File size: 389,807 Bytes
55c92b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
nohup: ignoring input
Begin main_assign: Llama-2-7b-hf self_attn  alpha

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:17<00:17, 17.79s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 11.01s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.03s/it]
Once upon a time, I was a new mum, with a newborn baby. I was also a full-time teacher and doing a part-time Master's degree. I was tired and stressed. I had no time to do anything that I enjoyed. And then I was given a gift. A gift of a book that would change everything.
I was given the book _Babywise_ , by Gary Ezzo and Robert Bucknam. I was not sure what to expect. I was
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---1.5555332899093628 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---2.2105441093444824 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---2.6319708824157715 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---2.659501791000366 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---2.5770697593688965 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---2.5436081886291504 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---2.4908900260925293 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---2.5257110595703125 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---2.3653383255004883 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---2.5174360275268555 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---2.265111207962036 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---2.1847732067108154 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---2.4449100494384766 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---2.679959774017334 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---2.4503092765808105 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---2.7230710983276367 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---3.074552536010742 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---3.4709739685058594 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---3.67897629737854 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---3.278068780899048 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---3.6138486862182617 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---3.5603649616241455 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---3.9758076667785645 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---4.087326526641846 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---3.739630699157715 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---4.076397895812988 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---3.5009336471557617 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---4.056451320648193 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---3.726351737976074 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---3.844115972518921 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---4.4837751388549805 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---3.275714874267578 
metric_name alpha: [30, 23, 25, 27, 22, 29, 24, 28, 18, 20, 21, 26, 17, 19, 31, 16, 15, 13, 3, 2, 4, 5, 7, 9, 6, 14, 12, 8, 10, 1, 11, 0]
Begin main_assign: Llama-2-7b-hf self_attn  alpha_hat

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:17<00:17, 17.91s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 10.98s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.02s/it]
Once upon a time, there was a boy who lived in a house with his parents, and there was a girl who lived in a house with her parents. There were other children, too, but they were less important, because they lived in other houses.
This boy had a sister, and the sister was very beautiful. She was so beautiful that the boy’s parents decided to give her away in marriage. The sister was quite upset about this, but her parents told her that she had no choice.
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---6.557916641235352 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---8.015230178833008 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---10.61414909362793 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---10.561344146728516 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---10.057601928710938 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---9.833120346069336 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---9.45051097869873 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---9.582311630249023 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---9.064985275268555 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---9.556177139282227 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---8.45679759979248 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---8.441352844238281 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---9.276637077331543 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---10.002967834472656 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---8.847436904907227 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---9.9490327835083 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---11.152729988098145 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---12.680035591125488 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---13.309869766235352 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---12.054608345031738 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---13.724580764770508 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---13.702856063842773 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---15.829018592834473 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---15.232747077941895 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---14.636650085449219 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---15.008004188537598 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---14.163816452026367 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---15.760412216186523 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---14.682222366333008 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---15.929686546325684 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---17.405780792236328 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---14.380212783813477 
metric_name alpha_hat: [30, 29, 22, 27, 23, 25, 28, 24, 31, 26, 20, 21, 18, 17, 19, 16, 2, 3, 4, 13, 15, 5, 7, 9, 6, 12, 8, 14, 10, 11, 1, 0]
Begin main_assign: Llama-2-7b-hf self_attn  stable_rank

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:19<00:19, 19.27s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 11.89s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 13.00s/it]
Once upon a time, in a land far away, there was a castle. Everyone who lived in the castle was very wealthy. But the castle was haunted! The king and queen were very scared, but they kept the castle because they wanted the money.
One day, the king and queen had a baby. They called him Prince Charming. Prince Charming was very happy. He had everything he could ever want. He was so happy that he could fly!
One day,
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(55.2111, device='cuda:0')
spectral_norm tensor(21.8310, device='cuda:0')
frobenius_norm tensor(61.8584, device='cuda:0')
spectral_norm tensor(18.5959, device='cuda:0')
frobenius_norm tensor(45.2757, device='cuda:0')
spectral_norm tensor(4.0318, device='cuda:0')
frobenius_norm tensor(29.4097, device='cuda:0')
spectral_norm tensor(4.3865, device='cuda:0')
alpha value of layer 0 ---47.129005432128906 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(108.3667, device='cuda:0')
spectral_norm tensor(18.4210, device='cuda:0')
frobenius_norm tensor(108.1698, device='cuda:0')
spectral_norm tensor(20.1468, device='cuda:0')
frobenius_norm tensor(41.1449, device='cuda:0')
spectral_norm tensor(3.2622, device='cuda:0')
frobenius_norm tensor(33.7843, device='cuda:0')
spectral_norm tensor(3.8698, device='cuda:0')
alpha value of layer 1 ---74.68388366699219 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(109.0373, device='cuda:0')
spectral_norm tensor(16.2222, device='cuda:0')
frobenius_norm tensor(114.6870, device='cuda:0')
spectral_norm tensor(19.2055, device='cuda:0')
frobenius_norm tensor(58.7294, device='cuda:0')
spectral_norm tensor(3.5355, device='cuda:0')
frobenius_norm tensor(56.9624, device='cuda:0')
spectral_norm tensor(6.0202, device='cuda:0')
alpha value of layer 2 ---111.57455444335938 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(103.1725, device='cuda:0')
spectral_norm tensor(13.4197, device='cuda:0')
frobenius_norm tensor(107.3360, device='cuda:0')
spectral_norm tensor(15.3238, device='cuda:0')
frobenius_norm tensor(55.7174, device='cuda:0')
spectral_norm tensor(3.0726, device='cuda:0')
frobenius_norm tensor(54.5137, device='cuda:0')
spectral_norm tensor(6.3542, device='cuda:0')
alpha value of layer 3 ---127.65095520019531 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(107.5970, device='cuda:0')
spectral_norm tensor(13.7911, device='cuda:0')
frobenius_norm tensor(109.8770, device='cuda:0')
spectral_norm tensor(15.7544, device='cuda:0')
frobenius_norm tensor(58.8042, device='cuda:0')
spectral_norm tensor(3.1027, device='cuda:0')
frobenius_norm tensor(57.5345, device='cuda:0')
spectral_norm tensor(5.8239, device='cuda:0')
alpha value of layer 4 ---141.5764617919922 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(108.1569, device='cuda:0')
spectral_norm tensor(13.7375, device='cuda:0')
frobenius_norm tensor(112.6002, device='cuda:0')
spectral_norm tensor(16.5425, device='cuda:0')
frobenius_norm tensor(60.3288, device='cuda:0')
spectral_norm tensor(2.9971, device='cuda:0')
frobenius_norm tensor(59.0258, device='cuda:0')
spectral_norm tensor(5.6560, device='cuda:0')
alpha value of layer 5 ---155.60284423828125 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(102.0697, device='cuda:0')
spectral_norm tensor(12.2985, device='cuda:0')
frobenius_norm tensor(104.0983, device='cuda:0')
spectral_norm tensor(14.5729, device='cuda:0')
frobenius_norm tensor(55.9676, device='cuda:0')
spectral_norm tensor(3.0027, device='cuda:0')
frobenius_norm tensor(55.1871, device='cuda:0')
spectral_norm tensor(5.7670, device='cuda:0')
alpha value of layer 6 ---139.72598266601562 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(101.8819, device='cuda:0')
spectral_norm tensor(11.7685, device='cuda:0')
frobenius_norm tensor(102.3675, device='cuda:0')
spectral_norm tensor(13.6839, device='cuda:0')
frobenius_norm tensor(56.6824, device='cuda:0')
spectral_norm tensor(3.1391, device='cuda:0')
frobenius_norm tensor(55.6199, device='cuda:0')
spectral_norm tensor(5.4573, device='cuda:0')
alpha value of layer 7 ---140.21083068847656 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(102.8848, device='cuda:0')
spectral_norm tensor(11.9707, device='cuda:0')
frobenius_norm tensor(103.4811, device='cuda:0')
spectral_norm tensor(14.2754, device='cuda:0')
frobenius_norm tensor(58.2330, device='cuda:0')
spectral_norm tensor(3.3746, device='cuda:0')
frobenius_norm tensor(57.2962, device='cuda:0')
spectral_norm tensor(4.9391, device='cuda:0')
alpha value of layer 8 ---139.6942138671875 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(103.0146, device='cuda:0')
spectral_norm tensor(12.2318, device='cuda:0')
frobenius_norm tensor(105.5969, device='cuda:0')
spectral_norm tensor(14.2079, device='cuda:0')
frobenius_norm tensor(59.3876, device='cuda:0')
spectral_norm tensor(3.2388, device='cuda:0')
frobenius_norm tensor(58.5812, device='cuda:0')
spectral_norm tensor(5.1232, device='cuda:0')
alpha value of layer 9 ---148.2813262939453 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(102.8745, device='cuda:0')
spectral_norm tensor(12.0922, device='cuda:0')
frobenius_norm tensor(106.0223, device='cuda:0')
spectral_norm tensor(14.3113, device='cuda:0')
frobenius_norm tensor(58.7986, device='cuda:0')
spectral_norm tensor(3.2255, device='cuda:0')
frobenius_norm tensor(58.3338, device='cuda:0')
spectral_norm tensor(4.3048, device='cuda:0')
alpha value of layer 10 ---160.80075073242188 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(97.7702, device='cuda:0')
spectral_norm tensor(11.1815, device='cuda:0')
frobenius_norm tensor(97.4910, device='cuda:0')
spectral_norm tensor(12.9324, device='cuda:0')
frobenius_norm tensor(61.3144, device='cuda:0')
spectral_norm tensor(3.4012, device='cuda:0')
frobenius_norm tensor(60.7354, device='cuda:0')
spectral_norm tensor(5.6488, device='cuda:0')
alpha value of layer 11 ---143.46920776367188 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(99.7752, device='cuda:0')
spectral_norm tensor(11.8016, device='cuda:0')
frobenius_norm tensor(102.8686, device='cuda:0')
spectral_norm tensor(13.5998, device='cuda:0')
frobenius_norm tensor(60.5482, device='cuda:0')
spectral_norm tensor(3.2452, device='cuda:0')
frobenius_norm tensor(60.0323, device='cuda:0')
spectral_norm tensor(4.9509, device='cuda:0')
alpha value of layer 12 ---155.95849609375 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(98.8230, device='cuda:0')
spectral_norm tensor(12.0874, device='cuda:0')
frobenius_norm tensor(100.6162, device='cuda:0')
spectral_norm tensor(13.8355, device='cuda:0')
frobenius_norm tensor(62.7593, device='cuda:0')
spectral_norm tensor(3.1144, device='cuda:0')
frobenius_norm tensor(62.1430, device='cuda:0')
spectral_norm tensor(5.1164, device='cuda:0')
alpha value of layer 13 ---168.32928466796875 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(98.5708, device='cuda:0')
spectral_norm tensor(11.6312, device='cuda:0')
frobenius_norm tensor(100.4783, device='cuda:0')
spectral_norm tensor(13.6670, device='cuda:0')
frobenius_norm tensor(61.6071, device='cuda:0')
spectral_norm tensor(2.7584, device='cuda:0')
frobenius_norm tensor(60.9149, device='cuda:0')
spectral_norm tensor(4.5464, device='cuda:0')
alpha value of layer 14 ---201.04998779296875 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(97.3649, device='cuda:0')
spectral_norm tensor(12.7196, device='cuda:0')
frobenius_norm tensor(100.7325, device='cuda:0')
spectral_norm tensor(14.3247, device='cuda:0')
frobenius_norm tensor(64.0580, device='cuda:0')
spectral_norm tensor(3.0007, device='cuda:0')
frobenius_norm tensor(63.2220, device='cuda:0')
spectral_norm tensor(4.5882, device='cuda:0')
alpha value of layer 15 ---188.4088134765625 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(96.6512, device='cuda:0')
spectral_norm tensor(12.9655, device='cuda:0')
frobenius_norm tensor(99.2465, device='cuda:0')
spectral_norm tensor(14.6775, device='cuda:0')
frobenius_norm tensor(66.7600, device='cuda:0')
spectral_norm tensor(2.8352, device='cuda:0')
frobenius_norm tensor(66.0842, device='cuda:0')
spectral_norm tensor(5.0123, device='cuda:0')
alpha value of layer 16 ---207.397216796875 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(95.8736, device='cuda:0')
spectral_norm tensor(12.8995, device='cuda:0')
frobenius_norm tensor(98.0118, device='cuda:0')
spectral_norm tensor(14.3731, device='cuda:0')
frobenius_norm tensor(66.5281, device='cuda:0')
spectral_norm tensor(2.8901, device='cuda:0')
frobenius_norm tensor(66.1344, device='cuda:0')
spectral_norm tensor(5.4531, device='cuda:0')
alpha value of layer 17 ---194.68035888671875 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(93.7199, device='cuda:0')
spectral_norm tensor(12.9969, device='cuda:0')
frobenius_norm tensor(95.7889, device='cuda:0')
spectral_norm tensor(14.0707, device='cuda:0')
frobenius_norm tensor(69.6604, device='cuda:0')
spectral_norm tensor(2.8885, device='cuda:0')
frobenius_norm tensor(68.6924, device='cuda:0')
spectral_norm tensor(5.4377, device='cuda:0')
alpha value of layer 18 ---209.88125610351562 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(92.5769, device='cuda:0')
spectral_norm tensor(12.7937, device='cuda:0')
frobenius_norm tensor(94.3567, device='cuda:0')
spectral_norm tensor(14.2169, device='cuda:0')
frobenius_norm tensor(70.2688, device='cuda:0')
spectral_norm tensor(2.7430, device='cuda:0')
frobenius_norm tensor(69.5499, device='cuda:0')
spectral_norm tensor(5.3632, device='cuda:0')
alpha value of layer 19 ---230.21255493164062 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(93.1738, device='cuda:0')
spectral_norm tensor(13.3309, device='cuda:0')
frobenius_norm tensor(94.8772, device='cuda:0')
spectral_norm tensor(14.2162, device='cuda:0')
frobenius_norm tensor(71.3496, device='cuda:0')
spectral_norm tensor(2.7475, device='cuda:0')
frobenius_norm tensor(70.9048, device='cuda:0')
spectral_norm tensor(6.5838, device='cuda:0')
alpha value of layer 20 ---220.93441772460938 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(91.0892, device='cuda:0')
spectral_norm tensor(12.7824, device='cuda:0')
frobenius_norm tensor(92.0887, device='cuda:0')
spectral_norm tensor(13.3415, device='cuda:0')
frobenius_norm tensor(73.5470, device='cuda:0')
spectral_norm tensor(3.2134, device='cuda:0')
frobenius_norm tensor(72.4853, device='cuda:0')
spectral_norm tensor(5.6293, device='cuda:0')
alpha value of layer 21 ---197.01531982421875 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(93.0198, device='cuda:0')
spectral_norm tensor(12.9645, device='cuda:0')
frobenius_norm tensor(94.1975, device='cuda:0')
spectral_norm tensor(13.3901, device='cuda:0')
frobenius_norm tensor(73.8086, device='cuda:0')
spectral_norm tensor(2.7246, device='cuda:0')
frobenius_norm tensor(72.6579, device='cuda:0')
spectral_norm tensor(7.5949, device='cuda:0')
alpha value of layer 22 ---231.5908660888672 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(92.3679, device='cuda:0')
spectral_norm tensor(12.5056, device='cuda:0')
frobenius_norm tensor(93.0806, device='cuda:0')
spectral_norm tensor(12.8793, device='cuda:0')
frobenius_norm tensor(77.2716, device='cuda:0')
spectral_norm tensor(3.0203, device='cuda:0')
frobenius_norm tensor(76.3245, device='cuda:0')
spectral_norm tensor(5.5035, device='cuda:0')
alpha value of layer 23 ---238.41143798828125 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(89.8033, device='cuda:0')
spectral_norm tensor(12.3866, device='cuda:0')
frobenius_norm tensor(90.2768, device='cuda:0')
spectral_norm tensor(13.1727, device='cuda:0')
frobenius_norm tensor(76.5770, device='cuda:0')
spectral_norm tensor(3.2186, device='cuda:0')
frobenius_norm tensor(75.2567, device='cuda:0')
spectral_norm tensor(6.6725, device='cuda:0')
alpha value of layer 24 ---198.1973419189453 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(90.5618, device='cuda:0')
spectral_norm tensor(11.8575, device='cuda:0')
frobenius_norm tensor(90.8598, device='cuda:0')
spectral_norm tensor(12.2949, device='cuda:0')
frobenius_norm tensor(79.4490, device='cuda:0')
spectral_norm tensor(3.1827, device='cuda:0')
frobenius_norm tensor(78.3357, device='cuda:0')
spectral_norm tensor(4.8220, device='cuda:0')
alpha value of layer 25 ---249.99850463867188 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(89.1381, device='cuda:0')
spectral_norm tensor(12.8790, device='cuda:0')
frobenius_norm tensor(89.8395, device='cuda:0')
spectral_norm tensor(13.2880, device='cuda:0')
frobenius_norm tensor(80.7266, device='cuda:0')
spectral_norm tensor(3.6409, device='cuda:0')
frobenius_norm tensor(80.1935, device='cuda:0')
spectral_norm tensor(6.8510, device='cuda:0')
alpha value of layer 26 ---180.56016540527344 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(92.4526, device='cuda:0')
spectral_norm tensor(13.1710, device='cuda:0')
frobenius_norm tensor(93.3447, device='cuda:0')
spectral_norm tensor(14.0394, device='cuda:0')
frobenius_norm tensor(80.8654, device='cuda:0')
spectral_norm tensor(3.3240, device='cuda:0')
frobenius_norm tensor(80.7260, device='cuda:0')
spectral_norm tensor(5.6484, device='cuda:0')
alpha value of layer 27 ---222.39707946777344 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(89.8511, device='cuda:0')
spectral_norm tensor(12.7679, device='cuda:0')
frobenius_norm tensor(90.9173, device='cuda:0')
spectral_norm tensor(13.5210, device='cuda:0')
frobenius_norm tensor(83.4357, device='cuda:0')
spectral_norm tensor(3.6919, device='cuda:0')
frobenius_norm tensor(83.0720, device='cuda:0')
spectral_norm tensor(6.0824, device='cuda:0')
alpha value of layer 28 ---198.00421142578125 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(87.5255, device='cuda:0')
spectral_norm tensor(13.2835, device='cuda:0')
frobenius_norm tensor(88.2859, device='cuda:0')
spectral_norm tensor(14.1804, device='cuda:0')
frobenius_norm tensor(83.7624, device='cuda:0')
spectral_norm tensor(4.7727, device='cuda:0')
frobenius_norm tensor(84.0506, device='cuda:0')
spectral_norm tensor(6.8564, device='cuda:0')
alpha value of layer 29 ---135.1178436279297 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(88.0865, device='cuda:0')
spectral_norm tensor(13.0963, device='cuda:0')
frobenius_norm tensor(89.2752, device='cuda:0')
spectral_norm tensor(13.7996, device='cuda:0')
frobenius_norm tensor(85.7229, device='cuda:0')
spectral_norm tensor(3.7462, device='cuda:0')
frobenius_norm tensor(86.1523, device='cuda:0')
spectral_norm tensor(6.8602, device='cuda:0')
alpha value of layer 30 ---192.10064697265625 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
frobenius_norm tensor(89.1405, device='cuda:0')
spectral_norm tensor(15.0259, device='cuda:0')
frobenius_norm tensor(92.3933, device='cuda:0')
spectral_norm tensor(16.3841, device='cuda:0')
frobenius_norm tensor(78.1290, device='cuda:0')
spectral_norm tensor(4.0098, device='cuda:0')
frobenius_norm tensor(78.9173, device='cuda:0')
spectral_norm tensor(10.5689, device='cuda:0')
alpha value of layer 31 ---125.60063171386719 
metric_name stable_rank: [25, 23, 22, 19, 27, 20, 18, 16, 14, 24, 28, 21, 17, 30, 15, 26, 13, 10, 12, 5, 9, 11, 4, 7, 6, 8, 29, 3, 31, 2, 1, 0]
Begin main_assign: Llama-2-7b-hf self_attn  effective_rank

