mt5-small-german-query-generation
Model description:
This model was created with the purpose to generate possible queries for a german input article.
For this model, we finetuned a multilingual T5 model mt5-small on the MMARCO dataset the machine translated version of the MS MARCO dataset.
The model was trained for 1 epoch, on 200,000 unique queries of the dataset. We trained the model on one K80 GPU for 25,000 iterations with following parameters:
- learning rate: 1e-3
- train batch size: 8
- max input sequence length: 512
- max target sequence length: 64
Model Performance:
Model evaluation was done on 2000 evaluation paragraphs of the dataset. Mean f1 ROUGE scores were calculated for the model.
| Rouge-1 | Rouge-2 | Rouge-L |
|---|---|---|
| 0.162 | 0.052 | 0.161 |
- Downloads last month
- 85
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.