|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: SETH_0.0001_0404_ES6 |
|
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. --> |
|
|
|
# SETH_0.0001_0404_ES6 |
|
|
|
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0645 |
|
- Precision: 0.8013 |
|
- Recall: 0.8537 |
|
- F1: 0.8267 |
|
- Accuracy: 0.9861 |
|
|
|
## 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: 0.0001 |
|
- 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 |
|
- training_steps: 2000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2589 | 0.96 | 25 | 0.0930 | 0.84 | 0.2530 | 0.3889 | 0.9670 | |
|
| 0.0625 | 1.92 | 50 | 0.0580 | 0.7024 | 0.8003 | 0.7482 | 0.9813 | |
|
| 0.041 | 2.88 | 75 | 0.0554 | 0.7890 | 0.7659 | 0.7773 | 0.9814 | |
|
| 0.0318 | 3.85 | 100 | 0.0528 | 0.6951 | 0.8709 | 0.7731 | 0.9814 | |
|
| 0.0254 | 4.81 | 125 | 0.0488 | 0.7601 | 0.8778 | 0.8147 | 0.9846 | |
|
| 0.0174 | 5.77 | 150 | 0.0571 | 0.7669 | 0.7814 | 0.7741 | 0.9833 | |
|
| 0.0144 | 6.73 | 175 | 0.0598 | 0.7744 | 0.8451 | 0.8082 | 0.9838 | |
|
| 0.0135 | 7.69 | 200 | 0.0587 | 0.7530 | 0.8657 | 0.8054 | 0.9848 | |
|
| 0.0074 | 8.65 | 225 | 0.0695 | 0.8162 | 0.8176 | 0.8169 | 0.9859 | |
|
| 0.0087 | 9.62 | 250 | 0.0606 | 0.7746 | 0.8279 | 0.8003 | 0.9848 | |
|
| 0.0063 | 10.58 | 275 | 0.0645 | 0.8013 | 0.8537 | 0.8267 | 0.9861 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
