checkpoint @ game=690 steps=690

training_log.txt

@@ -981,3 +981,13 @@
 [2026-06-14 13:25:27] game=  678 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=678 | loss=8.9301 (p=8.4493 v=0.4808) | game=7.9s train=162.8s
 [2026-06-14 13:28:17] game=  679 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=679 | loss=8.8782 (p=8.4493 v=0.4289) | game=5.4s train=164.7s
 [2026-06-14 13:31:06] game=  680 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=680 | loss=8.8281 (p=8.4493 v=0.3788) | game=6.1s train=162.7s
+[2026-06-14 13:33:58] game=  681 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=681 | loss=8.7988 (p=8.4493 v=0.3495) | game=6.0s train=162.6s
+[2026-06-14 13:36:49] game=  682 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=682 | loss=8.7632 (p=8.4493 v=0.3139) | game=6.6s train=164.5s
+[2026-06-14 13:39:39] game=  683 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=683 | loss=8.7610 (p=8.4493 v=0.3117) | game=6.5s train=162.9s
+[2026-06-14 13:42:26] game=  684 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=684 | loss=8.6836 (p=8.4493 v=0.2343) | game=4.9s train=162.6s
+[2026-06-14 13:45:16] game=  685 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=685 | loss=8.7152 (p=8.4493 v=0.2659) | game=5.1s train=164.3s
+[2026-06-14 13:48:03] game=  686 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=686 | loss=8.6714 (p=8.4493 v=0.2221) | game=4.8s train=162.7s
+[2026-06-14 13:50:52] game=  687 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=687 | loss=8.6808 (p=8.4493 v=0.2315) | game=6.0s train=162.6s
+[2026-06-14 13:53:42] game=  688 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=688 | loss=8.6585 (p=8.4493 v=0.2092) | game=5.6s train=164.5s
+[2026-06-14 13:56:30] game=  689 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=689 | loss=8.6411 (p=8.4493 v=0.1918) | game=5.4s train=162.8s
+[2026-06-14 13:59:18] game=  690 | 1/2-1/2 | moves= 48 | buf=70,000 | steps=690 | loss=8.6463 (p=8.4493 v=0.1970) | game=4.7s train=162.7s