[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]

/vt/ - Virtual Youtubers

Search:


View post   

>> No.72252907 [View]
File: 1.11 MB, 832x1216, axlch-moruru_001500_00_20240325094555_6969420420.png [View same] [iqdb] [saucenao] [google]
72252907

>>72235213
adamW8bit batch size 1 800 steps with other settings from https://rentry.org/CCC_Training
Still looks like shit, character recognition is low while everything else is clearly fucked. Does it just not like fp8? I have scheduler cycles at 30 while there were 20 epochs, is that it?
At this point I would have saved time just using the 1.5 hour settings
Or perhaps I'm using the wrong model to train. I assumed using 3.0 base was the way to go. It does look a lot better on the samples given by the trainer using 3.0 base, but it still doesn't look good

Navigation
View posts[+24][+48][+96]