Do you have the command "radius-server deadtime" configured on the AP? What value?
Not sure if this is the issue since I don't know the config. If you have it configured and only have one radius server you will see these as informational messages mainly.
When you enable this setting (Dead RADIUS Server List) it causes the Cisco IOS software to
mark as "dead" any RADIUS servers that fail to respond to authentication requests,
avoiding the wait for the request to time out before trying the next configured server. A
RADIUS server marked as dead is skipped by additional requests for the duration of minutes
unless all servers are marked dead.
I would remove the command if it is configured.
If this is not the problem I would also recommend upgrading to at least 12.3(7)JA.