v=0.2021) | game=5.3s train=87.3s
+[2026-06-22 05:06:42] game= 3287 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=3,287 | loss=8.6519 (p=8.4493 v=0.2026) | game=5.0s train=85.9s
+[2026-06-22 05:08:15] game= 3288 | 1/2-1/2 | moves= 52 | buf=50,000 | steps=3,288 | loss=8.6430 (p=8.4493 v=0.1937) | game=5.2s train=87.4s
+[2026-06-22 05:09:50] game= 3289 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=3,289 | loss=9.1998 (p=8.4493 v=0.7505) | game=8.8s train=85.8s
+[2026-06-22 05:11:23] game= 3290 | 1/2-1/2 | moves= 79 | buf=50,000 | steps=3,290 | loss=9.0822 (p=8.4493 v=0.6329) | game=7.8s train=85.9s