DistilBERT-yelp-sentiment-analysis
This model is a fine-tuned version of distilbert-base-uncased on the Yelp dataset. It achieves the following results on the evaluation set:
- Loss: 0.4803
- Accuracy: 0.8299
- F1: 0.6263
- Precision: 0.6756
- Recall: 0.6342
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.5764 | 1.0 | 772 | 0.4669 | 0.8299 | 0.6068 | 0.6229 | 0.6239 |
0.388 | 2.0 | 1544 | 0.5814 | 0.7805 | 0.6497 | 0.6356 | 0.6815 |
0.2689 | 3.0 | 2316 | 0.7125 | 0.8273 | 0.7169 | 0.7261 | 0.7266 |
0.2019 | 4.0 | 3088 | 0.8057 | 0.8234 | 0.6844 | 0.6842 | 0.6847 |
0.1498 | 5.0 | 3860 | 0.9611 | 0.8351 | 0.6890 | 0.6952 | 0.6836 |
0.1009 | 6.0 | 4632 | 1.0680 | 0.8169 | 0.6924 | 0.6930 | 0.6981 |
0.0762 | 7.0 | 5404 | 1.2147 | 0.8247 | 0.6642 | 0.6665 | 0.6626 |
0.0441 | 8.0 | 6176 | 1.3939 | 0.8143 | 0.7016 | 0.7125 | 0.7143 |
0.0471 | 9.0 | 6948 | 1.2903 | 0.8325 | 0.7109 | 0.7136 | 0.7116 |
0.054 | 10.0 | 7720 | 1.1024 | 0.8442 | 0.7089 | 0.7180 | 0.7035 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 60