bachfischer / comp90042-rumour-detection-on-twitter Goto Github PK

Hi,
I am running 01_rumour_detection_bertweet.ipynb but in the data folder, there is no train.data.jsonl file. How can I access this file? Thanks

Hi,

I am really a new learner of torch. Currently, I have a project which I hope to use BERTweet to fine tune and train a binary classifier. I found your project is relevant and I tried your code on my own dataset, and it has good performance. My question is that how to reload the model that I trained before. For example, in your shared code, torch.save(model.cpu().roberta.state_dict(),"./bertweet/bertweet_v22") can save the model to my local machine.

But, today, I tried to reload the trained model to do some prediction tasks, using the following code: model.load_state_dict(torch.load("./bertweet/bertweet_v22"))
model.eval()

It just report some error as follows,
Error(s) in loading state_dict for RobertaForSequenceClassification:
Missing key(s) in state_dict: "roberta.embeddings.position_ids", "roberta.embeddings.word_embeddings.weight", "roberta.embeddings.position_embeddings.weight", "roberta.embeddings.token_type_embeddings.weight", "roberta.embeddings.LayerNorm.weight", "roberta.embeddings.LayerNorm.bias", "roberta.encoder.layer.0.attention.self.query.weight", "roberta.encoder.layer.0.attention.self.query.bias", "roberta.encoder.layer.0.attention.self.key.weight", "roberta.encoder.layer.0.attention.self.key.bias", "roberta.encoder.layer.0.attention.self.value.weight", "roberta.encoder.layer.0.attention.self.value.bias", "roberta.encoder.layer.0.attention.output.dense.weight", "roberta.encoder.layer.0.attention.output.dense.bias", "roberta.encoder.layer.0.attention.output.LayerNorm.weight", "roberta.encoder.layer.0.attention.output.LayerNorm.bias", "roberta.encoder.layer.0.intermediate.dense.weight", "roberta.encoder.layer.0.intermediate.dense.bias", "roberta.encoder.layer.0.output.dense.weight", "roberta.encoder.layer.0.output.dense.bias", "roberta.encoder.layer.0.output.LayerNorm.weight", "roberta.encoder.layer.0.output.LayerNorm.bias", "roberta.encoder.layer...