|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- conll2003 |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: distilbert-base-cased-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: 0.9306692773228907 |
|
- name: Recall |
|
type: recall |
|
value: 0.9381841019199713 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9344115807345187 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9832666156472597 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distilbert-base-cased-ner |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the conll2003 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1183 |
|
- Precision: 0.9307 |
|
- Recall: 0.9382 |
|
- F1: 0.9344 |
|
- Accuracy: 0.9833 |
|
|
|
## 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: 2147483647 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1081 | 1.0 | 1756 | 0.0963 | 0.8947 | 0.8982 | 0.8964 | 0.9742 | |
|
| 0.0518 | 2.0 | 3512 | 0.0780 | 0.9219 | 0.9182 | 0.9200 | 0.9803 | |
|
| 0.0348 | 3.0 | 5268 | 0.0833 | 0.9258 | 0.9271 | 0.9264 | 0.9819 | |
|
| 0.0268 | 4.0 | 7024 | 0.0900 | 0.9152 | 0.9241 | 0.9196 | 0.9805 | |
|
| 0.0167 | 5.0 | 8780 | 0.0929 | 0.9225 | 0.9320 | 0.9272 | 0.9822 | |
|
| 0.0071 | 6.0 | 10536 | 0.1119 | 0.9229 | 0.9270 | 0.9249 | 0.9816 | |
|
| 0.0056 | 7.0 | 12292 | 0.1073 | 0.9286 | 0.9366 | 0.9326 | 0.9832 | |
|
| 0.0021 | 8.0 | 14048 | 0.1194 | 0.9285 | 0.9350 | 0.9318 | 0.9829 | |
|
| 0.0019 | 9.0 | 15804 | 0.1156 | 0.9318 | 0.9376 | 0.9347 | 0.9833 | |
|
| 0.0011 | 10.0 | 17560 | 0.1183 | 0.9307 | 0.9382 | 0.9344 | 0.9833 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
