|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: codebert-base-Password_Strength_Classifier |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
# codebert-base-Password_Strength_Classifier |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base). |
|
|
|
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0077 |
|
|
- Accuracy: 0.9975 |
|
|
- F1 |
|
|
- Weighted: 0.9975 |
|
|
- Micro: 0.9975 |
|
|
- Macro: 0.9963 |
|
|
- Recall |
|
|
- Weighted: 0.9975 |
|
|
- Micro: 0.9975 |
|
|
- Macro: 0.9978 |
|
|
- Precision |
|
|
- Weighted: 0.9975 |
|
|
- Macro: 0.9948 |
|
|
- Micro: 0.9975 |
|
|
|
|
|
## Model description |
|
|
|
|
|
The model classifies passwords as one of the following: |
|
|
1) Weak |
|
|
2) Medium |
|
|
3) Strong |
|
|
|
|
|
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Password%20Strength%20Classification%20(MC)/CodeBERT-Base%20-%20Password_Classifier.ipynb |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
This is intended to show the possibilities. It is mainly limited by the input data. |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
Dataset Source: https://www.kaggle.com/datasets/bhavikbb/password-strength-classifier-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: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Weighted F1 | Micro F1 | Macro F1 | Weighted Recall | Micro Recall | Macro Recall | Weighted Precision | Micro Precision | Macro Precision | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-----------:|:--------:|:--------:|:---------------:|:------------:|:------------:|:------------------:|:---------------:|:---------------:| |
|
|
| 0.0438 | 1.0 | 8371 | 0.0112 | 0.9956 | 0.9956 | 0.9956 | 0.9935 | 0.9956 | 0.9956 | 0.9963 | 0.9957 | 0.9956 | 0.9908 | |
|
|
| 0.0133 | 2.0 | 16742 | 0.0092 | 0.9966 | 0.9967 | 0.9966 | 0.9951 | 0.9966 | 0.9966 | 0.9966 | 0.9967 | 0.9966 | 0.9935 | |
|
|
| 0.0067 | 3.0 | 25113 | 0.0077 | 0.9975 | 0.9975 | 0.9975 | 0.9963 | 0.9975 | 0.9975 | 0.9978 | 0.9975 | 0.9975 | 0.9948 | |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.27.4 |
|
|
- Pytorch 2.0.0 |
|
|
- Datasets 2.11.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
