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: 5.9506
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: 0.001
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.737 | 1.0 | 557 | 5.9506 |
| 5.9622 | 2.0 | 1114 | 5.9506 |
| 5.9577 | 3.0 | 1671 | 5.9506 |
| 5.9543 | 4.0 | 2228 | 5.9506 |
| 5.9541 | 5.0 | 2785 | 5.9506 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2