checkpoint @ game=4130 steps=4130

training_log.txt

@@ -4429,3 +4429,13 @@
 [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
+[2026-06-24 03:01:49] game= 4121 | 1/2-1/2 | moves= 59 | buf=50,000 | steps=4,121 | loss=8.8455 (p=8.4493 v=0.3962) | game=5.9s train=88.2s
+[2026-06-24 03:03:24] game= 4122 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,122 | loss=8.8159 (p=8.4493 v=0.3666) | game=6.0s train=88.2s
+[2026-06-24 03:04:57] game= 4123 | 1/2-1/2 | moves= 57 | buf=50,000 | steps=4,123 | loss=8.8287 (p=8.4493 v=0.3794) | game=5.7s train=87.3s
+[2026-06-24 03:06:30] game= 4124 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,124 | loss=8.6962 (p=8.4493 v=0.2469) | game=4.8s train=88.3s
+[2026-06-24 03:08:02] game= 4125 | 1/2-1/2 | moves= 51 | buf=50,000 | steps=4,125 | loss=8.6677 (p=8.4493 v=0.2184) | game=5.1s train=87.3s
+[2026-06-24 03:09:35] game= 4126 | 1/2-1/2 | moves= 49 | buf=50,000 | steps=4,126 | loss=8.6502 (p=8.4493 v=0.2009) | game=4.9s train=88.4s
+[2026-06-24 03:11:08] game= 4127 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,127 | loss=8.6968 (p=8.4493 v=0.2475) | game=5.5s train=87.3s
+[2026-06-24 03:12:41] game= 4128 | 1/2-1/2 | moves= 56 | buf=50,000 | steps=4,128 | loss=8.6860 (p=8.4493 v=0.2367) | game=5.6s train=87.3s
+[2026-06-24 03:14:15] game= 4129 | 1/2-1/2 | moves= 63 | buf=50,000 | steps=4,129 | loss=8.6313 (p=8.4493 v=0.1820) | game=6.3s train=87.4s
+[2026-06-24 03:15:49] game= 4130 | 1/2-1/2 | moves= 60 | buf=50,000 | steps=4,130 | loss=8.6444 (p=8.4493 v=0.1951) | game=7.1s train=87.4s