I am using R here.

I am trying to predict the MRR (Material removal rate) with RF. I have 5 input parameters.

The RF model I am building in R is having a very poor accuracy. The current data has 25 points which I have divided into 18-7 for training and testing. I know the size is small so there might be the problem of over-fitting but even when I am trying it with a larger dataset (100 training, 25 testing) I am having a poor accuracy. Even linear regression is giving a better accuracy than this.

Where I am going wrong? I am attaching my R Code and the sample data below for your kind perusal. Any help would mean a lot.