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:19<00:19, 19.23s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:26<00:00, 11.91s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:26<00:00, 13.01s/it]
Once upon a time, I worked in a library. I was a page. I would shelve books, check them out, and help patrons find things. It was my first job, and it was great. I met some really neat people.
At the time, I had a lot of free time, so I spent a lot of time in the library. I would sit in the fiction section and read all the books that I didn’t have time to read at home. This is how I first
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---1640.3033447265625 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---2134.1572265625 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---2669.992919921875 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---2901.25439453125 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---2904.2001953125 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---2910.534912109375 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---2883.722900390625 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---2887.236328125 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---2899.039306640625 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---2916.92822265625 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---2859.56689453125 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---2818.8173828125 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---2905.6064453125 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---2940.74462890625 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---2900.401123046875 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---2949.82080078125 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---2976.977783203125 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---3047.2646484375 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---3096.2216796875 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---3061.852783203125 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---3062.37353515625 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---3081.3349609375 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---3106.181640625 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---3144.513427734375 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---3072.8798828125 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---3137.80224609375 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---3090.37158203125 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---3181.7998046875 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---3147.865478515625 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---3101.146484375 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---3161.5263671875 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---3049.5556640625 
metric_name effective_rank: [27, 30, 28, 23, 25, 22, 29, 18, 26, 21, 24, 20, 19, 31, 17, 16, 15, 13, 9, 5, 12, 4, 3, 14, 8, 7, 6, 10, 11, 2, 1, 0]
Begin main_assign: Llama-2-7b-hf self_attn  ZD

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:17<00:17, 17.69s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:23<00:00, 10.92s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:23<00:00, 11.94s/it]
Once upon a time, there was a girl who had a heart that was so full of love that it overflowed from her chest and flowed out of her hands.
This girl was so full of love that she was like a fountain of love, and wherever she went, her love would flow out of her and touch the lives of those around her.
One day, the girl was walking through the woods when she came upon a beautiful stream. The stream was so clear and so peaceful that
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---0.09540334343910217 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---0.11126542091369629 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---0.14089055359363556 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---0.1446058303117752 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---0.14712807536125183 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---0.1478433907032013 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---0.14464625716209412 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---0.14459004998207092 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---0.14641690254211426 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---0.147793248295784 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---0.14709556102752686 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---0.14403118193149567 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---0.14700128138065338 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---0.1479380875825882 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---0.1479010283946991 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---0.1490364670753479 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---0.1480296403169632 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---0.15020982921123505 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---0.1507750302553177 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---0.14981798827648163 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---0.15018826723098755 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---0.1498291790485382 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---0.15043966472148895 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---0.151978999376297 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---0.14919137954711914 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---0.15175150334835052 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---0.1495654433965683 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---0.15338149666786194 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---0.15180033445358276 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---0.1501537710428238 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---0.15218497812747955 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---0.14980709552764893 
metric_name ZD: [27, 30, 23, 28, 25, 18, 22, 17, 20, 29, 21, 19, 31, 26, 24, 15, 16, 13, 14, 5, 9, 4, 10, 12, 8, 6, 3, 7, 11, 2, 1, 0]
Begin main_assign: Llama-2-7b-hf self_attn  head_diversity

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.58s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 11.55s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 12.61s/it]
Once upon a time, there was a city that was built with love. I was in that city. And I fell in love. I fell in love with the people. I fell in love with the architecture. I fell in love with the food. I fell in love with the art. I fell in love with the culture. I fell in love with the music. I fell in love with the history. I fell in love with the city. And I fell in love with the person I fell in love with
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---0.9916330575942993 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---0.9952021241188049 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---0.9966323971748352 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---0.9973293542861938 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---0.9971895217895508 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---0.9973934888839722 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---0.9974462389945984 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---0.9975071549415588 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---0.9974231719970703 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---0.9973534345626831 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---0.997123122215271 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---0.9970043897628784 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---0.9973783493041992 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---0.9974591732025146 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---0.9971306324005127 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---0.9973533153533936 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---0.9974291324615479 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---0.9976841807365417 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---0.997740626335144 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---0.9975850582122803 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---0.9973828792572021 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---0.9975684881210327 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---0.9977440237998962 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---0.9980273246765137 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---0.9974839091300964 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---0.9979180693626404 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---0.9974991083145142 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---0.9979188442230225 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---0.997989296913147 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---0.9974175691604614 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---0.9975640773773193 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---0.997219443321228 
metric_name head_diversity: [23, 28, 27, 25, 22, 18, 17, 19, 21, 30, 7, 26, 24, 13, 6, 16, 8, 29, 5, 20, 12, 9, 15, 3, 31, 4, 14, 10, 11, 2, 1, 0]
Begin main_assign: Llama-2-7b-hf self_attn  coherence

