|
--- |
|
license: apache-2.0 |
|
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: 0.93732429303787 |
|
- name: Recall |
|
type: recall |
|
value: 0.9538875799394143 |
|
- name: F1 |
|
type: f1 |
|
value: 0.94553340562182 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9866809913463237 |
|
--- |
|
|
|
<!-- 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-finetuned-ner |
|
|
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0998 |
|
- Precision: 0.9373 |
|
- Recall: 0.9539 |
|
- F1: 0.9455 |
|
- Accuracy: 0.9867 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0878 | 1.0 | 1756 | 0.0694 | 0.9166 | 0.9288 | 0.9227 | 0.9819 | |
|
| 0.0366 | 2.0 | 3512 | 0.0718 | 0.9247 | 0.9467 | 0.9356 | 0.9850 | |
|
| 0.0247 | 3.0 | 5268 | 0.0727 | 0.9220 | 0.9435 | 0.9326 | 0.9844 | |
|
| 0.0153 | 4.0 | 7024 | 0.0746 | 0.9384 | 0.9532 | 0.9457 | 0.9860 | |
|
| 0.0107 | 5.0 | 8780 | 0.0874 | 0.9260 | 0.9475 | 0.9366 | 0.9847 | |
|
| 0.0043 | 6.0 | 10536 | 0.0898 | 0.9373 | 0.9517 | 0.9445 | 0.9863 | |
|
| 0.0041 | 7.0 | 12292 | 0.0984 | 0.9371 | 0.9507 | 0.9439 | 0.9858 | |
|
| 0.0031 | 8.0 | 14048 | 0.0982 | 0.9327 | 0.9515 | 0.9420 | 0.9856 | |
|
| 0.0014 | 9.0 | 15804 | 0.0987 | 0.9361 | 0.9544 | 0.9452 | 0.9860 | |
|
| 0.0006 | 10.0 | 17560 | 0.0998 | 0.9373 | 0.9539 | 0.9455 | 0.9867 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.13.2 |
|
|
