distilbert-base-uncased-finetuned-squad
This model is a fine-tuned version of distilbert-base-uncased on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.5282
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: 1e-05
- train_batch_size: 30
- eval_batch_size: 30
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 295 | 2.3734 |
| 3.0199 | 2.0 | 590 | 1.7638 |
| 3.0199 | 3.0 | 885 | 1.5867 |
| 1.582 | 4.0 | 1180 | 1.5535 |
| 1.582 | 5.0 | 1475 | 1.5281 |
| 1.2859 | 6.0 | 1770 | 1.5282 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2