ESIM issues

Results 3 ESIM issues

Sort by recently updated

Validation loss lower than training loss?

Throughout my first 7 epochs, loss is always lower on validation set rather than training set. Did anything go wrong or the validation set is just too easy? `* Training...

Lyn-bia

adding output attention feature for better interpretation

Similar to the SOTA models eg. standard transformer models where the attention is returned for using it for further interpretation. Some libraries support graphic visualization for the attention involved which...

ghadiaravi13