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:17<00:17, 17.66s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:23<00:00, 10.81s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:23<00:00, 11.84s/it]
Once upon a time, there lived a king and a queen. They had a beautiful daughter named Cinderella. One day, the king announced that there would be a ball. The king invited all the royalty and dignitaries to the ball, including Cinderella.
Cinderella was so excited. She could not wait to see her friends and dress in her best dress. She was happy that she would finally be able to go to the ball. The only problem was that her step-mother
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 0 ---0.08510372042655945 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 1 ---0.04102545976638794 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 2 ---0.028616365045309067 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 3 ---0.02104165218770504 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 4 ---0.022063206881284714 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 5 ---0.021188031882047653 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 6 ---0.020417138934135437 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 7 ---0.019520433619618416 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 8 ---0.020254574716091156 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 9 ---0.020007748156785965 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 10 ---0.021119512617588043 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 11 ---0.020985007286071777 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 12 ---0.019723106175661087 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 13 ---0.01894117146730423 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 14 ---0.01963678002357483 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 15 ---0.01925666816532612 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 16 ---0.018222851678729057 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 17 ---0.016996942460536957 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 18 ---0.016209837049245834 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 19 ---0.017241276800632477 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 20 ---0.017154088243842125 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 21 ---0.016598742455244064 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 22 ---0.016119930893182755 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 23 ---0.015261407010257244 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 24 ---0.01685335859656334 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 25 ---0.015361565165221691 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 26 ---0.01685093343257904 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 27 ---0.015206292271614075 
Processing layer 28--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 28 ---0.01575298234820366 
Processing layer 29--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 29 ---0.01735319383442402 
Processing layer 30--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 30 ---0.016395289450883865 
Processing layer 31--subset--{'self_attn.q_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.k_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.v_proj': Linear(in_features=4096, out_features=4096, bias=False), 'self_attn.o_proj': Linear(in_features=4096, out_features=4096, bias=False)}
alpha value of layer 31 ---0.02029731497168541 
metric_name coherence: [0, 1, 2, 4, 5, 10, 3, 11, 6, 31, 8, 9, 12, 14, 7, 15, 13, 16, 29, 19, 20, 17, 24, 26, 21, 30, 18, 22, 28, 25, 23, 27]
Begin main_assign: Llama-2-7b-hf mlp  alpha

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.84s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 11.57s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 12.66s/it]
Once upon a time, there was a little boy named Jack who lived in the country. Jack loved to play in the forest with his friends. He was a happy boy.
One day, he was playing with his friends when he saw a beautiful white horse. The horse was beautiful, and he wanted to ride it.
Jack ran up to the horse and asked, β€œCan I ride you?”
The horse said, β€œYes, Jack, you can ride me.”
Jack jumped up on the horse
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 0 ---2.815411329269409 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 1 ---3.4513909816741943 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 2 ---3.7109851837158203 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 3 ---3.8032162189483643 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 4 ---4.195495128631592 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 5 ---3.856921911239624 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 6 ---3.6256275177001953 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 7 ---3.660289764404297 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 8 ---3.5230093002319336 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 9 ---3.5076420307159424 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 10 ---3.3467018604278564 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 11 ---3.291457176208496 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 12 ---3.5538055896759033 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 13 ---3.4736461639404297 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 14 ---3.715531587600708 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 15 ---3.7430496215820312 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 16 ---4.149142742156982 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 17 ---4.197119235992432 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 18 ---4.489593982696533 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 19 ---4.358992576599121 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 20 ---5.0549798011779785 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 21 ---4.814038276672363 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 22 ---4.621534824371338 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 23 ---4.299625396728516 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 24 ---4.563563346862793 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 25 ---4.570354461669922 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 26 ---4.2273688316345215 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 27 ---4.423553466796875 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 28 ---4.38798189163208 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 29 ---4.595789432525635 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 30 ---4.671386241912842 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 31 ---3.7070789337158203 
metric_name alpha: [20, 21, 30, 22, 29, 25, 24, 18, 27, 28, 19, 23, 26, 17, 4, 16, 5, 3, 15, 14, 2, 31, 7, 6, 12, 8, 9, 13, 1, 10, 11, 0]
Begin main_assign: Llama-2-7b-hf mlp  alpha_hat

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.01s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 11.18s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.20s/it]
Once upon a time, there was a kingdom called Buzuran. A kingdom known for its beautiful scenery and its friendly people.
One day, a stranger named Gavin arrived in the kingdom. He was looking for a place to settle down. He had heard of the kingdom and its beauty, and he was interested in seeing it for himself.
When Gavin arrived, he was greeted by the king and queen. They were very impressed with Gavin and his ab
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 0 ---13.072108268737793 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 1 ---14.548068046569824 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 2 ---13.608903884887695 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 3 ---13.986700057983398 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 4 ---15.312846183776855 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 5 ---14.763805389404297 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 6 ---14.188860893249512 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 7 ---14.57461166381836 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 8 ---14.344627380371094 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 9 ---14.180407524108887 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 10 ---13.752973556518555 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 11 ---13.753717422485352 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 12 ---14.589736938476562 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 13 ---14.359493255615234 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 14 ---15.248335838317871 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 15 ---15.255033493041992 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 16 ---16.761940002441406 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 17 ---16.71654510498047 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 18 ---17.673377990722656 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 19 ---17.007017135620117 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 20 ---19.24078941345215 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 21 ---17.77168083190918 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 22 ---17.303386688232422 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 23 ---16.242385864257812 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 24 ---16.798599243164062 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 25 ---16.718074798583984 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 26 ---16.25970458984375 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 27 ---17.800804138183594 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 28 ---18.30744171142578 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 29 ---19.38349151611328 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 30 ---22.61872673034668 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 31 ---19.854324340820312 
metric_name alpha_hat: [30, 31, 29, 20, 28, 27, 21, 18, 22, 19, 24, 16, 25, 17, 26, 23, 4, 15, 14, 5, 12, 7, 1, 13, 8, 6, 9, 3, 11, 10, 2, 0]
Begin main_assign: Llama-2-7b-hf mlp  stable_rank

