dbert-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: 2.3699
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|
| 3.1176 | 1.0 | 7946 | 2.9781 |
| 2.873 | 2.0 | 15892 | 2.7518 |
| 2.7337 | 3.0 | 23838 | 2.6254 |
| 2.6536 | 4.0 | 31784 | 2.5434 |
| 2.5838 | 5.0 | 39730 | 2.4846 |
| 2.5376 | 6.0 | 47676 | 2.4394 |
| 2.513 | 7.0 | 55622 | 2.4142 |
| 2.4814 | 8.0 | 63568 | 2.3870 |
| 2.4737 | 9.0 | 71514 | 2.3759 |
| 2.467 | 10.0 | 79460 | 2.3699 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2