ul2-small-dutch-finetuned-qgsquad-qgen
This model is a fine-tuned version of ul2-small-dutch on the Squad V2 Dutch dataset. It achieves the following results on the evaluation set:
- Loss: 0.49
- Rouge4 Precision: 0.03
- Rouge4 Recall: 0.027
- Rouge4 Fmeasure: 0.027
Model description
More information needed
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: 5
Training results
| Epoch | Training Loss | Validation Loss | Rouge4 Precision | Rouge4 Recall | Rouge4 Fmeasure |
|---|---|---|---|---|---|
| 1 | 0.585900 | 0.512915 | 0.026600 | 0.023800 | 0.024100 |
| 2 | 0.550200 | 0.498777 | 0.030300 | 0.027800 | 0.027900 |
| 3 | 0.534800 | 0.493952 | 0.031700 | 0.028900 | 0.029100 |
- Downloads last month
- 13
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.