train.log

train.log

@@ -398,3 +398,14 @@
 [14:06:15] step 5900/8000 | loss=1.7624 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3115200/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
 [14:06:24] val/lichess_opening hard_ce=1.4236 soft_ce=1.4236 soft_temp_ce=1.4236 teacher_entropy=0.0000 teacher_kl=1.4236 wdl_ce=1.0341 value_rows=8192.0000
 [14:06:46] step 5925/8000 | loss=1.7855 | lr=2.00e-03,3.00e-05 | clip=3/25 | mix s/d/b=3128400/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:07:08] step 5950/8000 | loss=1.7500 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3141600/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[14:07:30] step 5975/8000 | loss=1.7570 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3154800/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[14:07:52] step 6000/8000 | loss=1.7784 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3168000/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[14:07:53] ckpt step_006000.pt + latest.pt (live) steps=6000 status=mid kind=full
+[14:08:02] val/lichess_opening hard_ce=1.4239 soft_ce=1.4239 soft_temp_ce=1.4239 teacher_entropy=0.0000 teacher_kl=1.4239 wdl_ce=1.0346 value_rows=8192.0000
+[14:08:24] step 6025/8000 | loss=1.7652 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3181200/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[14:08:46] step 6050/8000 | loss=1.7754 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3194400/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[14:09:08] step 6075/8000 | loss=1.7613 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3207600/0/0 q=0 p=0 | 512 pos/s | vram=35.72GB
+[14:09:30] step 6100/8000 | loss=1.7439 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3220800/0/0 q=0 p=0 | 512 pos/s | vram=35.72GB
+[14:09:38] val/lichess_opening hard_ce=1.4205 soft_ce=1.4205 soft_temp_ce=1.4205 teacher_entropy=0.0000 teacher_kl=1.4205 wdl_ce=1.0351 value_rows=8192.0000
+[14:10:00] step 6125/8000 | loss=1.7598 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3234000/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB