benleetownsend comments

Results 7 comments of


                                            benleetownsend

[Need help] How can I load a created base model

Thanks for your interest in finetune. The api for loading base model files saved in this way is. ``` new_model = Classifier(base_model=, base_model_path=) ``` where the base model object is...

[Need help] How can I load a created base model

If you wanted to use this new model frequently and wanted a cleaner api you could also do: ``` class NewBaseModel(RoBERTa): # replace RoBERTa with whatever model this is based...

AssertionError: Bad argument number for Name: 3, expecting 4

Are you trying to run finetune on tensorflow 2.0 by any chance?

AssertionError: Bad argument number for Name: 3, expecting 4

Thanks for the bug report, I can reproduce the second issue. For now you can set the kwarg chunk_long_sequences=False and this should reinstate the previous behaviour.

AssertionError: Bad argument number for Name: 3, expecting 4

Can you provide a minimum reproducible example for the first issue?

AssertionError: Bad argument number for Name: 3, expecting 4

Can you run `pip freeze | grep "tensorflow\|finetune"` and send me the output

Add a tensorboard log for final training loss value.

So, we explicitly run validation on the final model no matter the val interval. This is for the purpose of keep_best_model, otherwise we can accidentally waste the final set of...