Distil_BERT_1
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: 1.1229
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 |
|---|---|---|---|
| 1.2836 | 1.0 | 4380 | 1.1369 |
| 0.9333 | 2.0 | 8760 | 1.1010 |
| 0.7604 | 3.0 | 13140 | 1.1229 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3