This model was created with the purpose to generate possible queries for a german input article.
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 evaluation was done on 2000 evaluation paragraphs of the dataset. Mean f1 ROUGE scores were calculated for the model.
- Downloads last month