distilgpt2-CLM_US_Economic_News_Articles
This model is a fine-tuned version of distilgpt2. It achieves the following results on the evaluation set:
- Loss: 3.4472
Model description
This is a causal lamguage modeling project.
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Causal%20Language%20Modeling/US%20Economic%20News%20Articles/US%20Economic%20News%20Articles%20-%20CLM.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/heeraldedhia/us-economic-news-articles
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| 3.6225 | 1.0 | 1869 | 3.4853 |
| 3.5092 | 2.0 | 3738 | 3.4555 |
| 3.4514 | 3.0 | 5607 | 3.4472 |
Perplexity: 31.41
Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1
- Datasets 2.9.0
- Tokenizers 0.12.1
