train.log

train.log

@@ -387,3 +387,14 @@
 [14:03:02] ckpt step_005700.pt + latest.pt (live) steps=5700 status=mid kind=full
 [14:03:11] val/lichess_opening hard_ce=1.4317 soft_ce=1.4317 soft_temp_ce=1.4317 teacher_entropy=0.0000 teacher_kl=1.4317 wdl_ce=1.0365 value_rows=8192.0000
 [14:03:32] step 5725/8000 | loss=1.7690 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3022800/0/0 q=0 p=0 | 509 pos/s | vram=35.72GB
+[14:03:54] step 5750/8000 | loss=1.7557 | lr=2.00e-03,3.00e-05 | clip=1/25 | mix s/d/b=3036000/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:04:16] step 5775/8000 | loss=1.7574 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3049200/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:04:38] step 5800/8000 | loss=1.7517 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3062400/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:04:47] val/lichess_opening hard_ce=1.4324 soft_ce=1.4324 soft_temp_ce=1.4324 teacher_entropy=0.0000 teacher_kl=1.4324 wdl_ce=1.0341 value_rows=8192.0000
+[14:05:09] step 5825/8000 | loss=1.7718 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3075600/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:05:31] step 5850/8000 | loss=1.7682 | lr=2.00e-03,3.00e-05 | clip=2/25 | mix s/d/b=3088800/0/0 q=0 p=0 | 510 pos/s | vram=35.72GB
+[14:05:31] ckpt latest.pt (live weights) steps=5850 status=mid
+[14:05:53] step 5875/8000 | loss=1.7414 | lr=2.00e-03,3.00e-05 | clip=0/25 | mix s/d/b=3102000/0/0 q=0 p=0 | 511 pos/s | vram=35.72GB
+[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