|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- bc4chemd_ner |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bc4chemd_ner-Bio_ClinicalBERT-finetuned-ner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: bc4chemd_ner |
|
type: bc4chemd_ner |
|
args: bc4chemd |
|
metrics: |
|
- name: Precision |
|
type: precision |
|
value: 0.8944236722550557 |
|
- name: Recall |
|
type: recall |
|
value: 0.8777321865383098 |
|
- name: F1 |
|
type: f1 |
|
value: 0.8859993229654115 |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9908228496683563 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bc4chemd_ner-Bio_ClinicalBERT-finetuned-ner |
|
|
|
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the bc4chemd_ner dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0641 |
|
- Precision: 0.8944 |
|
- Recall: 0.8777 |
|
- F1: 0.8860 |
|
- Accuracy: 0.9908 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.006 | 1.0 | 1918 | 0.0310 | 0.8697 | 0.8510 | 0.8602 | 0.9894 | |
|
| 0.0097 | 2.0 | 3836 | 0.0345 | 0.8855 | 0.8637 | 0.8745 | 0.9898 | |
|
| 0.0058 | 3.0 | 5754 | 0.0359 | 0.8733 | 0.8836 | 0.8784 | 0.9902 | |
|
| 0.0014 | 4.0 | 7672 | 0.0440 | 0.8723 | 0.8842 | 0.8782 | 0.9903 | |
|
| 0.0005 | 5.0 | 9590 | 0.0539 | 0.8862 | 0.8673 | 0.8766 | 0.9903 | |
|
| 0.0001 | 6.0 | 11508 | 0.0558 | 0.8939 | 0.8628 | 0.8781 | 0.9904 | |
|
| 0.0001 | 7.0 | 13426 | 0.0558 | 0.8846 | 0.8729 | 0.8787 | 0.9903 | |
|
| 0.0012 | 8.0 | 15344 | 0.0635 | 0.8935 | 0.8696 | 0.8814 | 0.9905 | |
|
| 0.0 | 9.0 | 17262 | 0.0624 | 0.8897 | 0.8831 | 0.8864 | 0.9908 | |
|
| 0.0002 | 10.0 | 19180 | 0.0641 | 0.8944 | 0.8777 | 0.8860 | 0.9908 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.12.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
