Multi-label topics not captured

I am working on a task to classify a sentence into multiple topics (Multi-label classification).
Initially, I trained the entire 1.5M unlabeled data on bert base model using domain adaptation.
Then I manually annotated the labels with atleast 10 examples each and fine-tuned it.
The test accuracy what I received was 35% for 1 epoch and 46% for 7 epochs.
I see that the model is capturing negations too but it is not capturing multi-labels.
I know that there is no way to measure accuracy for train/test dataset after every epoch to get to know if it is overfitting or underfitting.
Can you suggest some some good range of epochs for this multi label classification or changes in hyper-parameter opt. settings? Or may be i should increase the quality of the labeled sentences? Suggestions please.

The issue names no files, tests, or entry points. Start by reviewing the BERT domain-adaptation and fine-tuning setup for the 1.5M unlabeled examples and manually labeled sentences, then examine how multi-label results are evaluated across epochs. Done requires a reproducible diagnosis of whether training settings or label quality explain the missing multi-label predictions.

Written by the indexing model from the issue text.