CoolFace
Modelpublic

neurae/distilbert-dnd-intents

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes29downloads
Model Card

This is distilbert base tuned with optimal lr, lr scheduler and weight decay on dnd-style-intents dataset.

parametrsvalue
learning rate1.8e-4
lr schedulerlinear
weight decay0

Model has next metrics on test data from dataset

metricvalue
accuracy0.985
Macro F10.984
Micro F10.985