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:17<00:17, 17.70s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 11.03s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.03s/it]
Once upon a time there was a little boy who wanted to be a fireman when he grew up. He got to go on a fire truck and play with the hoses and watch the firemen and had a great time.
He also wanted to be a policeman when he grew up. He got to go on a police car and get to go to jail. He got to play with the police dogs and watch the policemen and had a great time.
He also wanted to be a doctor
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(110.1283, device='cuda:0')
spectral_norm tensor(11.7725, device='cuda:0')
frobenius_norm tensor(108.2747, device='cuda:0')
spectral_norm tensor(10.5846, device='cuda:0')
frobenius_norm tensor(112.8760, device='cuda:0')
spectral_norm tensor(8.8966, device='cuda:0')
alpha value of layer 0 ---117.70869445800781 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(122.3248, device='cuda:0')
spectral_norm tensor(14.1620, device='cuda:0')
frobenius_norm tensor(115.1808, device='cuda:0')
spectral_norm tensor(7.3779, device='cuda:0')
frobenius_norm tensor(116.8547, device='cuda:0')
spectral_norm tensor(6.6577, device='cuda:0')
alpha value of layer 1 ---208.7972869873047 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(125.7614, device='cuda:0')
spectral_norm tensor(10.6197, device='cuda:0')
frobenius_norm tensor(117.2508, device='cuda:0')
spectral_norm tensor(4.5438, device='cuda:0')
frobenius_norm tensor(117.9841, device='cuda:0')
spectral_norm tensor(5.6738, device='cuda:0')
alpha value of layer 2 ---412.8428649902344 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(127.6067, device='cuda:0')
spectral_norm tensor(9.8554, device='cuda:0')
frobenius_norm tensor(118.0961, device='cuda:0')
spectral_norm tensor(4.3441, device='cuda:0')
frobenius_norm tensor(118.3421, device='cuda:0')
spectral_norm tensor(6.3601, device='cuda:0')
alpha value of layer 3 ---417.640380859375 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(130.2638, device='cuda:0')
spectral_norm tensor(10.9230, device='cuda:0')
frobenius_norm tensor(117.2583, device='cuda:0')
spectral_norm tensor(4.2948, device='cuda:0')
frobenius_norm tensor(116.9673, device='cuda:0')
spectral_norm tensor(6.2874, device='cuda:0')
alpha value of layer 4 ---411.2488708496094 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(131.0171, device='cuda:0')
spectral_norm tensor(12.3422, device='cuda:0')
frobenius_norm tensor(117.2556, device='cuda:0')
spectral_norm tensor(4.4561, device='cuda:0')
frobenius_norm tensor(117.0701, device='cuda:0')
spectral_norm tensor(6.4393, device='cuda:0')
alpha value of layer 5 ---378.5376892089844 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(133.2534, device='cuda:0')
spectral_norm tensor(13.9346, device='cuda:0')
frobenius_norm tensor(116.8471, device='cuda:0')
spectral_norm tensor(4.7412, device='cuda:0')
frobenius_norm tensor(116.4051, device='cuda:0')
spectral_norm tensor(6.2935, device='cuda:0')
alpha value of layer 6 ---346.97930908203125 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(133.1796, device='cuda:0')
spectral_norm tensor(13.7900, device='cuda:0')
frobenius_norm tensor(117.2589, device='cuda:0')
spectral_norm tensor(4.9844, device='cuda:0')
frobenius_norm tensor(116.5975, device='cuda:0')
spectral_norm tensor(6.7392, device='cuda:0')
alpha value of layer 7 ---315.34832763671875 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(131.0625, device='cuda:0')
spectral_norm tensor(12.9479, device='cuda:0')
frobenius_norm tensor(118.7164, device='cuda:0')
spectral_norm tensor(5.3742, device='cuda:0')
frobenius_norm tensor(117.8239, device='cuda:0')
spectral_norm tensor(7.0607, device='cuda:0')
alpha value of layer 8 ---289.63446044921875 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(129.7933, device='cuda:0')
spectral_norm tensor(13.0345, device='cuda:0')
frobenius_norm tensor(119.5203, device='cuda:0')
spectral_norm tensor(5.3777, device='cuda:0')
frobenius_norm tensor(118.6356, device='cuda:0')
spectral_norm tensor(7.0941, device='cuda:0')
alpha value of layer 9 ---290.9284362792969 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(129.3888, device='cuda:0')
spectral_norm tensor(13.1949, device='cuda:0')
frobenius_norm tensor(120.7769, device='cuda:0')
spectral_norm tensor(5.5907, device='cuda:0')
frobenius_norm tensor(119.6504, device='cuda:0')
spectral_norm tensor(7.0719, device='cuda:0')
alpha value of layer 10 ---283.04052734375 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(128.9186, device='cuda:0')
spectral_norm tensor(13.5576, device='cuda:0')
frobenius_norm tensor(121.8036, device='cuda:0')
spectral_norm tensor(5.6766, device='cuda:0')
frobenius_norm tensor(120.4323, device='cuda:0')
spectral_norm tensor(7.4645, device='cuda:0')
alpha value of layer 11 ---270.3800048828125 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(128.1013, device='cuda:0')
spectral_norm tensor(13.0662, device='cuda:0')
frobenius_norm tensor(122.9129, device='cuda:0')
spectral_norm tensor(6.0042, device='cuda:0')
frobenius_norm tensor(121.4419, device='cuda:0')
spectral_norm tensor(6.8182, device='cuda:0')
alpha value of layer 12 ---277.48046875 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(127.6379, device='cuda:0')
spectral_norm tensor(13.2896, device='cuda:0')
frobenius_norm tensor(124.1647, device='cuda:0')
spectral_norm tensor(6.3249, device='cuda:0')
frobenius_norm tensor(122.4098, device='cuda:0')
spectral_norm tensor(6.4258, device='cuda:0')
alpha value of layer 13 ---280.17169189453125 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(127.3744, device='cuda:0')
spectral_norm tensor(13.1519, device='cuda:0')
frobenius_norm tensor(124.2991, device='cuda:0')
spectral_norm tensor(6.4910, device='cuda:0')
frobenius_norm tensor(122.5321, device='cuda:0')
spectral_norm tensor(6.1543, device='cuda:0')
alpha value of layer 14 ---285.63787841796875 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(128.0534, device='cuda:0')
spectral_norm tensor(13.0927, device='cuda:0')
frobenius_norm tensor(124.9728, device='cuda:0')
spectral_norm tensor(6.8014, device='cuda:0')
frobenius_norm tensor(122.9694, device='cuda:0')
spectral_norm tensor(5.7687, device='cuda:0')
alpha value of layer 15 ---295.8956298828125 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(128.9326, device='cuda:0')
spectral_norm tensor(13.4859, device='cuda:0')
frobenius_norm tensor(124.8730, device='cuda:0')
spectral_norm tensor(7.0698, device='cuda:0')
frobenius_norm tensor(122.8834, device='cuda:0')
spectral_norm tensor(5.4697, device='cuda:0')
alpha value of layer 16 ---302.703857421875 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(130.1418, device='cuda:0')
spectral_norm tensor(13.9212, device='cuda:0')
frobenius_norm tensor(124.4075, device='cuda:0')
spectral_norm tensor(6.5251, device='cuda:0')
frobenius_norm tensor(122.7542, device='cuda:0')
spectral_norm tensor(5.4324, device='cuda:0')
alpha value of layer 17 ---320.5066833496094 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(131.3037, device='cuda:0')
spectral_norm tensor(13.5630, device='cuda:0')
frobenius_norm tensor(124.0418, device='cuda:0')
spectral_norm tensor(6.0638, device='cuda:0')
frobenius_norm tensor(122.6318, device='cuda:0')
spectral_norm tensor(5.3899, device='cuda:0')
alpha value of layer 18 ---343.27899169921875 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(131.7776, device='cuda:0')
spectral_norm tensor(12.6322, device='cuda:0')
frobenius_norm tensor(124.0385, device='cuda:0')
spectral_norm tensor(5.9170, device='cuda:0')
frobenius_norm tensor(122.9026, device='cuda:0')
spectral_norm tensor(5.5908, device='cuda:0')
alpha value of layer 19 ---343.8408203125 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(132.4897, device='cuda:0')
spectral_norm tensor(12.7395, device='cuda:0')
frobenius_norm tensor(123.9540, device='cuda:0')
spectral_norm tensor(6.1100, device='cuda:0')
frobenius_norm tensor(122.8897, device='cuda:0')
spectral_norm tensor(5.1633, device='cuda:0')
alpha value of layer 20 ---362.06610107421875 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(133.3879, device='cuda:0')
spectral_norm tensor(12.1366, device='cuda:0')
frobenius_norm tensor(123.7530, device='cuda:0')
spectral_norm tensor(5.6965, device='cuda:0')
frobenius_norm tensor(122.8804, device='cuda:0')
spectral_norm tensor(4.8811, device='cuda:0')
alpha value of layer 21 ---408.834228515625 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(134.1589, device='cuda:0')
spectral_norm tensor(11.9229, device='cuda:0')
frobenius_norm tensor(123.6884, device='cuda:0')
spectral_norm tensor(5.3241, device='cuda:0')
frobenius_norm tensor(122.9257, device='cuda:0')
spectral_norm tensor(5.2778, device='cuda:0')
alpha value of layer 22 ---402.9353942871094 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(134.1199, device='cuda:0')
spectral_norm tensor(10.9135, device='cuda:0')
frobenius_norm tensor(124.2959, device='cuda:0')
spectral_norm tensor(4.9033, device='cuda:0')
frobenius_norm tensor(123.6594, device='cuda:0')
spectral_norm tensor(5.8655, device='cuda:0')
alpha value of layer 23 ---412.6978454589844 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(134.4485, device='cuda:0')
spectral_norm tensor(10.8745, device='cuda:0')
frobenius_norm tensor(124.6739, device='cuda:0')
spectral_norm tensor(4.6898, device='cuda:0')
frobenius_norm tensor(124.1024, device='cuda:0')
spectral_norm tensor(5.6106, device='cuda:0')
alpha value of layer 24 ---449.614501953125 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(134.7100, device='cuda:0')
spectral_norm tensor(10.7878, device='cuda:0')
frobenius_norm tensor(125.2170, device='cuda:0')
spectral_norm tensor(4.9540, device='cuda:0')
frobenius_norm tensor(124.7208, device='cuda:0')
spectral_norm tensor(5.3156, device='cuda:0')
alpha value of layer 25 ---448.44183349609375 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(135.1252, device='cuda:0')
spectral_norm tensor(11.1821, device='cuda:0')
frobenius_norm tensor(125.6647, device='cuda:0')
spectral_norm tensor(5.8583, device='cuda:0')
frobenius_norm tensor(125.1040, device='cuda:0')
spectral_norm tensor(5.0074, device='cuda:0')
alpha value of layer 26 ---410.114013671875 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(135.2713, device='cuda:0')
spectral_norm tensor(11.5424, device='cuda:0')
frobenius_norm tensor(126.2993, device='cuda:0')
spectral_norm tensor(6.9998, device='cuda:0')
frobenius_norm tensor(125.7692, device='cuda:0')
spectral_norm tensor(5.1612, device='cuda:0')
alpha value of layer 27 ---352.2416687011719 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(134.6884, device='cuda:0')
spectral_norm tensor(11.4798, device='cuda:0')
frobenius_norm tensor(127.5331, device='cuda:0')
spectral_norm tensor(9.0437, device='cuda:0')
frobenius_norm tensor(126.5359, device='cuda:0')
spectral_norm tensor(4.9416, device='cuda:0')
alpha value of layer 28 ---330.72796630859375 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(135.0423, device='cuda:0')
spectral_norm tensor(12.0559, device='cuda:0')
frobenius_norm tensor(128.7051, device='cuda:0')
spectral_norm tensor(11.3077, device='cuda:0')
frobenius_norm tensor(126.9749, device='cuda:0')
spectral_norm tensor(4.4258, device='cuda:0')
alpha value of layer 29 ---359.37579345703125 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(138.1487, device='cuda:0')
spectral_norm tensor(19.7267, device='cuda:0')
frobenius_norm tensor(130.8807, device='cuda:0')
spectral_norm tensor(19.9367, device='cuda:0')
frobenius_norm tensor(126.2216, device='cuda:0')
spectral_norm tensor(4.5236, device='cuda:0')
alpha value of layer 30 ---290.23907470703125 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
frobenius_norm tensor(144.1483, device='cuda:0')
spectral_norm tensor(19.9982, device='cuda:0')
frobenius_norm tensor(135.9538, device='cuda:0')
spectral_norm tensor(19.9404, device='cuda:0')
frobenius_norm tensor(126.0626, device='cuda:0')
spectral_norm tensor(7.8316, device='cuda:0')
alpha value of layer 31 ---119.1807861328125 
metric_name stable_rank: [24, 25, 3, 2, 23, 4, 26, 21, 22, 5, 20, 29, 27, 6, 19, 18, 28, 17, 7, 16, 15, 9, 30, 8, 14, 10, 13, 12, 11, 1, 31, 0]
Begin main_assign: Llama-2-7b-hf mlp  effective_rank

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.39s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 11.39s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.44s/it]
Once upon a time, my father-in-law went to the bank to change a cheque. He was asked to write his signature on the cheque and to then place a tick in the box indicating whether the cheque was a deposit or a withdrawal.
My father-in-law was confused. He was not accustomed to the new style of cheque, which was introduced in the 1980s.
β€œI know it says β€˜deposit’, but
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 0 ---3572.474365234375 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 1 ---3627.507568359375 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 2 ---3733.4091796875 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 3 ---3785.27880859375 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 4 ---3790.103271484375 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 5 ---3778.20458984375 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 6 ---3768.807373046875 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 7 ---3756.693359375 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 8 ---3748.4443359375 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 9 ---3745.5185546875 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 10 ---3735.50341796875 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 11 ---3737.810302734375 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 12 ---3740.48388671875 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 13 ---3753.927734375 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 14 ---3753.2763671875 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 15 ---3771.952880859375 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 16 ---3771.9111328125 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 17 ---3772.70849609375 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 18 ---3783.5595703125 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 19 ---3788.821044921875 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 20 ---3790.424560546875 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 21 ---3790.768310546875 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 22 ---3790.56396484375 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 23 ---3793.769287109375 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 24 ---3795.335693359375 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 25 ---3797.1728515625 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 26 ---3800.90966796875 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 27 ---3804.0595703125 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 28 ---3810.544921875 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 29 ---3812.28857421875 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 30 ---3802.36669921875 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 31 ---3771.994873046875 
metric_name effective_rank: [29, 28, 27, 30, 26, 25, 24, 23, 21, 22, 20, 4, 19, 3, 18, 5, 17, 31, 15, 16, 6, 7, 13, 14, 8, 9, 12, 11, 10, 2, 1, 0]
Begin main_assign: Llama-2-7b-hf mlp  ZD

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.59s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 11.55s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 12.60s/it]
Once upon a time, in a faraway land, there lived a prince and a princess. They loved each other very much. The prince was very rich, but the princess was poor. The prince loved the princess so much that he wanted to give her everything he had.
One day, the prince decided to give the princess a gift. He went to the market and bought her a beautiful golden ring. The princess was very happy. She loved the ring. But the prince was not happy
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 0 ---0.15578114986419678 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 1 ---0.15707579255104065 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 2 ---0.15797409415245056 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 3 ---0.1574869602918625 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 4 ---0.15727774798870087 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 5 ---0.15676063299179077 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 6 ---0.1562662124633789 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 7 ---0.15596774220466614 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 8 ---0.1566615253686905 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 9 ---0.1561465859413147 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 10 ---0.15556025505065918 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 11 ---0.15571480989456177 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 12 ---0.15566584467887878 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 13 ---0.15572252869606018 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 14 ---0.15585064888000488 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 15 ---0.15579025447368622 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 16 ---0.15610937774181366 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 17 ---0.1567423790693283 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 18 ---0.15685215592384338 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 19 ---0.15697705745697021 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 20 ---0.15734341740608215 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 21 ---0.1579303741455078 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 22 ---0.15809854865074158 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 23 ---0.15812799334526062 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 24 ---0.1577608585357666 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 25 ---0.15747487545013428 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 26 ---0.1573786735534668 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 27 ---0.15686684846878052 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 28 ---0.15638381242752075 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 29 ---0.1558859944343567 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 30 ---0.1538189947605133 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 31 ---0.15391211211681366 
metric_name ZD: [23, 22, 2, 21, 24, 3, 25, 26, 20, 4, 1, 19, 27, 18, 5, 17, 8, 28, 6, 9, 16, 7, 29, 14, 15, 0, 13, 11, 12, 10, 31, 30]
Begin main_assign: Llama-2-7b-hf mlp  head_diversity

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.53s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 11.41s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:24<00:00, 12.47s/it]
Once upon a time, there were three kingdoms. The first kingdom was ruled by a king who was very wise. The second kingdom was ruled by a king who was very greedy. The third kingdom was ruled by a king who was very lazy.
The first king was very happy and lived in peace with his people. The second king was very unhappy and lived in fear of his people. The third king was very sad and lived in shame with his people.
One day, the first king decided to
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
Traceback (most recent call last):
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/main_assign.py", line 58, in <module>
    all_layer_alpha = calculate_expert(model, metric=metric_name, keyword=keyword)
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/alphalora/expert_number.py", line 354, in calculate_expert
    all_layer_alpha.append(torch.stack(layer_final_alpha).mean().item())
RuntimeError: stack expects a non-empty TensorList
Begin main_assign: Llama-2-7b-hf mlp  coherence

Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 1/2 [00:18<00:18, 18.65s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 11.55s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 2/2 [00:25<00:00, 12.61s/it]
Once upon a time, I was a child. I was full of dreams and visions of the future. I believed in the power of love and in the strength of family. I was the idealist, the dreamer, the one who believed that all good things were possible.
Then I grew up. I became a teenager. I was still full of dreams and visions of the future, but the dreams were tinged with darkness, and the visions were full of desp
LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 4096, padding_idx=0)
    (layers): ModuleList(
      (0-31): 32 x LlamaDecoderLayer(
        (self_attn): LlamaAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (v_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (up_proj): Linear(in_features=4096, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
        (post_attention_layernorm): LlamaRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): LlamaRMSNorm((4096,), eps=1e-05)
    (rotary_emb): LlamaRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
config: 
 LlamaConfig {
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 0,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "vocab_size": 32000
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 0 ---0.018758879974484444 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 1 ---0.015916038304567337 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 2 ---0.014297164976596832 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 3 ---0.013034423813223839 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 4 ---0.012964712455868721 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 5 ---0.013287676498293877 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 6 ---0.013558547012507915 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 7 ---0.013750488869845867 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 8 ---0.013907302170991898 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 9 ---0.013899993151426315 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 10 ---0.014043152332305908 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 11 ---0.014066706411540508 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 12 ---0.01396130956709385 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 13 ---0.013774177059531212 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 14 ---0.013727117329835892 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 15 ---0.013336378149688244 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 16 ---0.013238323852419853 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 17 ---0.013199622742831707 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 18 ---0.012931596487760544 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 19 ---0.012751361355185509 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 20 ---0.012693298980593681 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 21 ---0.012600544840097427 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 22 ---0.012644654139876366 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 23 ---0.012538459151983261 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 24 ---0.012461837381124496 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 25 ---0.012478632852435112 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 26 ---0.012449456378817558 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 27 ---0.012493574991822243 
Processing layer 28--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 28 ---0.012300195172429085 
Processing layer 29--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 29 ---0.01232621818780899 
Processing layer 30--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 30 ---0.012763611972332 
Processing layer 31--subset--{'mlp.gate_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.up_proj': Linear(in_features=4096, out_features=11008, bias=False), 'mlp.down_proj': Linear(in_features=11008, out_features=4096, bias=False)}
alpha value of layer 31 ---0.014904310926795006 
metric_name coherence: [0, 1, 31, 2, 11, 10, 12, 8, 9, 13, 7, 14, 6, 15, 5, 16, 17, 3, 4, 18, 30, 19, 20, 22, 21, 23, 27, 25, 24, 26, 29, 28]
Begin main_assign: Qwen2.5-7B self_attn  alpha

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.28it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.33it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.33it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.29it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.30it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a king who loved gold. He even had his own gold mine, but he was never satisfied with what he had. One day, he decided to go on a journey to find even more gold. He sent his men to explore the world and bring back as much gold as they could find. They searched high and low, but they could not find any more gold. The king was disappointed. He felt like he had been cheated. But then, he had an idea. He decided
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 0 ---3.7398271560668945 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 1 ---4.61224889755249 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 2 ---3.6950488090515137 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 3 ---3.5232601165771484 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 4 ---4.135606288909912 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 5 ---3.5275750160217285 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 6 ---6.992785453796387 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 7 ---3.8776655197143555 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 8 ---5.665498733520508 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 9 ---4.215641021728516 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 10 ---3.8878092765808105 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 11 ---4.219095706939697 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 12 ---3.7720558643341064 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 13 ---7.641180515289307 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 14 ---3.707275152206421 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 15 ---3.25449800491333 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 16 ---4.158566474914551 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 17 ---3.467252492904663 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 18 ---5.359913349151611 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 19 ---3.048678398132324 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 20 ---2.6340246200561523 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 21 ---4.8504228591918945 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 22 ---3.2433063983917236 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 23 ---6.264342308044434 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 24 ---3.845273494720459 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 25 ---4.786241054534912 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 26 ---2.9173049926757812 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 27 ---2.295574426651001 
metric_name alpha: [13, 6, 23, 8, 18, 21, 25, 1, 11, 9, 16, 4, 10, 7, 24, 12, 0, 14, 2, 5, 3, 17, 15, 22, 19, 26, 20, 27]
Begin main_assign: Qwen2.5-7B self_attn  alpha_hat

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:01,  1.56it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.63it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:01<00:00,  1.62it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.50it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.54it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a man who was in the habit of getting up at six o'clock every morning and jogging around his neighborhood. One morning, while he was out for his usual morning run, he saw an old man sitting in a park bench. He asked the old man what he was doing there. The old man replied,"I am waiting for my son to arrive." The man asked,"What does he do? Where does he work?" The old man said,"He is
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 0 ---11.435125350952148 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 1 ---7.411468505859375 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 2 ---7.694450378417969 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 3 ---7.890998363494873 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 4 ---7.172995567321777 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 5 ---7.2080488204956055 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 6 ---11.36629867553711 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 7 ---7.176176071166992 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 8 ---7.694736957550049 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 9 ---7.057432174682617 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 10 ---6.2363386154174805 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 11 ---6.52932071685791 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 12 ---7.182070732116699 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 13 ---8.655073165893555 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 14 ---5.977964401245117 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 15 ---5.821178436279297 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 16 ---7.714193820953369 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 17 ---6.244594573974609 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 18 ---7.704196929931641 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 19 ---5.97743558883667 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 20 ---5.515291213989258 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 21 ---7.423676490783691 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 22 ---6.235415458679199 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 23 ---11.209845542907715 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 24 ---7.722582817077637 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 25 ---10.762764930725098 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 26 ---7.431804180145264 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 27 ---8.220139503479004 
metric_name alpha_hat: [0, 6, 23, 25, 13, 27, 3, 24, 16, 18, 8, 2, 26, 21, 1, 5, 12, 7, 4, 9, 11, 17, 10, 22, 14, 19, 15, 20]
Begin main_assign: Qwen2.5-7B self_attn  stable_rank

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.21it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.29it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.31it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.37it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.34it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a family with 10 children. Each of the 10 children had a different number of books in their bookshelves. The first child had 1 book, the second had 2 books, the third had 3 books, and so on until the tenth child, who had 10 books. One day, the parents decided to redistribute the books so that each child would have the same number of books. How many books did each child end up with? To
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(74.6100, device='cuda:0')
spectral_norm tensor(22.8962, device='cuda:0')
frobenius_norm tensor(37.2340, device='cuda:0')
spectral_norm tensor(4.1839, device='cuda:0')
frobenius_norm tensor(12.2050, device='cuda:0')
spectral_norm tensor(1.2453, device='cuda:0')
frobenius_norm tensor(44.6291, device='cuda:0')
spectral_norm tensor(6.0001, device='cuda:0')
alpha value of layer 0 ---60.29820251464844 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(56.7970, device='cuda:0')
spectral_norm tensor(10.4783, device='cuda:0')
frobenius_norm tensor(29.9237, device='cuda:0')
spectral_norm tensor(4.7115, device='cuda:0')
frobenius_norm tensor(18.3318, device='cuda:0')
spectral_norm tensor(1.4635, device='cuda:0')
frobenius_norm tensor(51.8109, device='cuda:0')
spectral_norm tensor(3.7208, device='cuda:0')
alpha value of layer 1 ---105.13154602050781 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(65.4367, device='cuda:0')
spectral_norm tensor(5.5540, device='cuda:0')
frobenius_norm tensor(31.8038, device='cuda:0')
spectral_norm tensor(3.0331, device='cuda:0')
frobenius_norm tensor(14.7804, device='cuda:0')
spectral_norm tensor(1.2128, device='cuda:0')
frobenius_norm tensor(50.6930, device='cuda:0')
spectral_norm tensor(3.9768, device='cuda:0')
alpha value of layer 2 ---139.9442901611328 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(67.9445, device='cuda:0')
spectral_norm tensor(7.3888, device='cuda:0')
frobenius_norm tensor(32.4597, device='cuda:0')
spectral_norm tensor(3.6898, device='cuda:0')
frobenius_norm tensor(17.2702, device='cuda:0')
spectral_norm tensor(1.2119, device='cuda:0')
frobenius_norm tensor(53.1248, device='cuda:0')
spectral_norm tensor(3.7626, device='cuda:0')
alpha value of layer 3 ---141.09706115722656 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(64.7004, device='cuda:0')
spectral_norm tensor(6.6270, device='cuda:0')
frobenius_norm tensor(29.1071, device='cuda:0')
spectral_norm tensor(3.3637, device='cuda:0')
frobenius_norm tensor(20.8693, device='cuda:0')
spectral_norm tensor(1.5107, device='cuda:0')
frobenius_norm tensor(53.3331, device='cuda:0')
spectral_norm tensor(3.7430, device='cuda:0')
alpha value of layer 4 ---141.01356506347656 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(63.2364, device='cuda:0')
spectral_norm tensor(5.9598, device='cuda:0')
frobenius_norm tensor(26.6552, device='cuda:0')
spectral_norm tensor(2.6609, device='cuda:0')
frobenius_norm tensor(19.8491, device='cuda:0')
spectral_norm tensor(1.5480, device='cuda:0')
frobenius_norm tensor(53.4192, device='cuda:0')
spectral_norm tensor(4.0186, device='cuda:0')
alpha value of layer 5 ---138.5137939453125 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(64.2853, device='cuda:0')
spectral_norm tensor(5.5097, device='cuda:0')
frobenius_norm tensor(28.5616, device='cuda:0')
spectral_norm tensor(2.9881, device='cuda:0')
frobenius_norm tensor(20.6937, device='cuda:0')
spectral_norm tensor(1.4517, device='cuda:0')
frobenius_norm tensor(54.9730, device='cuda:0')
spectral_norm tensor(5.0745, device='cuda:0')
alpha value of layer 6 ---137.01039123535156 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(60.9057, device='cuda:0')
spectral_norm tensor(4.5698, device='cuda:0')
frobenius_norm tensor(23.8630, device='cuda:0')
spectral_norm tensor(2.5382, device='cuda:0')
frobenius_norm tensor(24.6983, device='cuda:0')
spectral_norm tensor(1.7165, device='cuda:0')
frobenius_norm tensor(60.3206, device='cuda:0')
spectral_norm tensor(3.5918, device='cuda:0')
alpha value of layer 7 ---188.773193359375 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(63.3943, device='cuda:0')
spectral_norm tensor(3.9526, device='cuda:0')
frobenius_norm tensor(27.2992, device='cuda:0')
spectral_norm tensor(2.5236, device='cuda:0')
frobenius_norm tensor(20.6254, device='cuda:0')
spectral_norm tensor(1.4007, device='cuda:0')
frobenius_norm tensor(55.2465, device='cuda:0')
spectral_norm tensor(3.4821, device='cuda:0')
alpha value of layer 8 ---210.70074462890625 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(58.6742, device='cuda:0')
spectral_norm tensor(4.6933, device='cuda:0')
frobenius_norm tensor(23.2825, device='cuda:0')
spectral_norm tensor(2.6721, device='cuda:0')
frobenius_norm tensor(24.7824, device='cuda:0')
spectral_norm tensor(1.5406, device='cuda:0')
frobenius_norm tensor(60.4736, device='cuda:0')
spectral_norm tensor(6.3921, device='cuda:0')
alpha value of layer 9 ---145.1187744140625 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(63.5265, device='cuda:0')
spectral_norm tensor(4.3337, device='cuda:0')
frobenius_norm tensor(27.1029, device='cuda:0')
spectral_norm tensor(2.6480, device='cuda:0')
frobenius_norm tensor(22.3527, device='cuda:0')
spectral_norm tensor(1.3822, device='cuda:0')
frobenius_norm tensor(57.0854, device='cuda:0')
spectral_norm tensor(4.1727, device='cuda:0')
alpha value of layer 10 ---192.07977294921875 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(64.2904, device='cuda:0')
spectral_norm tensor(4.0832, device='cuda:0')
frobenius_norm tensor(28.0532, device='cuda:0')
spectral_norm tensor(2.6312, device='cuda:0')
frobenius_norm tensor(19.8152, device='cuda:0')
spectral_norm tensor(1.4528, device='cuda:0')
frobenius_norm tensor(55.3427, device='cuda:0')
spectral_norm tensor(4.3578, device='cuda:0')
alpha value of layer 11 ---177.22564697265625 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(62.3252, device='cuda:0')
spectral_norm tensor(3.9938, device='cuda:0')
frobenius_norm tensor(26.8499, device='cuda:0')
spectral_norm tensor(2.5529, device='cuda:0')
frobenius_norm tensor(20.6057, device='cuda:0')
spectral_norm tensor(1.3954, device='cuda:0')
frobenius_norm tensor(55.6693, device='cuda:0')
spectral_norm tensor(4.6503, device='cuda:0')
alpha value of layer 12 ---178.88079833984375 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(61.0881, device='cuda:0')
spectral_norm tensor(4.2847, device='cuda:0')
frobenius_norm tensor(25.6297, device='cuda:0')
spectral_norm tensor(2.9570, device='cuda:0')
frobenius_norm tensor(22.4836, device='cuda:0')
spectral_norm tensor(1.3594, device='cuda:0')
frobenius_norm tensor(57.5732, device='cuda:0')
spectral_norm tensor(5.3631, device='cuda:0')
alpha value of layer 13 ---166.80108642578125 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(59.9385, device='cuda:0')
spectral_norm tensor(4.1989, device='cuda:0')
frobenius_norm tensor(25.3315, device='cuda:0')
spectral_norm tensor(2.3592, device='cuda:0')
frobenius_norm tensor(19.7791, device='cuda:0')
spectral_norm tensor(1.4382, device='cuda:0')
frobenius_norm tensor(54.6680, device='cuda:0')
spectral_norm tensor(4.8688, device='cuda:0')
alpha value of layer 14 ---158.56539916992188 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(62.2632, device='cuda:0')
spectral_norm tensor(4.4386, device='cuda:0')
frobenius_norm tensor(26.5240, device='cuda:0')
spectral_norm tensor(2.5572, device='cuda:0')
frobenius_norm tensor(20.8667, device='cuda:0')
spectral_norm tensor(1.5160, device='cuda:0')
frobenius_norm tensor(55.3834, device='cuda:0')
spectral_norm tensor(4.4431, device='cuda:0')
alpha value of layer 15 ---162.2994384765625 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(59.5504, device='cuda:0')
spectral_norm tensor(4.1705, device='cuda:0')
frobenius_norm tensor(23.7914, device='cuda:0')
spectral_norm tensor(2.3827, device='cuda:0')
frobenius_norm tensor(22.4299, device='cuda:0')
spectral_norm tensor(1.8284, device='cuda:0')
frobenius_norm tensor(57.2100, device='cuda:0')
spectral_norm tensor(5.3112, device='cuda:0')
alpha value of layer 16 ---142.52708435058594 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(61.2952, device='cuda:0')
spectral_norm tensor(3.9247, device='cuda:0')
frobenius_norm tensor(24.2607, device='cuda:0')
spectral_norm tensor(2.3428, device='cuda:0')
frobenius_norm tensor(22.0993, device='cuda:0')
spectral_norm tensor(1.6527, device='cuda:0')
frobenius_norm tensor(56.9147, device='cuda:0')
spectral_norm tensor(4.7962, device='cuda:0')
alpha value of layer 17 ---167.6918182373047 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(57.8086, device='cuda:0')
spectral_norm tensor(4.1784, device='cuda:0')
frobenius_norm tensor(23.1346, device='cuda:0')
spectral_norm tensor(2.7649, device='cuda:0')
frobenius_norm tensor(24.9173, device='cuda:0')
spectral_norm tensor(1.5424, device='cuda:0')
frobenius_norm tensor(60.8592, device='cuda:0')
spectral_norm tensor(5.2139, device='cuda:0')
alpha value of layer 18 ---164.66351318359375 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(57.4449, device='cuda:0')
spectral_norm tensor(4.5447, device='cuda:0')
frobenius_norm tensor(21.3000, device='cuda:0')
spectral_norm tensor(2.4431, device='cuda:0')
frobenius_norm tensor(25.0779, device='cuda:0')
spectral_norm tensor(1.6237, device='cuda:0')
frobenius_norm tensor(59.6389, device='cuda:0')
spectral_norm tensor(4.9505, device='cuda:0')
alpha value of layer 19 ---154.86126708984375 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(58.7482, device='cuda:0')
spectral_norm tensor(4.0858, device='cuda:0')
frobenius_norm tensor(22.3411, device='cuda:0')
spectral_norm tensor(2.3521, device='cuda:0')
frobenius_norm tensor(25.9143, device='cuda:0')
spectral_norm tensor(1.7104, device='cuda:0')
frobenius_norm tensor(60.9286, device='cuda:0')
spectral_norm tensor(4.8709, device='cuda:0')
alpha value of layer 20 ---170.74554443359375 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(57.1627, device='cuda:0')
spectral_norm tensor(3.6813, device='cuda:0')
frobenius_norm tensor(19.9702, device='cuda:0')
spectral_norm tensor(2.2489, device='cuda:0')
frobenius_norm tensor(27.7738, device='cuda:0')
spectral_norm tensor(1.6762, device='cuda:0')
frobenius_norm tensor(63.2683, device='cuda:0')
spectral_norm tensor(5.2737, device='cuda:0')
alpha value of layer 21 ---184.6076202392578 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(58.1757, device='cuda:0')
spectral_norm tensor(4.0771, device='cuda:0')
frobenius_norm tensor(19.4699, device='cuda:0')
spectral_norm tensor(1.9257, device='cuda:0')
frobenius_norm tensor(27.1717, device='cuda:0')
spectral_norm tensor(2.0305, device='cuda:0')
frobenius_norm tensor(63.5510, device='cuda:0')
spectral_norm tensor(4.3551, device='cuda:0')
alpha value of layer 22 ---174.45973205566406 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(59.5436, device='cuda:0')
spectral_norm tensor(4.0933, device='cuda:0')
frobenius_norm tensor(20.5584, device='cuda:0')
spectral_norm tensor(2.1754, device='cuda:0')
frobenius_norm tensor(27.5827, device='cuda:0')
spectral_norm tensor(1.8698, device='cuda:0')
frobenius_norm tensor(64.9988, device='cuda:0')
spectral_norm tensor(5.3918, device='cuda:0')
alpha value of layer 23 ---165.96688842773438 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(56.8169, device='cuda:0')
spectral_norm tensor(3.8277, device='cuda:0')
frobenius_norm tensor(19.4813, device='cuda:0')
spectral_norm tensor(1.8291, device='cuda:0')
frobenius_norm tensor(31.0836, device='cuda:0')
spectral_norm tensor(2.3168, device='cuda:0')
frobenius_norm tensor(65.3215, device='cuda:0')
spectral_norm tensor(6.2412, device='cuda:0')
alpha value of layer 24 ---155.8324432373047 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(55.3445, device='cuda:0')
spectral_norm tensor(3.8164, device='cuda:0')
frobenius_norm tensor(17.7185, device='cuda:0')
spectral_norm tensor(1.8025, device='cuda:0')
frobenius_norm tensor(33.9660, device='cuda:0')
spectral_norm tensor(3.0984, device='cuda:0')
frobenius_norm tensor(68.8981, device='cuda:0')
spectral_norm tensor(5.3780, device='cuda:0')
alpha value of layer 25 ---147.80517578125 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(51.7868, device='cuda:0')
spectral_norm tensor(3.9548, device='cuda:0')
frobenius_norm tensor(16.9575, device='cuda:0')
spectral_norm tensor(1.9295, device='cuda:0')
frobenius_norm tensor(40.6153, device='cuda:0')
spectral_norm tensor(3.1825, device='cuda:0')
frobenius_norm tensor(71.6628, device='cuda:0')
spectral_norm tensor(6.2830, device='cuda:0')
alpha value of layer 26 ---135.41717529296875 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
frobenius_norm tensor(56.6802, device='cuda:0')
spectral_norm tensor(7.8725, device='cuda:0')
frobenius_norm tensor(18.0258, device='cuda:0')
spectral_norm tensor(2.1181, device='cuda:0')
frobenius_norm tensor(36.7123, device='cuda:0')
spectral_norm tensor(4.5755, device='cuda:0')
frobenius_norm tensor(66.9187, device='cuda:0')
spectral_norm tensor(10.3449, device='cuda:0')
alpha value of layer 27 ---57.62150573730469 
metric_name stable_rank: [8, 10, 7, 21, 12, 11, 22, 20, 17, 13, 23, 18, 15, 14, 24, 19, 25, 9, 16, 3, 4, 2, 5, 6, 26, 1, 0, 27]
Begin main_assign: Qwen2.5-7B self_attn  effective_rank

