metadata

license: mit
base_model: deepset/gbert-large
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: FragZONFactMetaRecommendation
    results: []
widget:
  - text: Wer arbeitet im Ressort PWG von ZEIT ONLINE?
    example_title: Meta
  - text: Wann ist Helmut Schmidt gestorben?
    example_title: Fakt
  - text: Was kann die ZEIT-KI?
    example_title: Meta
  - text: Wer hat 2021/22 die Meisterschaft der Fussballbundesliga gewonnen?
    example_title: Fakt
  - text: Wen soll ich bei der nächsten Bundestagswahl wählen?
    example_title: Empfehlung

FragZONFactMetaRecommendation

This model is a fine-tuned version of deepset/gbert-large on the beta dataset. It achieves the following results on the evaluation set:

Loss: 0.4128
Accuracy: 0.9205

Model description

Fine-tuned gbert on queries

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.171	1.0	76	0.4003	0.9139
0.1154	2.0	152	0.4128	0.9205

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1