Downloads · 30 days
5
18% of all-time downloads
DagoBERT
jpostma/DagoBERT
DagoBERT is a fill-mask model from jpostma. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
28
Public
Repo size
935 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin467 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- roberta
- Access
- Public
- Created
- Sep 3, 2023
- Updated
- Sep 3, 2023
- SHA
- 334660f7
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
DagoBERT
This model is a domain-adapted version of pdelobelle/robbert-v2-dutch-base to Dutch annual reports. It achieves the following results on the evaluation set:
- Loss:
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:
- train_batch_size:
- eval_batch_size:
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs:
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 2 | 9.5998 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- mit
- Languages
- nl
- Created
- Sep 3, 2023
- Updated
- Sep 3, 2023