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.40it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.46it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.46it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.54it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.50it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, in a faraway land, there was a wizard named Zephyr. Zephyr had a magical garden filled with enchanted flowers that bloomed only once a year on the night of the full moon. Each flower had a unique power: some could grant wishes, others could heal, and some could even bring the dead back to life. Zephyr knew that the garden was in danger, and he needed to protect it. He decided to create a secret code to lock the garden's entrance
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 0 ---1452.84130859375 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 1 ---1305.515869140625 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 2 ---1505.5045166015625 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 3 ---1528.22900390625 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 4 ---1506.9344482421875 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 5 ---1515.52099609375 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 6 ---1521.9154052734375 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 7 ---1530.30126953125 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 8 ---1513.680908203125 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 9 ---1508.0103759765625 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 10 ---1541.102294921875 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 11 ---1515.346923828125 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 12 ---1515.414306640625 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 13 ---1518.91796875 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 14 ---1460.6475830078125 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 15 ---1482.7188720703125 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 16 ---1503.2802734375 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 17 ---1507.509033203125 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 18 ---1475.742431640625 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 19 ---1503.236083984375 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 20 ---1508.0513916015625 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 21 ---1513.8974609375 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 22 ---1492.510986328125 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 23 ---1560.966552734375 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 24 ---1547.26904296875 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 25 ---1559.457763671875 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 26 ---1530.5631103515625 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 27 ---1474.574462890625 
metric_name effective_rank: [23, 25, 24, 10, 26, 7, 3, 6, 13, 5, 12, 11, 21, 8, 20, 9, 17, 4, 2, 16, 19, 22, 15, 18, 27, 14, 0, 1]
Begin main_assign: Qwen2.5-7B self_attn  ZD

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:01,  1.55it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.64it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:01<00:00,  1.64it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.74it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.70it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time there was a very special fish, who lived in a very special lake, and who had a very special name.
And when the fish was born, his parents named him Nemo.
Nemo was a very happy fish, who loved to swim around his lake, and who had a lot of friends.
There was Dory, the forgetful fish, who would always forget where she was going, and Marlin, the protective fish, who would always look after his family.
Nemo was also
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 0 ---0.14184384047985077 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 1 ---0.13445976376533508 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 2 ---0.1448441445827484 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 3 ---0.14360329508781433 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 4 ---0.14149385690689087 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 5 ---0.14219337701797485 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 6 ---0.14448319375514984 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 7 ---0.14329871535301208 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 8 ---0.14073410630226135 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 9 ---0.14020180702209473 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 10 ---0.14346933364868164 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 11 ---0.14193479716777802 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 12 ---0.1403268575668335 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 13 ---0.14010006189346313 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 14 ---0.13355384767055511 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 15 ---0.13806670904159546 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 16 ---0.13962170481681824 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 17 ---0.13812372088432312 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 18 ---0.13966597616672516 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 19 ---0.13903221487998962 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 20 ---0.1419043242931366 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 21 ---0.13662637770175934 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 22 ---0.13463997840881348 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 23 ---0.13744638860225677 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 24 ---0.1426282525062561 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 25 ---0.1387733370065689 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 26 ---0.13506180047988892 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 27 ---0.13298790156841278 
metric_name ZD: [2, 6, 3, 10, 7, 24, 5, 11, 20, 0, 4, 8, 12, 9, 13, 18, 16, 19, 25, 17, 15, 23, 21, 26, 22, 1, 14, 27]
Begin main_assign: Qwen2.5-7B self_attn  head_diversity

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.18it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.12it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.11it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.18it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.16it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time in the land of Mathoria, there was a magical forest where every tree had a unique number of leaves. The King of Mathoria decided to plant a new tree every day for a week (7 days), starting with 1 leaf on the first day and increasing the number of leaves by 1 each day. However, a mischievous sprite named Sprinkle loved to play tricks on the trees. On every even day, Sprinkle would randomly remove a number of leaves from the tree, between
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
Traceback (most recent call last):
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/main_assign.py", line 58, in <module>
    all_layer_alpha = calculate_expert(model, metric=metric_name, keyword=keyword)
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/alphalora/expert_number.py", line 350, in calculate_expert
    layer_final_alpha = func_call[metric](num_heads, subset)
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/alphalora/expert_number.py", line 310, in head_diversity_asssist
    ans.append(head_diversity(W, num_heads))
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/alphalora/expert_number.py", line 191, in head_diversity
    w_heads = W.view(num_heads, head_dim, d_in)
RuntimeError: shape '[28, 18, 3584]' is invalid for input of size 1835008
Begin main_assign: Qwen2.5-7B self_attn  coherence

