|
--- |
|
tags: |
|
- generated_from_trainer |
|
language: |
|
- sv |
|
datasets: |
|
- wikiann |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: BERT_swedish-ner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: wikiann |
|
type: wikiann |
|
config: sv |
|
split: train |
|
args: sv |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9340386115444618 |
|
- name: Recall |
|
type: recall |
|
value: 0.9418907624993855 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9379482534942355 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.979997105690534 |
|
widget: |
|
- "Jag heter Peter Petersson och jag jobbar på Skatteverket. Jag bor i Uppsala." |
|
inference: |
|
parameters: |
|
aggregation_strategy: "first" |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# BERT_swedish-ner |
|
|
|
This model is a fine-tuned version of [KB/bert-base-swedish-cased](https://huggingface.co/KB/bert-base-swedish-cased) on the wikiann dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1316 |
|
- Precision: 0.9340 |
|
- Recall: 0.9419 |
|
- F1: 0.9379 |
|
- Accuracy: 0.9800 |
|
|
|
## Model description |
|
|
|
Finetuned the model from [KB/bert-base-swedish-cased](https://huggingface.co/KB/bert-base-swedish-cased) for Swedish NER task. The model can classify three categories: |
|
- PER (person names) |
|
- LOC (Location) |
|
- ORG (Organization) |
|
|
|
## Intended uses & limitations |
|
|
|
NER, token classification |
|
|
|
## Training and evaluation data |
|
|
|
wikiann-SV dataset |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 12 |
|
- eval_batch_size: 12 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.22.1 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
