checkpoint @ game=590 steps=590

training_log.txt

@@ -881,3 +881,13 @@
 [2026-06-14 08:44:09] game=  578 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=578 | loss=8.8513 (p=8.4493 v=0.4020) | game=4.7s train=161.1s
 [2026-06-14 08:46:56] game=  579 | 1/2-1/2 | moves= 53 | buf=70,000 | steps=579 | loss=8.8389 (p=8.4493 v=0.3896) | game=5.2s train=161.5s
 [2026-06-14 08:49:42] game=  580 | 1/2-1/2 | moves= 48 | buf=70,000 | steps=580 | loss=8.7986 (p=8.4493 v=0.3493) | game=4.7s train=161.9s
+[2026-06-14 08:52:33] game=  581 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=581 | loss=8.7717 (p=8.4493 v=0.3224) | game=5.7s train=161.6s
+[2026-06-14 08:55:20] game=  582 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=582 | loss=8.7760 (p=8.4493 v=0.3267) | game=5.9s train=162.0s
+[2026-06-14 08:58:09] game=  583 | 1/2-1/2 | moves= 72 | buf=70,000 | steps=583 | loss=8.7262 (p=8.4493 v=0.2769) | game=7.0s train=161.9s
+[2026-06-14 09:00:56] game=  584 | 1/2-1/2 | moves= 50 | buf=70,000 | steps=584 | loss=8.7216 (p=8.4493 v=0.2723) | game=4.8s train=162.1s
+[2026-06-14 09:03:43] game=  585 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=585 | loss=8.7069 (p=8.4493 v=0.2576) | game=5.0s train=161.4s
+[2026-06-14 09:06:29] game=  586 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=586 | loss=8.6790 (p=8.4493 v=0.2297) | game=4.7s train=161.3s
+[2026-06-14 09:09:17] game=  587 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=587 | loss=8.6816 (p=8.4493 v=0.2323) | game=6.3s train=162.0s
+[2026-06-14 09:12:06] game=  588 | 1/2-1/2 | moves= 69 | buf=70,000 | steps=588 | loss=8.6770 (p=8.4493 v=0.2277) | game=6.7s train=162.1s
+[2026-06-14 09:14:52] game=  589 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=589 | loss=8.6628 (p=8.4493 v=0.2135) | game=5.0s train=161.5s
+[2026-06-14 09:17:40] game=  590 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=590 | loss=8.6239 (p=8.4493 v=0.1746) | game=4.9s train=162.3s