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.19it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.21it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.20it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.29it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.25it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time in the not-so-distant past, the average person had a choice of two or three local phone companies and one long distance company. Now, you have to be an expert to navigate the maze of telephone companies and options. This article will help you make the right choice for your telephone needs.
If you are using a cellular phone, you should only use it in an emergency. It is important to use a cell phone only in emergencies because they use a lot of battery power. If you use a
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 0 ---0.019099362194538116 
Processing layer 1--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 1 ---0.03270909935235977 
Processing layer 2--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 2 ---0.02031659334897995 
Processing layer 3--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 3 ---0.020667918026447296 
Processing layer 4--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 4 ---0.021066918969154358 
Processing layer 5--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 5 ---0.019672438502311707 
Processing layer 6--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 6 ---0.020373258739709854 
Processing layer 7--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 7 ---0.01879500225186348 
Processing layer 8--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 8 ---0.018471794202923775 
Processing layer 9--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 9 ---0.01999843120574951 
Processing layer 10--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 10 ---0.018006717786192894 
Processing layer 11--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 11 ---0.019990842789411545 
Processing layer 12--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 12 ---0.01996159367263317 
Processing layer 13--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 13 ---0.020418085157871246 
Processing layer 14--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 14 ---0.020115870982408524 
Processing layer 15--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 15 ---0.02094407193362713 
Processing layer 16--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 16 ---0.02063441462814808 
Processing layer 17--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 17 ---0.018953558057546616 
Processing layer 18--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 18 ---0.020888380706310272 
Processing layer 19--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 19 ---0.01945885643362999 
Processing layer 20--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 20 ---0.019533313810825348 
Processing layer 21--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 21 ---0.018554046750068665 
Processing layer 22--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 22 ---0.020378313958644867 
Processing layer 23--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 23 ---0.019100410863757133 
Processing layer 24--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 24 ---0.018557211384177208 
Processing layer 25--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 25 ---0.019475571811199188 
Processing layer 26--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 26 ---0.021406373009085655 
Processing layer 27--subset--{'self_attn.q_proj': Linear(in_features=3584, out_features=3584, bias=True), 'self_attn.k_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.v_proj': Linear(in_features=3584, out_features=512, bias=True), 'self_attn.o_proj': Linear(in_features=3584, out_features=3584, bias=False)}
alpha value of layer 27 ---0.02655916102230549 
metric_name coherence: [1, 27, 26, 4, 15, 18, 3, 16, 13, 22, 6, 2, 14, 9, 11, 12, 5, 20, 25, 19, 23, 0, 17, 7, 24, 21, 8, 10]
Begin main_assign: Qwen2.5-7B mlp  alpha

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.32it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.37it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.35it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.44it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.41it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time there was a little girl named Maria. She was 10 years old and she loved to play with her dolls. Every night before she went to sleep she would place her dolls on her bed and have a tea party with them. One night, she was feeling very lonely. She wanted someone to talk to who could understand her. She wanted to be with her dolls, but she wanted a friend too. She prayed that God would send her a friend. She prayed that God would send her a
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 0 ---5.5507073402404785 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 1 ---2.925907850265503 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 2 ---3.427783727645874 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 3 ---4.130731105804443 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 4 ---4.2790751457214355 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 5 ---4.67555570602417 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 6 ---5.680507659912109 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 7 ---5.469402313232422 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 8 ---4.489261150360107 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 9 ---5.958518981933594 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 10 ---5.11647367477417 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 11 ---4.431467056274414 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 12 ---4.447659969329834 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 13 ---4.224405288696289 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 14 ---4.203671932220459 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 15 ---4.193532943725586 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 16 ---4.277862548828125 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 17 ---4.189056396484375 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 18 ---4.484411716461182 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 19 ---4.689056396484375 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 20 ---4.993287563323975 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 21 ---6.104448318481445 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 22 ---6.7987060546875 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 23 ---6.16623067855835 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 24 ---6.090585231781006 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 25 ---5.552665710449219 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 26 ---5.523178577423096 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 27 ---4.90322208404541 
metric_name alpha: [22, 23, 21, 24, 9, 6, 25, 0, 26, 7, 10, 20, 27, 19, 5, 8, 18, 12, 11, 4, 16, 13, 14, 15, 17, 3, 2, 1]
Begin main_assign: Qwen2.5-7B mlp  alpha_hat

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:01,  1.57it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.65it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:01<00:00,  1.64it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.71it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.68it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, a little boy named Timmy went to visit his grandmother. On the way, he saw a beautiful rainbow in the sky. He wanted to find the pot of gold at the end of the rainbow. But the rainbow led him to a magical door that was locked with a puzzle. 
The puzzle was: "I am not alive, but I grow; I don't have lungs, but I need air; I don't have a mouth, but water kills me. What am I?" 

Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 0 ---26.469465255737305 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 1 ---15.14222526550293 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 2 ---15.627280235290527 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 3 ---21.562671661376953 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 4 ---18.97063636779785 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 5 ---21.275915145874023 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 6 ---20.404766082763672 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 7 ---21.564342498779297 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 8 ---17.832380294799805 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 9 ---24.982494354248047 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 10 ---21.225040435791016 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 11 ---18.6888484954834 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 12 ---19.226669311523438 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 13 ---18.279586791992188 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 14 ---17.538372039794922 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 15 ---17.4776611328125 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 16 ---18.033130645751953 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 17 ---17.052593231201172 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 18 ---18.05915641784668 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 19 ---18.863903045654297 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 20 ---19.91156768798828 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 21 ---22.948781967163086 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 22 ---26.310537338256836 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 23 ---24.970985412597656 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 24 ---24.232511520385742 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 25 ---23.717098236083984 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 26 ---23.539913177490234 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 27 ---24.706113815307617 
metric_name alpha_hat: [0, 22, 9, 23, 27, 24, 25, 26, 21, 7, 3, 5, 10, 6, 20, 12, 4, 19, 11, 13, 18, 16, 8, 14, 15, 17, 2, 1]
Begin main_assign: Qwen2.5-7B mlp  stable_rank

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.23it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.28it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.28it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.35it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.32it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a little girl. She was very beautiful, but she was so bad that nobody liked her. She had no friends. She didn't want to play with other children. She didn't want to go to school. She lived by herself in a small house. The only thing that made her happy was a little dog. The little girl was very sad. She didn't know what to do. One day, she walked out of the house and saw a beautiful bird. She wanted to
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(126.6843, device='cuda:0')
spectral_norm tensor(37.7735, device='cuda:0')
frobenius_norm tensor(108.8807, device='cuda:0')
spectral_norm tensor(7.8392, device='cuda:0')
frobenius_norm tensor(115.3682, device='cuda:0')
spectral_norm tensor(6.5322, device='cuda:0')
alpha value of layer 0 ---172.02789306640625 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(123.2531, device='cuda:0')
spectral_norm tensor(20.7839, device='cuda:0')
frobenius_norm tensor(101.4097, device='cuda:0')
spectral_norm tensor(8.8381, device='cuda:0')
frobenius_norm tensor(101.5777, device='cuda:0')
spectral_norm tensor(13.5321, device='cuda:0')
alpha value of layer 1 ---74.3896484375 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(138.8778, device='cuda:0')
spectral_norm tensor(23.4270, device='cuda:0')
frobenius_norm tensor(112.7775, device='cuda:0')
spectral_norm tensor(6.5452, device='cuda:0')
frobenius_norm tensor(115.6860, device='cuda:0')
spectral_norm tensor(7.9797, device='cuda:0')
alpha value of layer 2 ---180.73681640625 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(153.6270, device='cuda:0')
spectral_norm tensor(22.2753, device='cuda:0')
frobenius_norm tensor(132.3810, device='cuda:0')
spectral_norm tensor(7.2662, device='cuda:0')
frobenius_norm tensor(131.2425, device='cuda:0')
spectral_norm tensor(17.0355, device='cuda:0')
alpha value of layer 3 ---146.2799072265625 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(156.7403, device='cuda:0')
spectral_norm tensor(22.8238, device='cuda:0')
frobenius_norm tensor(129.6389, device='cuda:0')
spectral_norm tensor(5.4833, device='cuda:0')
frobenius_norm tensor(128.7504, device='cuda:0')
spectral_norm tensor(8.4121, device='cuda:0')
alpha value of layer 4 ---280.12554931640625 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(149.4161, device='cuda:0')
spectral_norm tensor(21.1506, device='cuda:0')
frobenius_norm tensor(133.9768, device='cuda:0')
spectral_norm tensor(6.2399, device='cuda:0')
frobenius_norm tensor(132.0446, device='cuda:0')
spectral_norm tensor(8.4305, device='cuda:0')
alpha value of layer 5 ---252.07894897460938 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(151.2180, device='cuda:0')
spectral_norm tensor(14.3238, device='cuda:0')
frobenius_norm tensor(129.6978, device='cuda:0')
spectral_norm tensor(4.1238, device='cuda:0')
frobenius_norm tensor(127.6298, device='cuda:0')
spectral_norm tensor(7.3585, device='cuda:0')
alpha value of layer 6 ---467.14599609375 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(141.6723, device='cuda:0')
spectral_norm tensor(13.0737, device='cuda:0')
frobenius_norm tensor(133.2031, device='cuda:0')
spectral_norm tensor(5.1650, device='cuda:0')
frobenius_norm tensor(132.6786, device='cuda:0')
spectral_norm tensor(7.6574, device='cuda:0')
alpha value of layer 7 ---360.915771484375 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(139.1350, device='cuda:0')
spectral_norm tensor(12.2201, device='cuda:0')
frobenius_norm tensor(135.6841, device='cuda:0')
spectral_norm tensor(4.7790, device='cuda:0')
frobenius_norm tensor(134.1169, device='cuda:0')
spectral_norm tensor(8.0838, device='cuda:0')
alpha value of layer 8 ---403.66400146484375 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(152.4723, device='cuda:0')
spectral_norm tensor(28.9447, device='cuda:0')
frobenius_norm tensor(124.9508, device='cuda:0')
spectral_norm tensor(5.0401, device='cuda:0')
frobenius_norm tensor(123.2868, device='cuda:0')
spectral_norm tensor(7.9764, device='cuda:0')
alpha value of layer 9 ---293.7569580078125 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(141.8071, device='cuda:0')
spectral_norm tensor(14.3111, device='cuda:0')
frobenius_norm tensor(133.1904, device='cuda:0')
spectral_norm tensor(5.2121, device='cuda:0')
frobenius_norm tensor(132.4129, device='cuda:0')
spectral_norm tensor(9.0536, device='cuda:0')
alpha value of layer 10 ---321.69720458984375 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(139.0032, device='cuda:0')
spectral_norm tensor(12.7478, device='cuda:0')
frobenius_norm tensor(135.5063, device='cuda:0')
spectral_norm tensor(5.4040, device='cuda:0')
frobenius_norm tensor(134.1321, device='cuda:0')
spectral_norm tensor(9.8842, device='cuda:0')
alpha value of layer 11 ---310.609130859375 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(136.5591, device='cuda:0')
spectral_norm tensor(12.8626, device='cuda:0')
frobenius_norm tensor(136.9887, device='cuda:0')
spectral_norm tensor(5.2525, device='cuda:0')
frobenius_norm tensor(135.8750, device='cuda:0')
spectral_norm tensor(10.9823, device='cuda:0')
alpha value of layer 12 ---315.332763671875 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(139.4029, device='cuda:0')
spectral_norm tensor(12.9032, device='cuda:0')
frobenius_norm tensor(135.3871, device='cuda:0')
spectral_norm tensor(5.2956, device='cuda:0')
frobenius_norm tensor(133.7299, device='cuda:0')
spectral_norm tensor(10.5605, device='cuda:0')
alpha value of layer 13 ---310.2343444824219 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(136.9790, device='cuda:0')
spectral_norm tensor(12.1678, device='cuda:0')
frobenius_norm tensor(136.4235, device='cuda:0')
spectral_norm tensor(5.1185, device='cuda:0')
frobenius_norm tensor(134.9485, device='cuda:0')
spectral_norm tensor(9.6906, device='cuda:0')
alpha value of layer 14 ---343.6784362792969 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(135.3356, device='cuda:0')
spectral_norm tensor(11.3039, device='cuda:0')
frobenius_norm tensor(137.9369, device='cuda:0')
spectral_norm tensor(5.1105, device='cuda:0')
frobenius_norm tensor(135.9716, device='cuda:0')
spectral_norm tensor(10.2615, device='cuda:0')
alpha value of layer 15 ---349.14691162109375 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(135.1444, device='cuda:0')
spectral_norm tensor(11.1679, device='cuda:0')
frobenius_norm tensor(137.6841, device='cuda:0')
spectral_norm tensor(5.1499, device='cuda:0')
frobenius_norm tensor(135.1051, device='cuda:0')
spectral_norm tensor(10.5823, device='cuda:0')
alpha value of layer 16 ---341.401611328125 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(133.7680, device='cuda:0')
spectral_norm tensor(11.1640, device='cuda:0')
frobenius_norm tensor(138.4800, device='cuda:0')
spectral_norm tensor(5.2358, device='cuda:0')
frobenius_norm tensor(135.3299, device='cuda:0')
spectral_norm tensor(8.6134, device='cuda:0')
alpha value of layer 17 ---363.3155212402344 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(133.3184, device='cuda:0')
spectral_norm tensor(10.9756, device='cuda:0')
frobenius_norm tensor(140.8582, device='cuda:0')
spectral_norm tensor(5.6010, device='cuda:0')
frobenius_norm tensor(137.9481, device='cuda:0')
spectral_norm tensor(7.5009, device='cuda:0')
alpha value of layer 18 ---372.74267578125 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(135.1317, device='cuda:0')
spectral_norm tensor(12.0810, device='cuda:0')
frobenius_norm tensor(140.5321, device='cuda:0')
spectral_norm tensor(5.5793, device='cuda:0')
frobenius_norm tensor(137.1833, device='cuda:0')
spectral_norm tensor(6.9554, device='cuda:0')
alpha value of layer 19 ---382.8515625 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(134.6000, device='cuda:0')
spectral_norm tensor(11.1297, device='cuda:0')
frobenius_norm tensor(141.2537, device='cuda:0')
spectral_norm tensor(5.9169, device='cuda:0')
frobenius_norm tensor(138.0343, device='cuda:0')
spectral_norm tensor(6.5506, device='cuda:0')
alpha value of layer 20 ---386.7352294921875 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(136.7462, device='cuda:0')
spectral_norm tensor(11.6961, device='cuda:0')
frobenius_norm tensor(141.2342, device='cuda:0')
spectral_norm tensor(5.6582, device='cuda:0')
frobenius_norm tensor(137.9897, device='cuda:0')
spectral_norm tensor(5.3100, device='cuda:0')
alpha value of layer 21 ---478.354248046875 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(136.9238, device='cuda:0')
spectral_norm tensor(12.4543, device='cuda:0')
frobenius_norm tensor(141.9774, device='cuda:0')
spectral_norm tensor(6.5433, device='cuda:0')
frobenius_norm tensor(139.0448, device='cuda:0')
spectral_norm tensor(5.1260, device='cuda:0')
alpha value of layer 22 ---442.48614501953125 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(138.1573, device='cuda:0')
spectral_norm tensor(14.3250, device='cuda:0')
frobenius_norm tensor(141.6219, device='cuda:0')
spectral_norm tensor(6.6344, device='cuda:0')
frobenius_norm tensor(138.9087, device='cuda:0')
spectral_norm tensor(5.2948, device='cuda:0')
alpha value of layer 23 ---412.3252868652344 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(135.7100, device='cuda:0')
spectral_norm tensor(12.7437, device='cuda:0')
frobenius_norm tensor(143.0019, device='cuda:0')
spectral_norm tensor(6.6948, device='cuda:0')
frobenius_norm tensor(141.1184, device='cuda:0')
spectral_norm tensor(5.4309, device='cuda:0')
alpha value of layer 24 ---414.9455261230469 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(134.2979, device='cuda:0')
spectral_norm tensor(12.3842, device='cuda:0')
frobenius_norm tensor(144.5099, device='cuda:0')
spectral_norm tensor(7.7998, device='cuda:0')
frobenius_norm tensor(143.8913, device='cuda:0')
spectral_norm tensor(6.7086, device='cuda:0')
alpha value of layer 25 ---306.970947265625 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(134.3241, device='cuda:0')
spectral_norm tensor(10.3940, device='cuda:0')
frobenius_norm tensor(145.9831, device='cuda:0')
spectral_norm tensor(10.3400, device='cuda:0')
frobenius_norm tensor(143.8145, device='cuda:0')
spectral_norm tensor(5.9343, device='cuda:0')
alpha value of layer 26 ---317.8813781738281 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
frobenius_norm tensor(139.7623, device='cuda:0')
spectral_norm tensor(14.5234, device='cuda:0')
frobenius_norm tensor(145.0968, device='cuda:0')
spectral_norm tensor(16.8470, device='cuda:0')
frobenius_norm tensor(133.4643, device='cuda:0')
spectral_norm tensor(7.9846, device='cuda:0')
alpha value of layer 27 ---148.7277069091797 
metric_name stable_rank: [21, 6, 22, 24, 23, 8, 20, 19, 18, 17, 7, 15, 14, 16, 10, 26, 12, 11, 13, 25, 9, 4, 5, 2, 0, 27, 3, 1]
Begin main_assign: Qwen2.5-7B mlp  effective_rank

