|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
- roc_auc |
|
model-index: |
|
- name: distilbert-base-uncased_research_articles_multilabel |
|
results: [] |
|
language: |
|
- en |
|
pipeline_tag: text-classification |
|
--- |
|
|
|
# distilbert-base-uncased_research_articles_multilabel |
|
|
|
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1956 |
|
- F1: 0.8395 |
|
- Roc Auc: 0.8909 |
|
- Accuracy: 0.6977 |
|
|
|
## Model description |
|
|
|
This is a multilabel classification model of the topics included in research articles. |
|
|
|
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Multilabel%20Classification/Research%20Articles-Multilabel%20clf.ipynb |
|
|
|
## Intended uses & limitations |
|
|
|
This model is intended to demonstrate my ability to solve a complex problem using technology. |
|
|
|
## Training and evaluation data |
|
|
|
Dataset Source: https://www.kaggle.com/datasets/shivanandmn/multilabel-classification-dataset |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:| |
|
| 0.3043 | 1.0 | 263 | 0.2199 | 0.8198 | 0.8686 | 0.6829 | |
|
| 0.2037 | 2.0 | 526 | 0.1988 | 0.8355 | 0.8845 | 0.7010 | |
|
| 0.1756 | 3.0 | 789 | 0.1956 | 0.8395 | 0.8909 | 0.6977 | |
|
| 0.1579 | 4.0 | 1052 | 0.1964 | 0.8371 | 0.8902 | 0.6919 | |
|
| 0.1461 | 5.0 | 1315 | 0.1991 | 0.8353 | 0.8874 | 0.6953 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.3 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
