distilbert-base-uncased-answerable-or-not
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: 0.0297
- Accuracy: 0.9924
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2014 | 1.0 | 198 | 0.1863 | 0.9418 |
| 0.2518 | 2.0 | 396 | 0.0605 | 0.9873 |
| 0.0009 | 3.0 | 594 | 0.0297 | 0.9924 |
| 0.0005 | 4.0 | 792 | 0.0675 | 0.9848 |
| 0.0004 | 5.0 | 990 | 0.0586 | 0.9924 |
| 0.0004 | 6.0 | 1188 | 0.0520 | 0.9873 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2