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.01it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.03it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.02it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.09it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.06it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a queen who wanted to build a castle. She had a team of builders who would work day and night to complete the castle. She wanted the castle to be the most magnificent one in the kingdom. The queen would often visit the builders to see the progress of the castle. She would give them advice on how to make it even better. The builders worked hard and the castle was built in a short time. The queen was very happy with the castle and she made it the official residence
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 0 ---2950.251953125 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 1 ---3178.52880859375 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 2 ---3286.484375 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 3 ---3382.06787109375 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 4 ---3406.15234375 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 5 ---3428.05908203125 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 6 ---3425.3720703125 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 7 ---3438.742919921875 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 8 ---3428.871826171875 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 9 ---3411.824951171875 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 10 ---3431.89013671875 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 11 ---3419.459716796875 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 12 ---3425.357177734375 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 13 ---3405.046875 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 14 ---3417.287841796875 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 15 ---3418.02490234375 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 16 ---3407.5625 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 17 ---3408.4970703125 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 18 ---3426.13232421875 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 19 ---3422.40576171875 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 20 ---3435.60009765625 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 21 ---3436.99267578125 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 22 ---3444.177734375 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 23 ---3438.670654296875 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 24 ---3432.22265625 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 25 ---3429.8212890625 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 26 ---3432.60546875 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 27 ---3447.41943359375 
metric_name effective_rank: [27, 22, 7, 23, 21, 20, 26, 24, 10, 25, 8, 5, 18, 6, 12, 19, 11, 15, 14, 9, 17, 16, 4, 13, 3, 2, 1, 0]
Begin main_assign: Qwen2.5-7B mlp  ZD

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:00<00:02,  1.29it/s]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.33it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.31it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.41it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:02<00:00,  1.37it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time there lived a rich man. He had a servantοΌˆδ»†δΊΊοΌ‰. He and the servant loved wine and good food very much. Each time the rich man left his home, the servant would drink the wine and eat up all the nice food in the house. The rich man knew what his servant did, but he had never caught his servant doing that. One morning, when he left home, he said to the servant, β€œHere are two bottles of poisonοΌˆζ―’θ―οΌ‰ and some nice
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 0 ---0.14041712880134583 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 1 ---0.12673243880271912 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 2 ---0.14196857810020447 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 3 ---0.15253740549087524 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 4 ---0.15330302715301514 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 5 ---0.1531524807214737 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 6 ---0.15197408199310303 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 7 ---0.15272140502929688 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 8 ---0.15372541546821594 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 9 ---0.15197794139385223 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 10 ---0.15327925980091095 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 11 ---0.15320764482021332 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 12 ---0.15106868743896484 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 13 ---0.15193961560726166 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 14 ---0.14989005029201508 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 15 ---0.15030330419540405 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 16 ---0.1516457051038742 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 17 ---0.15101006627082825 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 18 ---0.14948342740535736 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 19 ---0.15111291408538818 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 20 ---0.15065661072731018 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 21 ---0.15124627947807312 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 22 ---0.1522490233182907 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 23 ---0.15400244295597076 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 24 ---0.15468579530715942 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 25 ---0.15433579683303833 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 26 ---0.1542406529188156 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 27 ---0.1527990698814392 
metric_name ZD: [24, 25, 26, 23, 8, 4, 10, 11, 5, 27, 7, 3, 22, 9, 6, 13, 16, 21, 19, 12, 17, 20, 15, 14, 18, 2, 0, 1]
Begin main_assign: Qwen2.5-7B mlp  head_diversity

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:01<00:04,  1.43s/it]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:02<00:02,  1.24s/it]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:03<00:01,  1.28s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:04<00:00,  1.19s/it]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:04<00:00,  1.23s/it]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, there was a little boy named Timmy. Timmy loved to play outside and explore the world around him. One day, while playing in the park, he met a talking tree named Oakley.
Oakley told Timmy that there was a magical forest nearby that only appeared once every hundred years. The forest was filled with talking animals and magical creatures that could grant wishes. Timmy was excited to hear this news and begged Oakley to take him there.
Oakley agreed and led Timmy
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
Traceback (most recent call last):
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/main_assign.py", line 58, in <module>
    all_layer_alpha = calculate_expert(model, metric=metric_name, keyword=keyword)
  File "/mnt/bn/life-mllm/users/cxr/quantization/quantization_metric/alphalora/expert_number.py", line 354, in calculate_expert
    all_layer_alpha.append(torch.stack(layer_final_alpha).mean().item())
RuntimeError: stack expects a non-empty TensorList
Begin main_assign: Qwen2.5-7B mlp  coherence

Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]
Loading checkpoint shards:  25%|β–ˆβ–ˆβ–Œ       | 1/4 [00:01<00:03,  1.01s/it]
Loading checkpoint shards:  50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 2/4 [00:01<00:01,  1.12it/s]
Loading checkpoint shards:  75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 3/4 [00:02<00:00,  1.15it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.23it/s]
Loading checkpoint shards: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 4/4 [00:03<00:00,  1.18it/s]
Setting `pad_token_id` to `eos_token_id`:151643 for open-end generation.
Once upon a time, the land of Greece was ruled by three powerful and evil sorceresses: Echidna, the mother of the monsters; her daughter, the monster Medusa; and the sea-goddess Gorgon. Their leader was the most evil of the three, the monster Medusa. When the gods tried to stop her, she became so angry that she attacked them and killed them all. She then took their weapons, which she used to attack the world. She even attacked the other
Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(152064, 3584)
    (layers): ModuleList(
      (0-27): 28 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=3584, out_features=3584, bias=True)
          (k_proj): Linear(in_features=3584, out_features=512, bias=True)
          (v_proj): Linear(in_features=3584, out_features=512, bias=True)
          (o_proj): Linear(in_features=3584, out_features=3584, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (up_proj): Linear(in_features=3584, out_features=18944, bias=False)
          (down_proj): Linear(in_features=18944, out_features=3584, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((3584,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((3584,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=3584, out_features=152064, bias=False)
)
config: 
 Qwen2Config {
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 3584,
  "initializer_range": 0.02,
  "intermediate_size": 18944,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 28,
  "num_hidden_layers": 28,
  "num_key_value_heads": 4,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 152064
}

Processing layer 0--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 0 ---0.030741512775421143 
Processing layer 1--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 1 ---0.0886889323592186 
Processing layer 2--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 2 ---0.038115616887807846 
Processing layer 3--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 3 ---0.01555887795984745 
Processing layer 4--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 4 ---0.015330223366618156 
Processing layer 5--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 5 ---0.014795559458434582 
Processing layer 6--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 6 ---0.013012934476137161 
Processing layer 7--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 7 ---0.012255651876330376 
Processing layer 8--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 8 ---0.012662074528634548 
Processing layer 9--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 9 ---0.017650291323661804 
Processing layer 10--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 10 ---0.012567928992211819 
Processing layer 11--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 11 ---0.012772100046277046 
Processing layer 12--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 12 ---0.012693522498011589 
Processing layer 13--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 13 ---0.012766292318701744 
Processing layer 14--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 14 ---0.01258667092770338 
Processing layer 15--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 15 ---0.012480087578296661 
Processing layer 16--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 16 ---0.012708479538559914 
Processing layer 17--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 17 ---0.01283347513526678 
Processing layer 18--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 18 ---0.01226731389760971 
Processing layer 19--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 19 ---0.012299998663365841 
Processing layer 20--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 20 ---0.01201008539646864 
Processing layer 21--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 21 ---0.011824443936347961 
Processing layer 22--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 22 ---0.011804303154349327 
Processing layer 23--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 23 ---0.012257957831025124 
Processing layer 24--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 24 ---0.012149857357144356 
Processing layer 25--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 25 ---0.012290380895137787 
Processing layer 26--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 26 ---0.012179265730082989 
Processing layer 27--subset--{'mlp.gate_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.up_proj': Linear(in_features=3584, out_features=18944, bias=False), 'mlp.down_proj': Linear(in_features=18944, out_features=3584, bias=False)}
alpha value of layer 27 ---0.01317012868821621 
metric_name coherence: [1, 2, 0, 9, 3, 4, 5, 27, 6, 17, 11, 13, 16, 12, 8, 14, 10, 15, 19, 25, 18, 23, 7, 26, 24, 20, 21, 22]