checkpoint @ game=4030 steps=4030

training_log.txt

@@ -4329,3 +4329,13 @@
 [2026-06-23 11:08:51] game= 4018 | 1/2-1/2 | moves= 53 | buf=50,000 | steps=4,018 | loss=8.7071 (p=8.4493 v=0.2578) | game=6.3s train=98.6s
 [2026-06-23 11:10:41] game= 4019 | 1/2-1/2 | moves= 65 | buf=50,000 | steps=4,019 | loss=8.7236 (p=8.4493 v=0.2743) | game=7.6s train=103.1s
 [2026-06-23 11:12:27] game= 4020 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,020 | loss=8.7184 (p=8.4493 v=0.2691) | game=7.2s train=98.7s
+[2026-06-23 11:14:15] game= 4021 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,021 | loss=8.6850 (p=8.4493 v=0.2357) | game=7.2s train=96.3s
+[2026-06-23 11:15:57] game= 4022 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,022 | loss=8.6464 (p=8.4493 v=0.1971) | game=5.9s train=96.5s
+[2026-06-23 11:17:42] game= 4023 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,023 | loss=8.6720 (p=8.4493 v=0.2227) | game=9.3s train=95.8s
+[2026-06-23 11:19:27] game= 4024 | 1/2-1/2 | moves= 81 | buf=50,000 | steps=4,024 | loss=8.6320 (p=8.4493 v=0.1827) | game=8.3s train=96.4s
+[2026-06-23 11:21:10] game= 4025 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,025 | loss=8.6015 (p=8.4493 v=0.1522) | game=5.8s train=97.2s
+[2026-06-23 11:22:53] game= 4026 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,026 | loss=8.6136 (p=8.4493 v=0.1643) | game=6.1s train=97.5s
+[2026-06-23 11:24:37] game= 4027 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,027 | loss=8.6145 (p=8.4493 v=0.1652) | game=5.6s train=97.5s
+[2026-06-23 11:26:29] game= 4028 | 1/2-1/2 | moves= 61 | buf=50,000 | steps=4,028 | loss=9.1786 (p=8.4493 v=0.7293) | game=15.2s train=97.3s
+[2026-06-23 11:28:15] game= 4029 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,029 | loss=9.1194 (p=8.4493 v=0.6701) | game=7.3s train=98.3s
+[2026-06-23 11:29:59] game= 4030 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,030 | loss=9.0127 (p=8.4493 v=0.5635) | game=5.8s train=98.5s