checkpoint @ game=2030 steps=2030

training_log.txt

@@ -2328,3 +2328,13 @@
 [2026-06-19 03:54:18] game= 2018 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=2,018 | loss=8.8194 (p=8.4493 v=0.3701) | game=4.8s train=86.2s
 [2026-06-19 03:55:53] game= 2019 | 1/2-1/2 | moves= 70 | buf=50,000 | steps=2,019 | loss=8.7985 (p=8.4493 v=0.3492) | game=7.0s train=88.0s
 [2026-06-19 03:57:25] game= 2020 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,020 | loss=8.7426 (p=8.4493 v=0.2933) | game=5.1s train=86.3s
+[2026-06-19 03:58:59] game= 2021 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=2,021 | loss=8.7107 (p=8.4493 v=0.2614) | game=5.0s train=86.1s
+[2026-06-19 04:00:33] game= 2022 | 1/2-1/2 | moves= 58 | buf=50,000 | steps=2,022 | loss=8.6936 (p=8.4493 v=0.2443) | game=5.8s train=88.1s
+[2026-06-19 04:02:05] game= 2023 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=2,023 | loss=8.6632 (p=8.4493 v=0.2139) | game=5.9s train=86.2s
+[2026-06-19 04:03:37] game= 2024 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=2,024 | loss=8.7213 (p=8.4493 v=0.2720) | game=6.0s train=86.0s
+[2026-06-19 04:05:09] game= 2025 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=2,025 | loss=8.6481 (p=8.4493 v=0.1988) | game=5.7s train=86.1s
+[2026-06-19 04:06:42] game= 2026 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=2,026 | loss=8.6159 (p=8.4493 v=0.1666) | game=5.4s train=88.4s
+[2026-06-19 04:08:17] game= 2027 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=2,027 | loss=8.5980 (p=8.4493 v=0.1487) | game=8.1s train=86.2s
+[2026-06-19 04:09:48] game= 2028 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,028 | loss=8.6241 (p=8.4493 v=0.1748) | game=5.1s train=86.3s
+[2026-06-19 04:11:22] game= 2029 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=2,029 | loss=8.6120 (p=8.4493 v=0.1627) | game=5.1s train=88.4s
+[2026-06-19 04:12:53] game= 2030 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=2,030 | loss=8.5938 (p=8.4493 v=0.1445) | game=5.3s train=86.2s