Max Children Issue and SA timeouts

[Jason Burzenski]

>Bayes scores was bad but the training is quick and I think long learning
periods are a little overrated so you don't risk >that much. But it's your
call of course.

Do you have any idea how long it would take to retrain a system that
currently sees ~50K msgs per day?  I'm thinking maybe kill the db on a
Friday and hope it rebuilds by Monday.  I never timed my initial bayes
training.

-------------------------- MailScanner list ----------------------
To leave, send    leave mailscanner    to jiscmail at jiscmail.ac.uk
For further info about MailScanner, please see the Most Asked
Questions at    http://www.mailscanner.biz/maq/     and the archives
at    http://www.jiscmail.ac.uk/lists/mailscanner.html
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.mailscanner.info/pipermail/mailscanner/attachments/20040423/b09cde53/attachment.html