distilbert_NewsQA_model
This model is a fine-tuned version of distilbert-base-uncased on an the NewsQA dataset. So it was specifically trained to answer questions in English news articles. It achieves the following results on the evaluation set:
- Loss: 1.9481
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
- distributed_type: tpu
- 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 |
|---|---|---|---|
| 2.0465 | 1.0 | 6730 | 2.0565 |
| 1.8092 | 2.0 | 13460 | 1.9559 |
| 1.7095 | 3.0 | 20190 | 1.9481 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.12.1+cu102
- Datasets 2.9.0
- Tokenizers 0.13.2