distilbert-base-uncased-SQUADMODELDISTILUNCASED
This model was trained from scratch on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.4911
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5808 | 1.0 | 6167 | 1.3138 |
| 0.4698 | 2.0 | 12334 | 1.3968 |
| 0.427 | 3.0 | 18501 | 1.4911 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3