How to fine-tune a Embedding retriever on positive and negative feedback

[vibha0411]

I see that
[https://colab.research.google.com/drive/1Tz9GSzre7JfvXDDKe7sCnO0FMuDViMnN?usp=sharing#scrollTo=TD2PZuuNTpQ3]
PseudoLabelGenerator runs basically
Question generation - optional step
Negative mining
Pseudo labeling (margin scoring)
steps.
But in a case where i already have the positive and negative documents for a question, I would not be requiring the negative mining step, however as per my understanding I still require the margin scoring to perform the training.

So how do I go about this scenario?
Kindly help.

[vibha0411]

Basically can I just do margin scoring separately?
My training data consists of both the positive and negative docs.
How should i go about fine-tuning the embedding retriever?

[vibha0411]

@bglearning ,@mkkuemmel , @vblagoje really interested to know your thoughts on this.