metadata
license: cc-by-sa-4.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.8597087378640776
- name: Recall
type: recall
value: 0.8941433860652979
- name: F1
type: f1
value: 0.8765880217785844
- name: Accuracy
type: accuracy
value: 0.9760991339759331
bert-finetuned-ner
This model is a fine-tuned version of klue/bert-base on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0943
- Precision: 0.8597
- Recall: 0.8941
- F1: 0.8766
- Accuracy: 0.9761
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1321 | 1.0 | 1756 | 0.1003 | 0.8010 | 0.8514 | 0.8254 | 0.9687 |
| 0.0654 | 2.0 | 3512 | 0.0927 | 0.8331 | 0.8862 | 0.8588 | 0.9739 |
| 0.0382 | 3.0 | 5268 | 0.0943 | 0.8597 | 0.8941 | 0.8766 | 0.9761 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2