Skip to content

Parameter name inconsistency: masked_lm_labels vs labels in forward method #26

@sw1125598670

Description

@sw1125598670

Hello! I encountered an issue during pretraining where the forward method doesn't recognize the masked_lm_labels parameter.

"/home/mickey/Tools/miniconda3/envs/methylbert/lib/python3.11/site-packages/methylbert/trainer.py", line 287
mask_lm_output = self.model.forward(input_ids = data["input"],
masked_lm_labels = data["label"])
Questions:
Should the parameter name be labels instead of masked_lm_labels?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions