|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conll2003 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-cased-finetuned-conll2003 |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: conll2003 |
|
type: conll2003 |
|
args: conll2003 |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.9409771754636234 |
|
- name: Recall |
|
type: recall |
|
value: 0.946886775524852 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9439227260531259 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9859745687878966 |
|
--- |
|
|
|
<!-- 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-base-cased-finetuned-conll2003 |
|
|
|
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: 0.0643 |
|
- Precision: 0.9410 |
|
- Recall: 0.9469 |
|
- F1: 0.9439 |
|
- Accuracy: 0.9860 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2349 | 0.57 | 500 | 0.0885 | 0.8957 | 0.8980 | 0.8968 | 0.9747 | |
|
| 0.0822 | 1.14 | 1000 | 0.0774 | 0.9184 | 0.9219 | 0.9202 | 0.9802 | |
|
| 0.0476 | 1.71 | 1500 | 0.0683 | 0.9345 | 0.9325 | 0.9335 | 0.9833 | |
|
| 0.0368 | 2.28 | 2000 | 0.0653 | 0.9333 | 0.9430 | 0.9381 | 0.9847 | |
|
| 0.028 | 2.85 | 2500 | 0.0670 | 0.9279 | 0.9342 | 0.9311 | 0.9835 | |
|
| 0.0171 | 3.42 | 3000 | 0.0643 | 0.9410 | 0.9469 | 0.9439 | 0.9860 | |
|
| 0.0149 | 3.99 | 3500 | 0.0667 | 0.9369 | 0.9477 | 0.9422 | 0.9856 | |
|
| 0.0088 | 4.56 | 4000 | 0.0698 | 0.9360 | 0.9473 | 0.9416 | 0.9855 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
