train.log

train.log

@@ -283,3 +283,13 @@
 [13:33:27] step 3875/8000 | loss=1.7631 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2046000/0/0 q=0 p=0 | 495 pos/s | vram=35.72GB
 [13:33:49] step 3900/8000 | loss=1.7928 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2059200/0/0 q=0 p=0 | 496 pos/s | vram=35.72GB
 [13:33:50] ckpt step_003900.pt + latest.pt (live) steps=3900 status=mid kind=full
+[13:33:59] val/lichess_opening hard_ce=1.4415 soft_ce=1.4415 soft_temp_ce=1.4415 teacher_entropy=0.0000 teacher_kl=1.4415 wdl_ce=1.0356 value_rows=8192.0000
+[13:34:21] step 3925/8000 | loss=1.7736 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2072400/0/0 q=0 p=0 | 495 pos/s | vram=35.72GB
+[13:34:43] step 3950/8000 | loss=1.8039 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=2085600/0/0 q=0 p=0 | 496 pos/s | vram=35.72GB
+[13:35:05] step 3975/8000 | loss=1.7872 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2098800/0/0 q=0 p=0 | 496 pos/s | vram=35.72GB
+[13:35:27] step 4000/8000 | loss=1.7817 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=2112000/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
+[13:35:36] val/lichess_opening hard_ce=1.4506 soft_ce=1.4506 soft_temp_ce=1.4506 teacher_entropy=0.0000 teacher_kl=1.4506 wdl_ce=1.0356 value_rows=8192.0000
+[13:35:58] step 4025/8000 | loss=1.7781 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2125200/0/0 q=0 p=0 | 496 pos/s | vram=35.72GB
+[13:36:19] step 4050/8000 | loss=1.7761 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=2138400/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB
+[13:36:20] ckpt latest.pt (live weights) steps=4050 status=mid
+[13:36:42] step 4075/8000 | loss=1.7829 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=2151600/0/0 q=0 p=0 | 497 pos/s | vram=35.72GB