metadata
license: apache-2.0
datasets:
- google-research-datasets/go_emotions
language:
- de
metrics:
- accuracy value: 0.27
- f1 value: 0.382
- roc_auc value: 0.658
pipeline_tag: text-classification
tags:
- medical
This is basically the German translation of arpanghoshal/EmoRoBERTa. We used the go_emotions dataset, translated it into German and fine-tuned the intfloat/multilingual-e5-large model.
Hyperparameters
- Epochs: 10
- learning_rate: 1e-5
- weight_decay: 0.01
Model Performance
- accuracy: 0.27
- f1: 0.382
- roc_auc: 0.658