checkpoint @ game=540 steps=540

training_log.txt

@@ -826,3 +826,13 @@
 [2026-06-14 06:06:09] game=  528 | 1/2-1/2 | moves= 66 | buf=70,000 | steps=528 | loss=8.8163 (p=8.4493 v=0.3670) | game=6.4s train=161.5s
 [2026-06-14 06:08:56] game=  529 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=529 | loss=8.8048 (p=8.4493 v=0.3555) | game=4.8s train=162.6s
 [2026-06-14 06:11:44] game=  530 | 1/2-1/2 | moves= 64 | buf=70,000 | steps=530 | loss=8.7688 (p=8.4493 v=0.3195) | game=6.2s train=162.2s
+[2026-06-14 06:14:35] game=  531 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=531 | loss=8.7566 (p=8.4493 v=0.3073) | game=5.8s train=161.6s
+[2026-06-14 06:17:23] game=  532 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=532 | loss=8.7515 (p=8.4493 v=0.3022) | game=5.7s train=162.7s
+[2026-06-14 06:20:10] game=  533 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=533 | loss=8.7363 (p=8.4493 v=0.2870) | game=5.2s train=161.8s
+[2026-06-14 06:22:59] game=  534 | 1/2-1/2 | moves= 70 | buf=70,000 | steps=534 | loss=8.7210 (p=8.4493 v=0.2717) | game=6.7s train=162.4s
+[2026-06-14 06:25:47] game=  535 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=535 | loss=8.6916 (p=8.4493 v=0.2423) | game=4.9s train=162.7s
+[2026-06-14 06:28:34] game=  536 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=536 | loss=8.6897 (p=8.4493 v=0.2404) | game=4.9s train=162.6s
+[2026-06-14 06:31:22] game=  537 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=537 | loss=8.6921 (p=8.4493 v=0.2428) | game=5.7s train=161.6s
+[2026-06-14 06:34:15] game=  538 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=538 | loss=8.9578 (p=8.4493 v=0.5085) | game=11.8s train=161.7s
+[2026-06-14 06:37:02] game=  539 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=539 | loss=8.9390 (p=8.4493 v=0.4897) | game=5.3s train=161.7s
+[2026-06-14 06:39:51] game=  540 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=540 | loss=8.9510 (p=8.4493 v=0.5017) | game=5.7s train=162.7s