output
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3561
- Accuracy: 0.913
- Precision: 0.9319
- Recall: 0.8918
- F1: 0.9114
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: 5e-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: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3442 | 0.2 | 500 | 0.3018 | 0.8867 | 0.8598 | 0.9251 | 0.8912 |
| 0.274 | 0.4 | 1000 | 0.2399 | 0.9033 | 0.9060 | 0.9008 | 0.9034 |
| 0.2598 | 0.6 | 1500 | 0.2668 | 0.9095 | 0.9280 | 0.8886 | 0.9079 |
| 0.2394 | 0.8 | 2000 | 0.2395 | 0.9097 | 0.8871 | 0.9396 | 0.9126 |
| 0.2267 | 1.0 | 2500 | 0.2418 | 0.9104 | 0.9425 | 0.8749 | 0.9074 |
| 0.1518 | 1.2 | 3000 | 0.2692 | 0.9133 | 0.8968 | 0.9348 | 0.9154 |
| 0.1465 | 1.4 | 3500 | 0.3561 | 0.913 | 0.9319 | 0.8918 | 0.9114 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1