roberta-base-dapt - ECB hawkish/dovish/neutral classifier

Fine-tuned from LorenzoAleCon29/roberta-base-ECB-dapt on annotated ECB communication (press conference statements, speeches and monetary-policy statements). Labels: dovish, neutral, hawkish.

Test-set performance

loss accuracy f1 macro f1 weighted
1.9001 0.6496 0.6504 0.6545

Usage

from transformers import pipeline
clf = pipeline("text-classification", model="LorenzoAleCon29/roberta-base-dapt-ecb-hawkish-dovish")
clf("Inflationary pressures warrant a tightening of the policy stance.")

Training curves, trainer states and full reports: https://github.com/LorenzoAlessandro/BdF-Project

Downloads last month
5
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for LorenzoAleCon29/roberta-base-dapt-ecb-hawkish-dovish

Finetuned
(1)
this model