metadata
base_model: PleIAs/Monad
pipeline_tag: text-classification
datasets:
- breadlicker45/gender-classification-v4.5
this is a bad model and is overfitted: DO NOT USE
settings I trained with:
- max length: 512
- batch size: 64 on one mi300x
- how much of the dataset did it train on: about 12% of the dataset.