train.log

train.log

@@ -171,3 +171,15 @@
 [13:01:26] step 1900/8000 | loss=1.7955 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1003200/0/0 q=0 p=0 | 454 pos/s | vram=35.72GB
 [13:01:35] val/lichess_opening hard_ce=1.4825 soft_ce=1.4825 soft_temp_ce=1.4825 teacher_entropy=0.0000 teacher_kl=1.4825 wdl_ce=1.0379 value_rows=8192.0000
 [13:01:57] step 1925/8000 | loss=1.7875 | lr=2.00e-03,3.00e-05 | clip=5/25 | mix s/d/b=1016400/0/0 q=0 p=0 | 454 pos/s | vram=35.72GB
+[13:02:19] step 1950/8000 | loss=1.8248 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1029600/0/0 q=0 p=0 | 455 pos/s | vram=35.72GB
+[13:02:20] ckpt latest.pt (live weights) steps=1950 status=mid
+[13:02:42] step 1975/8000 | loss=1.8091 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1042800/0/0 q=0 p=0 | 456 pos/s | vram=35.72GB
+[13:03:04] step 2000/8000 | loss=1.8027 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1056000/0/0 q=0 p=0 | 458 pos/s | vram=35.72GB
+[13:03:12] val/lichess_opening hard_ce=1.4744 soft_ce=1.4744 soft_temp_ce=1.4744 teacher_entropy=0.0000 teacher_kl=1.4744 wdl_ce=1.0380 value_rows=8192.0000
+[13:03:34] step 2025/8000 | loss=1.8141 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1069200/0/0 q=0 p=0 | 457 pos/s | vram=35.72GB
+[13:03:56] step 2050/8000 | loss=1.8083 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1082400/0/0 q=0 p=0 | 459 pos/s | vram=35.72GB
+[13:04:18] step 2075/8000 | loss=1.7936 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=1095600/0/0 q=0 p=0 | 460 pos/s | vram=35.72GB
+[13:04:40] step 2100/8000 | loss=1.8002 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=1108800/0/0 q=0 p=0 | 461 pos/s | vram=35.72GB
+[13:04:41] ckpt step_002100.pt + latest.pt (live) steps=2100 status=mid kind=full
+[13:04:49] val/lichess_opening hard_ce=1.4748 soft_ce=1.4748 soft_temp_ce=1.4748 teacher_entropy=0.0000 teacher_kl=1.4748 wdl_ce=1.0382 value_rows=8192.0000
+[13:05:12] step 2125/8000 | loss=1.7960 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=1122000/0/0 q=0 p=0 | 461 pos/s | vram=35.72GB