NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2-tuning
This model is a fine-tuned version of mastikaui/NLP-Sentiment-Analysis-Airline-Tweets-with-BERT-V2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3128
- Accuracy: 0.8776
- F1 Score: 0.8775
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Score |
|---|---|---|---|---|---|
| 0.3035 | 1.0 | 1224 | 0.3224 | 0.8636 | 0.8637 |
| 0.2797 | 2.0 | 2448 | 0.3174 | 0.8685 | 0.8685 |
| 0.2881 | 3.0 | 3672 | 0.3139 | 0.8709 | 0.8709 |
| 0.2719 | 4.0 | 4896 | 0.3167 | 0.8734 | 0.8734 |
| 0.2573 | 5.0 | 6120 | 0.3155 | 0.8758 | 0.8758 |
| 0.2524 | 6.0 | 7344 | 0.3153 | 0.8743 | 0.8743 |
| 0.2531 | 7.0 | 8568 | 0.3158 | 0.8752 | 0.8753 |
| 0.2516 | 8.0 | 9792 | 0.3199 | 0.8746 | 0.8747 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.