distilBERT_wiki_SST-2
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6966
- Accuracy: 0.4885
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: 512
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| No log | 1.0 | 132 | 0.6997 | 0.4771 |
| No log | 2.0 | 264 | 0.6966 | 0.4805 |
| No log | 3.0 | 396 | 0.6962 | 0.5264 |
| 0.683 | 4.0 | 528 | 0.6961 | 0.5631 |
| 0.683 | 5.0 | 660 | 0.6966 | 0.4885 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
