bort-News_About_Gold
This model is a fine-tuned version of amazon/bort. It achieves the following results on the evaluation set:
- Loss: 0.3791
- Accuracy: 0.8770
- Weighted f1: 0.8743
- Micro f1: 0.8770
- Macro f1: 0.7791
- Weighted recall: 0.8770
- Micro recall: 0.8770
- Macro recall: 0.7539
- Weighted precision: 0.8778
- Micro precision: 0.8770
- Macro precision: 0.8463
Model description
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)/News%20About%20Gold%20-%20Sentiment%20Analysis%20-%20BORT%20with%20W%26B.ipynb
This project is part of a comparison of seven (7) transformers. Here is the README page for the comparison: https://github.com/DunnBC22/NLP_Projects/tree/main/Sentiment%20Analysis/Sentiment%20Analysis%20of%20Commodity%20News%20-%20Gold%20(Transformer%20Comparison)
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/ankurzing/sentiment-analysis-in-commodity-market-gold
Input Word Length:
/Images/Input%20Word%20Length.png)
Class Distribution:
/Images/Class%20Distribution.png)
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 | Accuracy | Weighted f1 | Micro f1 | Macro f1 | Weighted recall | Micro recall | Macro recall | Weighted precision | Micro precision | Macro precision |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.0437 | 1.0 | 133 | 0.8379 | 0.6954 | 0.6800 | 0.6954 | 0.5285 | 0.6954 | 0.6954 | 0.5326 | 0.6944 | 0.6954 | 0.5434 |
| 0.6297 | 2.0 | 266 | 0.4715 | 0.8340 | 0.8209 | 0.8340 | 0.6267 | 0.8340 | 0.8340 | 0.6368 | 0.8111 | 0.8340 | 0.6187 |
| 0.4216 | 3.0 | 399 | 0.3984 | 0.8661 | 0.8616 | 0.8661 | 0.7464 | 0.8661 | 0.8661 | 0.7231 | 0.8698 | 0.8661 | 0.8597 |
| 0.3339 | 4.0 | 532 | 0.3808 | 0.8765 | 0.8748 | 0.8765 | 0.7825 | 0.8765 | 0.8765 | 0.7628 | 0.8774 | 0.8765 | 0.8304 |
| 0.2869 | 5.0 | 665 | 0.3791 | 0.8770 | 0.8743 | 0.8770 | 0.7791 | 0.8770 | 0.8770 | 0.7539 | 0.8778 | 0.8770 | 0.8463 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.3
