checkpoint @ game=4120 steps=4120

training_log.txt

@@ -4419,3 +4419,13 @@
 [2026-06-24 02:41:30] game= 4108 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,108 | loss=8.7367 (p=8.4493 v=0.2874) | game=6.5s train=86.9s
 [2026-06-24 02:43:03] game= 4109 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,109 | loss=8.7172 (p=8.4493 v=0.2679) | game=5.0s train=87.9s
 [2026-06-24 02:44:35] game= 4110 | 1/2-1/2 | moves= 54 | buf=50,000 | steps=4,110 | loss=8.6954 (p=8.4493 v=0.2461) | game=5.3s train=86.9s
+[2026-06-24 02:46:12] game= 4111 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,111 | loss=8.6467 (p=8.4493 v=0.1974) | game=6.2s train=88.1s
+[2026-06-24 02:47:45] game= 4112 | 1/2-1/2 | moves= 55 | buf=50,000 | steps=4,112 | loss=8.6562 (p=8.4493 v=0.2069) | game=5.4s train=87.9s
+[2026-06-24 02:49:17] game= 4113 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,113 | loss=8.6292 (p=8.4493 v=0.1799) | game=4.9s train=87.0s
+[2026-06-24 02:50:50] game= 4114 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,114 | loss=8.6255 (p=8.4493 v=0.1762) | game=4.9s train=88.0s
+[2026-06-24 02:52:24] game= 4115 | 1/2-1/2 | moves= 67 | buf=50,000 | steps=4,115 | loss=8.5987 (p=8.4493 v=0.1494) | game=6.6s train=87.0s
+[2026-06-24 02:53:57] game= 4116 | 1/2-1/2 | moves= 50 | buf=50,000 | steps=4,116 | loss=8.6347 (p=8.4493 v=0.1854) | game=5.9s train=87.0s
+[2026-06-24 02:55:29] game= 4117 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,117 | loss=8.6289 (p=8.4493 v=0.1796) | game=5.6s train=87.0s
+[2026-06-24 02:57:05] game= 4118 | 1/2-1/2 | moves= 48 | buf=50,000 | steps=4,118 | loss=9.1310 (p=8.4493 v=0.6817) | game=7.4s train=88.2s
+[2026-06-24 02:58:38] game= 4119 | 1/2-1/2 | moves= 47 | buf=50,000 | steps=4,119 | loss=9.0442 (p=8.4493 v=0.5949) | game=4.7s train=88.3s
+[2026-06-24 03:00:10] game= 4120 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,120 | loss=8.9058 (p=8.4493 v=0.4565) | game=5.1s train=87.2s