|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: clinical_bert_ft |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# clinical_bert_ft |
|
|
|
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2439 |
|
- F1: 0.8252 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- 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 | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 0.5938 | 1.0 | 95 | 0.2480 | 0.7084 | |
|
| 0.1567 | 2.0 | 190 | 0.2035 | 0.7855 | |
|
| 0.083 | 3.0 | 285 | 0.2002 | 0.8026 | |
|
| 0.0482 | 4.0 | 380 | 0.2046 | 0.8118 | |
|
| 0.0269 | 5.0 | 475 | 0.2230 | 0.8143 | |
|
| 0.0185 | 6.0 | 570 | 0.2178 | 0.8175 | |
|
| 0.0123 | 7.0 | 665 | 0.2269 | 0.8253 | |
|
| 0.0093 | 8.0 | 760 | 0.2421 | 0.8227 | |
|
| 0.0072 | 9.0 | 855 | 0.2446 | 0.8267 | |
|
| 0.006 | 10.0 | 950 | 0.2439 | 0.8252 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.3.2 |
|
- Tokenizers 0.12.1 |
|
|
