EmbExtractor type error
Dear team,
thank you for the great tool. I have been trying to implement the perturbation workflow on my dataset and I face the following error when I extract the embeddings with get_state_embs() function
RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got torch.cuda.FloatTensor instead (while checking arguments for embedding)
I have only 2 states, start and goal.
I do not get the error with the example dataset.
Thank you for the question - could you please send the full error trace for context?
Dear,
Thank you for the quick response. Please find the attached screenshot for the complete traceback
Thank you for including the full error trace! We would suggest checking your tokenized dataset to ensure that each label is of the same type within that label and that your input_ids are all integer token IDs as expected.