distilbert-qa-checkpoint-v5
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4904
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3912 | 1.0 | 2059 | 0.3897 |
| 0.3313 | 2.0 | 4118 | 0.3449 |
| 0.2679 | 3.0 | 6177 | 0.3508 |
| 0.2323 | 4.0 | 8236 | 0.3489 |
| 0.2047 | 5.0 | 10295 | 0.3578 |
| 0.1913 | 6.0 | 12354 | 0.4529 |
| 0.1821 | 7.0 | 14413 | 0.4904 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3