|
--- |
|
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: 0.9267369114257491 |
|
- name: Recall |
|
type: recall |
|
value: 0.9473241332884551 |
|
- name: F1 |
|
type: f1 |
|
value: 0.9369174434087884 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9852239948195679 |
|
--- |
|
|
|
<!-- 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: 0.1060 |
|
- Precision: 0.9267 |
|
- Recall: 0.9473 |
|
- F1: 0.9369 |
|
- Accuracy: 0.9852 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1012 | 1.0 | 1756 | 0.0895 | 0.8924 | 0.9194 | 0.9057 | 0.9767 | |
|
| 0.0491 | 2.0 | 3512 | 0.0818 | 0.9070 | 0.9260 | 0.9164 | 0.9801 | |
|
| 0.0334 | 3.0 | 5268 | 0.0818 | 0.9170 | 0.9315 | 0.9242 | 0.9821 | |
|
| 0.0235 | 4.0 | 7024 | 0.0893 | 0.9074 | 0.9364 | 0.9216 | 0.9815 | |
|
| 0.0167 | 5.0 | 8780 | 0.0879 | 0.9106 | 0.9414 | 0.9258 | 0.9828 | |
|
| 0.0071 | 6.0 | 10536 | 0.0955 | 0.9172 | 0.9435 | 0.9301 | 0.9836 | |
|
| 0.0039 | 7.0 | 12292 | 0.1016 | 0.9209 | 0.9423 | 0.9315 | 0.9835 | |
|
| 0.0021 | 8.0 | 14048 | 0.1043 | 0.9294 | 0.9463 | 0.9378 | 0.9847 | |
|
| 0.0014 | 9.0 | 15804 | 0.1064 | 0.9271 | 0.9475 | 0.9372 | 0.9853 | |
|
| 0.0005 | 10.0 | 17560 | 0.1060 | 0.9267 | 0.9473 | 0.9369 | 0.9852 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
