distilbert-base-uncased-SpamFilter-LG

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0500
• Accuracy: 0.9845
• F1: 0.9848

Model description

This is a binary classification of whether the inputs are spam or not.

For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Binary%20Classification/Spam%20Filter-%20Larger%20Dataset/DunnBC22-distilbert-base-uncased-SpamFilter-LG.ipynb

Intended uses & limitations

This model is intended to demonstrate my ability to solve a complx problem using technology.

The main limitation is the quality of the data source.

Training and evaluation data

Dataset Source: https://www.kaggle.com/datasets/uciml/sms-spam-collection-dataset

Input Word Length By Class:

Confusion Matrix:

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	F1
0.0568	1.0	65	0.0568	0.9787	0.9791
0.03	2.0	130	0.0533	0.9806	0.9811
0.0241	3.0	195	0.0500	0.9845	0.9848

Framework versions

• Transformers 4.21.1
• Pytorch 1.12.1
• Datasets 2.4.0
• Tokenizers 0.12.1