forecast (log data to normal)

[realusername]

I am using a forecast() function.
My model is based on the log of my data however I would like to get my forecast with the actual values.
Here's what I have:

training <- log_data
model <- arima(training, order=c(0,1,1), seasonal=list(order=c(0,1,1), period=12))

log_pred <- forecast(model, h=12, level=95)

[realusername]

fc<-forecast(ARIMA,h=12)
fc$mean<-exp(fc$mean)
fc$upper<-exp(fc$upper)
fc$lower<-exp(fc$lower)
fc$x<-exp(fc$x)