distilbert-base-uncased-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0319
- Accuracy: 0.6038
- F1 Score: 0.5960
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: 1.0136026165598675e-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 Score |
|---|---|---|---|---|---|
| No log | 1.0 | 186 | 1.0319 | 0.6038 | 0.5960 |
| No log | 2.0 | 372 | 0.9585 | 0.5930 | 0.5890 |
| 1.0352 | 3.0 | 558 | 0.9438 | 0.5795 | 0.5791 |
| 1.0352 | 4.0 | 744 | 0.9726 | 0.5957 | 0.5966 |
| 1.0352 | 5.0 | 930 | 1.0109 | 0.5876 | 0.5870 |
| 0.6438 | 6.0 | 1116 | 1.1121 | 0.5795 | 0.5775 |
| 0.6438 | 7.0 | 1302 | 1.1804 | 0.5714 | 0.5711 |
| 0.6438 | 8.0 | 1488 | 1.2388 | 0.5741 | 0.5754 |
| 0.3747 | 9.0 | 1674 | 1.2941 | 0.5714 | 0.5708 |
| 0.3747 | 10.0 | 1860 | 1.3156 | 0.5714 | 0.5707 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1