mdeberta-v3-base-socialdisner

This model is a finetuned version of mdeberta-v3-base for the socialdisner dataset used in a benchmark in the paper TODO. The model has a F1 of 0.935

Please refer to the original publication for more information TODO LINK

Parameters used

parameter Value
batch size 16
learning rate 1e-05
classifier dropout 0.2
warmup ratio 0
warmup steps 0
weight decay 0
optimizer AdamW
epochs 10
early stopping patience 3

BibTeX entry and citation info

TODO
Downloads last month
108
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Dataset used to train IIC/mdeberta-v3-base-socialdisner

Collection including IIC/mdeberta-v3-base-socialdisner

Evaluation results