distilbert-base-uncased-OnionOrNot
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: 0.2039
- Accuracy: 0.9224
- F1: 0.9218
Model description
This is a binary classification model to determine if the input sample is an onion news title 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/OnionOrNot/DunnBC22-distilbert-base-uncased-OnionOrNot.ipynb
Intended uses & limitations
This model is intended to demonstrate my ability to solve a complex problem using technology.
The main limitation is the quality of the data source.
Training and evaluation data
Dataset Source: https://www.kaggle.com/datasets/chrisfilo/onion-or-not
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: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.3334 | 1.0 | 300 | 0.2382 | 0.9024 | 0.9011 |
0.1822 | 2.0 | 600 | 0.2039 | 0.9224 | 0.9218 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1
- Datasets 2.4.0
- Tokenizers 0.12.1