|
--- |
|
license: cc-by-nc-4.0 |
|
pipeline_tag: fill-mask |
|
tags: |
|
- legal |
|
language: |
|
- da |
|
datasets: |
|
- multi_eurlex |
|
- DDSC/partial-danish-gigaword-no-twitter |
|
model-index: |
|
- name: coastalcph/danish-legal-bert-base |
|
results: [] |
|
--- |
|
|
|
# Danish LegalBERT (derivative of Maltehb/danish-bert-botxo) |
|
|
|
This model is a derivative of [Maltehb/danish-bert-botxo](https://huggingface.co/Maltehb/danish-bert-botxo) adapted to legal text. It has been pre-trained on a combination of the Danish part of the MultiEURLEX (Chalkidis et al., 2021) dataset comprising EU legislation and two subsets (`retsinformationdk`, `retspraksis`) of the Danish Gigaword Corpus (Derczynski et al., 2021) comprising legal proceedings. |
|
It achieves the following results on the evaluation set: |
|
- Loss: - |
|
|
|
## Model description |
|
|
|
This is a BERT model (Devlin et al., 2018) model pre-trained on Danish legal corpora. It follows a base configuration with 12 Transformer layers, each one with 768 hidden units and 12 attention heads. |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
This model is pre-training on a combination of the Danish part of the MultiEURLEX dataset and two subsets (`retsinformationdk`, `retspraksis`) of the Danish Gigaword Corpus. |
|
|
|
## Training procedure |
|
|
|
The model was initially pre-trained for 500k steps with sequences up to 128 tokens, and then continued pre-training for additional 100k with sequences up to 512 tokens. |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.00001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- distributed_type: tpu |
|
- num_devices: 8 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 256 |
|
- total_eval_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- training_steps: 100000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Length | Step | Validation Loss | |
|
|:-------------:|:------:|:-------:|:---------------:| |
|
| 1.0030 | 128 | 50000 | - | |
|
| 0.9593 | 128 | 100000 | - | |
|
|
