I am a bit new to ML, below are the results after I fine tuned distilRoBERTa. I cant tell if my model is over-fitting, under-fitting or ok? I ran 7 epochs.
I think its overfitting as validation loss is lowest at epoch 3 and goes up again after epoch 3, so 3 epochs might be optimal for fine-tuning this dataset and model? A second opinion would be appreciated.
I have a multi class classification problem with 11 classes and my dataset is imbalanced, though representative of real world data. I had 40k training samples and 5.3k validation set.