Weight initialization Error on using pretrained model in pytorch

[adiv5]

I am getting this error

Weights of BertForMultiLable not initialized from pretrained model: ['classifier.weight', 'classifier.bias']
Weights from pretrained model not used in BertForMultiLable: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias']

while using the provided pretrained biobert from here in this repo. here is the issue for reference.

Is there some issue in the model?

[EmilyAlsentzer]

Hi Aditya,

Can you clarify what you are doing that gets this error? Are you trying to use clinical BERT model in the instructions provided by the Bert-Multi-Label-Text-Classification repo? Is the issue that it works when you use BERT but not clinical BERT or do you get the same error regardless of which BERT model you use?

[EmilyAlsentzer]

Closing this issue due to lack of activity. Feel free to reopen and provide more details.