|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: SETH_5e-05_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_5e-05_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: 0.0650 |
|
- Precision: 0.7754 |
|
- Recall: 0.8675 |
|
- F1: 0.8188 |
|
- Accuracy: 0.9857 |
|
|
|
## 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.331 | 0.96 | 25 | 0.1111 | 0.3370 | 0.6265 | 0.4383 | 0.9582 | |
|
| 0.0683 | 1.92 | 50 | 0.0626 | 0.7098 | 0.8210 | 0.7614 | 0.9796 | |
|
| 0.0423 | 2.88 | 75 | 0.0547 | 0.7559 | 0.8313 | 0.7918 | 0.9827 | |
|
| 0.0342 | 3.85 | 100 | 0.0527 | 0.6795 | 0.8795 | 0.7667 | 0.9805 | |
|
| 0.0298 | 4.81 | 125 | 0.0574 | 0.6802 | 0.8933 | 0.7723 | 0.9804 | |
|
| 0.02 | 5.77 | 150 | 0.0476 | 0.7457 | 0.8124 | 0.7776 | 0.9837 | |
|
| 0.0165 | 6.73 | 175 | 0.0520 | 0.7845 | 0.8210 | 0.8024 | 0.9852 | |
|
| 0.0145 | 7.69 | 200 | 0.0645 | 0.7075 | 0.8950 | 0.7903 | 0.9828 | |
|
| 0.0092 | 8.65 | 225 | 0.0620 | 0.7945 | 0.8451 | 0.8190 | 0.9863 | |
|
| 0.0083 | 9.62 | 250 | 0.0727 | 0.7426 | 0.8692 | 0.8010 | 0.9836 | |
|
| 0.0054 | 10.58 | 275 | 0.0628 | 0.8 | 0.8330 | 0.8162 | 0.9861 | |
|
| 0.0058 | 11.54 | 300 | 0.0650 | 0.7754 | 0.8675 | 0.8188 | 0.9857 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
