|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: SETH_0.0001_250 |
|
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_250 |
|
|
|
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: 0.0681 |
|
- Precision: 0.7818 |
|
- Recall: 0.7945 |
|
- F1: 0.7881 |
|
- Accuracy: 0.9850 |
|
|
|
## 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: 500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.2912 | 0.76 | 25 | 0.1275 | 0.8475 | 0.0909 | 0.1642 | 0.9647 | |
|
| 0.0752 | 1.52 | 50 | 0.0588 | 0.6884 | 0.7873 | 0.7345 | 0.9799 | |
|
| 0.0433 | 2.27 | 75 | 0.0603 | 0.6623 | 0.8309 | 0.7371 | 0.9803 | |
|
| 0.0394 | 3.03 | 100 | 0.0516 | 0.6761 | 0.8727 | 0.7619 | 0.9822 | |
|
| 0.0292 | 3.79 | 125 | 0.0534 | 0.7430 | 0.8145 | 0.7771 | 0.9836 | |
|
| 0.0249 | 4.55 | 150 | 0.0520 | 0.7384 | 0.8109 | 0.7730 | 0.9828 | |
|
| 0.0196 | 5.3 | 175 | 0.0618 | 0.7442 | 0.8145 | 0.7778 | 0.9833 | |
|
| 0.0165 | 6.06 | 200 | 0.0604 | 0.7538 | 0.8182 | 0.7847 | 0.9846 | |
|
| 0.0131 | 6.82 | 225 | 0.0613 | 0.7788 | 0.7745 | 0.7767 | 0.9843 | |
|
| 0.0095 | 7.58 | 250 | 0.0681 | 0.7818 | 0.7945 | 0.7881 | 0.9850 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.2 |
|
|
