checkpoint @ game=810 steps=810

training_log.txt

@@ -1101,3 +1101,13 @@
 [2026-06-15 06:20:13] game=  798 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=798 | loss=8.7168 (p=8.4493 v=0.2675) | game=4.9s train=179.0s
 [2026-06-15 06:23:17] game=  799 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=799 | loss=8.7132 (p=8.4493 v=0.2639) | game=5.3s train=178.1s
 [2026-06-15 06:26:21] game=  800 | 1/2-1/2 | moves= 55 | buf=70,000 | steps=800 | loss=8.6773 (p=8.4493 v=0.2280) | game=6.2s train=178.0s
+[2026-06-15 06:29:28] game=  801 | 1/2-1/2 | moves= 63 | buf=70,000 | steps=801 | loss=8.6546 (p=8.4493 v=0.2054) | game=6.1s train=178.0s
+[2026-06-15 06:32:33] game=  802 | 1/2-1/2 | moves= 66 | buf=70,000 | steps=802 | loss=8.6454 (p=8.4493 v=0.1961) | game=6.4s train=178.9s
+[2026-06-15 06:35:37] game=  803 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=803 | loss=8.6344 (p=8.4493 v=0.1851) | game=5.6s train=178.1s
+[2026-06-15 06:38:41] game=  804 | 1/2-1/2 | moves= 58 | buf=70,000 | steps=804 | loss=8.5951 (p=8.4493 v=0.1458) | game=5.6s train=179.1s
+[2026-06-15 06:41:44] game=  805 | 1/2-1/2 | moves= 51 | buf=70,000 | steps=805 | loss=8.6070 (p=8.4493 v=0.1577) | game=4.9s train=178.1s
+[2026-06-15 06:44:51] game=  806 | 1/2-1/2 | moves= 77 | buf=70,000 | steps=806 | loss=8.5776 (p=8.4493 v=0.1283) | game=7.4s train=179.1s
+[2026-06-15 06:47:54] game=  807 | 1/2-1/2 | moves= 52 | buf=70,000 | steps=807 | loss=8.5872 (p=8.4493 v=0.1379) | game=5.0s train=178.1s
+[2026-06-15 06:51:06] game=  808 | 1/2-1/2 | moves= 81 | buf=70,000 | steps=808 | loss=8.9659 (p=8.4493 v=0.5166) | game=12.5s train=179.2s
+[2026-06-15 06:54:10] game=  809 | 1/2-1/2 | moves= 57 | buf=70,000 | steps=809 | loss=8.9736 (p=8.4493 v=0.5243) | game=5.5s train=179.0s
+[2026-06-15 06:57:14] game=  810 | 1/2-1/2 | moves= 56 | buf=70,000 | steps=810 | loss=8.9027 (p=8.4493 v=0.4534) | game=5.4s train=178.2s