checkpoint @ game=870 steps=870

training_log.txt

@@ -1161,3 +1161,13 @@
 [2026-06-15 09:25:32] game=  858 | 1/2-1/2 | moves= 59 | buf=70,000 | steps=858 | loss=8.5860 (p=8.4493 v=0.1367) | game=5.7s train=178.8s
 [2026-06-15 09:28:41] game=  859 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=859 | loss=8.9749 (p=8.4493 v=0.5256) | game=10.0s train=178.7s
 [2026-06-15 09:31:46] game=  860 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=860 | loss=8.9527 (p=8.4493 v=0.5034) | game=4.9s train=180.4s
+[2026-06-15 09:34:54] game=  861 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=861 | loss=8.9222 (p=8.4493 v=0.4729) | game=5.9s train=178.8s
+[2026-06-15 09:37:58] game=  862 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=862 | loss=8.8403 (p=8.4493 v=0.3910) | game=5.3s train=178.8s
+[2026-06-15 09:41:04] game=  863 | 1/2-1/2 | moves= 49 | buf=70,000 | steps=863 | loss=8.8186 (p=8.4493 v=0.3693) | game=4.8s train=180.6s
+[2026-06-15 09:44:09] game=  864 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=864 | loss=8.7918 (p=8.4493 v=0.3425) | game=5.9s train=178.9s
+[2026-06-15 09:47:12] game=  865 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=865 | loss=8.7268 (p=8.4493 v=0.2775) | game=5.0s train=179.0s
+[2026-06-15 09:50:20] game=  866 | 1/2-1/2 | moves= 75 | buf=70,000 | steps=866 | loss=8.7046 (p=8.4493 v=0.2553) | game=7.2s train=180.6s
+[2026-06-15 09:53:24] game=  867 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=867 | loss=8.6933 (p=8.4493 v=0.2440) | game=5.0s train=178.9s
+[2026-06-15 09:56:28] game=  868 | 1/2-1/2 | moves= 54 | buf=70,000 | steps=868 | loss=8.6719 (p=8.4493 v=0.2226) | game=5.2s train=178.8s
+[2026-06-15 09:59:35] game=  869 | 1/2-1/2 | moves= 67 | buf=70,000 | steps=869 | loss=8.6701 (p=8.4493 v=0.2208) | game=6.5s train=180.7s
+[2026-06-15 10:02:40] game=  870 | 1/2-1/2 | moves= 61 | buf=70,000 | steps=870 | loss=8.6355 (p=8.4493 v=0.1862) | game=5.9s train=179.0s