bert-base-uncased-finetuned-squad
This model is a fine-tuned version of bert-base-uncased on the SQuAD1.1 dataset. It was trained through Transformers' example Colab notebook on Question Answering, available here. It achieves the following results on the evaluation set:
- Loss: 1.0780
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. They are equal to the ones used to fine-tune distilbert-base-uncased for QA:
- 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 |
|---|---|---|---|
| 1.0706 | 1.0 | 5533 | 1.0250 |
| 0.7899 | 2.0 | 11066 | 1.0356 |
| 0.5991 | 3.0 | 16599 | 1.0780 |
Validation results
| EM | F1 |
|---|---|
| 80.3690 | 88.0110 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3
- Downloads last month
- 72
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.