my_awesome_qa_model
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: 2.5056
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 250 | 1.6117 |
| 1.0 | 2.0 | 500 | 1.6333 |
| 1.0 | 3.0 | 750 | 1.7714 |
| 0.5364 | 4.0 | 1000 | 1.8200 |
| 0.5364 | 5.0 | 1250 | 2.1226 |
| 0.3006 | 6.0 | 1500 | 2.1703 |
| 0.3006 | 7.0 | 1750 | 2.2897 |
| 0.1855 | 8.0 | 2000 | 2.4398 |
| 0.1855 | 9.0 | 2250 | 2.4811 |
| 0.1347 | 10.0 | 2500 | 2.5056 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2