Hello, Kjartan. You wrote in <mid:[EMAIL PROTECTED]>
K�> I did build a new regard file with ~200 spam mails and ~200 non spam K�> mails. The new regard.rdb file is around 100KB in size. I see the file you sent me. It is actually what I think about: Actually I need only first 8 bytes to say what is wrong. My file contains 19269 tokens. Your said that it contains... 4294954311 tokens! This is equal to -12983 and means that this is very bug in learning machine which I mentioned before (and already corrected). Of course I must check the end of file when I actually test the base. And I'll do it in near future (remember that this is only testing version). As you ask, I've deleted your file. -- Sincerely, Alexey. Using TB 1.63b7 on WinXP SP1 Corp + MUI RU, spelling by ORFO2002 mailto:[EMAIL PROTECTED] ________________________________________________ Current version is 1.62 | "Using TBDEV" information: http://www.silverstones.com/thebat/TBUDLInfo.html
