|
--- |
|
language: |
|
- da |
|
- no |
|
- nb |
|
- nn |
|
- sv |
|
- fo |
|
- is |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- dane |
|
- norne |
|
- wikiann |
|
- suc3.0 |
|
model-index: |
|
- name: nbailab-base-ner-scandi |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
widget: |
|
- "Hans er en professor på IT Universitetet i København, og han er en rigtig københavner. Hans kat, altså Hans' kat, Lisa, er supersød. Han fik købt en Mona Lisa på tilbud i Netto og gav den til hans kat, og nu er Mona Lisa Lisa's kæreste eje. Hans er med hans bror Peter, og de besluttede, at Peterskirken skulle have fint besøg af Peter og hans ven Hans." |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# nbailab-base-ner-scandi-unbalanced |
|
|
|
This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on the concatenation of DaNE, NorNE, SUC 3.0 and the Icelandic and Faroese parts of the WikiAnn dataset. |
|
It achieves the following results on DaNE: |
|
- Loss: 0.0666 |
|
- Micro F1: 0.8693 |
|
- Micro F1 No Misc: 0.8925 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 90135.90000000001 |
|
- num_epochs: 1000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Micro F1 | Micro F1 No Misc | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:----------------:| |
|
| 0.6682 | 1.0 | 2816 | 0.0872 | 0.6916 | 0.7306 | |
|
| 0.0684 | 2.0 | 5632 | 0.0464 | 0.8167 | 0.8538 | |
|
| 0.0444 | 3.0 | 8448 | 0.0367 | 0.8485 | 0.8783 | |
|
| 0.0349 | 4.0 | 11264 | 0.0316 | 0.8684 | 0.8920 | |
|
| 0.0282 | 5.0 | 14080 | 0.0290 | 0.8820 | 0.9033 | |
|
| 0.0231 | 6.0 | 16896 | 0.0283 | 0.8854 | 0.9060 | |
|
| 0.0189 | 7.0 | 19712 | 0.0253 | 0.8964 | 0.9156 | |
|
| 0.0155 | 8.0 | 22528 | 0.0260 | 0.9016 | 0.9201 | |
|
| 0.0123 | 9.0 | 25344 | 0.0266 | 0.9059 | 0.9233 | |
|
| 0.0098 | 10.0 | 28160 | 0.0280 | 0.9091 | 0.9279 | |
|
| 0.008 | 11.0 | 30976 | 0.0309 | 0.9093 | 0.9287 | |
|
| 0.0065 | 12.0 | 33792 | 0.0313 | 0.9103 | 0.9284 | |
|
| 0.0053 | 13.0 | 36608 | 0.0322 | 0.9078 | 0.9257 | |
|
| 0.0046 | 14.0 | 39424 | 0.0343 | 0.9075 | 0.9256 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.10.3 |
|
- Pytorch 1.9.0+cu102 |
|
- Datasets 1.12.1 |
|
- Tokenizers 0.10.3 |
|
|
