dbert-review-classification-no-0
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3861
- Accuracy: 0.5476
- Mse: 0.7262
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Mse |
|---|---|---|---|---|---|
| No log | 1.0 | 425 | 1.1171 | 0.4978 | 0.8375 |
| 1.128 | 2.0 | 850 | 1.0512 | 0.5479 | 0.7035 |
| 0.8848 | 3.0 | 1275 | 1.0840 | 0.5582 | 0.7564 |
| 0.6721 | 4.0 | 1700 | 1.2197 | 0.5617 | 0.6870 |
| 0.4925 | 5.0 | 2125 | 1.3861 | 0.5476 | 0.7262 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1