dbert-peft-rating
This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0726
- Accuracy: 0.4988
- Mse: 0.8475
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: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mse |
|---|---|---|---|---|---|
| No log | 1.0 | 425 | 1.2773 | 0.4119 | 1.1295 |
| 1.3444 | 2.0 | 850 | 1.1427 | 0.4706 | 0.8780 |
| 1.1864 | 3.0 | 1275 | 1.1049 | 0.4885 | 0.8633 |
| 1.1177 | 4.0 | 1700 | 1.0943 | 0.4892 | 0.8169 |
| 1.0957 | 5.0 | 2125 | 1.0881 | 0.4923 | 0.8172 |
| 1.0893 | 6.0 | 2550 | 1.0814 | 0.4933 | 0.8636 |
| 1.0893 | 7.0 | 2975 | 1.0781 | 0.4943 | 0.8324 |
| 1.0761 | 8.0 | 3400 | 1.0749 | 0.4991 | 0.8464 |
| 1.0687 | 9.0 | 3825 | 1.0727 | 0.5002 | 0.8530 |
| 1.0668 | 10.0 | 4250 | 1.0726 | 0.4988 | 0.8475 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1