checkpoint @ game=500 steps=500

training_log.txt

@@ -786,3 +786,13 @@
 [2026-06-14 04:14:11] game=  488 | 1/2-1/2 | moves= 74 | buf=70,000 | steps=488 | loss=8.9601 (p=8.4493 v=0.5108) | game=7.1s train=161.4s
 [2026-06-14 04:16:57] game=  489 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=489 | loss=8.9128 (p=8.4493 v=0.4635) | game=4.9s train=161.5s
 [2026-06-14 04:19:45] game=  490 | 1/2-1/2 | moves= 65 | buf=70,000 | steps=490 | loss=8.9349 (p=8.4493 v=0.4856) | game=6.3s train=161.5s
+[2026-06-14 04:22:36] game=  491 | 1/2-1/2 | moves= 69 | buf=70,000 | steps=491 | loss=8.9069 (p=8.4493 v=0.4576) | game=6.7s train=161.6s
+[2026-06-14 04:25:25] game=  492 | 1/2-1/2 | moves= 73 | buf=70,000 | steps=492 | loss=8.8972 (p=8.4493 v=0.4479) | game=7.5s train=161.3s
+[2026-06-14 04:28:13] game=  493 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=493 | loss=8.8726 (p=8.4493 v=0.4233) | game=6.5s train=161.4s
+[2026-06-14 04:31:02] game=  494 | 1/2-1/2 | moves= 73 | buf=70,000 | steps=494 | loss=8.8610 (p=8.4493 v=0.4117) | game=7.5s train=161.1s
+[2026-06-14 04:33:49] game=  495 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=495 | loss=8.8613 (p=8.4493 v=0.4120) | game=5.4s train=161.6s
+[2026-06-14 04:36:36] game=  496 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=496 | loss=8.8445 (p=8.4493 v=0.3952) | game=5.3s train=161.7s
+[2026-06-14 04:39:23] game=  497 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=497 | loss=8.8264 (p=8.4493 v=0.3771) | game=6.1s train=161.7s
+[2026-06-14 04:42:10] game=  498 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=498 | loss=8.8385 (p=8.4493 v=0.3892) | game=5.7s train=161.3s
+[2026-06-14 04:44:58] game=  499 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=499 | loss=8.8137 (p=8.4493 v=0.3644) | game=6.4s train=161.5s
+[2026-06-14 04:47:45] game=  500 | 1/2-1/2 | moves= 64 | buf=70,000 | steps=500 | loss=8.8018 (p=8.4493 v=0.3525) | game=6.2s train=161.0s