checkpoint @ game=520 steps=520

training_log.txt

@@ -806,3 +806,13 @@
 [2026-06-14 05:10:12] game=  508 | 1/2-1/2 | moves= 53 | buf=70,000 | steps=508 | loss=8.9242 (p=8.4493 v=0.4749) | game=5.1s train=161.9s
 [2026-06-14 05:12:58] game=  509 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=509 | loss=8.9066 (p=8.4493 v=0.4573) | game=5.0s train=161.3s
 [2026-06-14 05:15:45] game=  510 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=510 | loss=8.8936 (p=8.4493 v=0.4443) | game=4.9s train=162.0s
+[2026-06-14 05:18:35] game=  511 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=511 | loss=8.8714 (p=8.4493 v=0.4221) | game=4.7s train=162.1s
+[2026-06-14 05:21:24] game=  512 | 1/2-1/2 | moves= 68 | buf=70,000 | steps=512 | loss=8.8381 (p=8.4493 v=0.3888) | game=6.6s train=161.8s
+[2026-06-14 05:24:10] game=  513 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=513 | loss=8.8497 (p=8.4493 v=0.4004) | game=5.3s train=161.4s
+[2026-06-14 05:26:58] game=  514 | 1/2-1/2 | moves= 66 | buf=70,000 | steps=514 | loss=8.8313 (p=8.4493 v=0.3820) | game=6.3s train=161.4s
+[2026-06-14 05:29:45] game=  515 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=515 | loss=8.8395 (p=8.4493 v=0.3902) | game=4.7s train=162.3s
+[2026-06-14 05:32:30] game=  516 | 1-0 | moves= 31 | buf=70,000 | steps=516 | loss=8.8081 (p=8.4493 v=0.3588) | game=3.0s train=161.9s
+[2026-06-14 05:35:17] game=  517 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=517 | loss=8.7828 (p=8.4493 v=0.3335) | game=5.0s train=162.0s
+[2026-06-14 05:38:05] game=  518 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=518 | loss=8.7728 (p=8.4493 v=0.3235) | game=6.3s train=162.0s
+[2026-06-14 05:40:54] game=  519 | 1/2-1/2 | moves= 71 | buf=70,000 | steps=519 | loss=8.7599 (p=8.4493 v=0.3106) | game=6.9s train=162.3s
+[2026-06-14 05:43:42] game=  520 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=520 | loss=8.7629 (p=8.4493 v=0.3136) | game=5.3s train=162.1s