bert-base-uncased-finetuned-swag-mcq
This model is a fine-tuned version of bert-base-uncased on the swag dataset. It achieves the following results on the evaluation set:
- Loss: 0.9458
- Accuracy: 0.8055
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7305 | 1.0 | 4597 | 0.5244 | 0.7958 |
| 0.4343 | 2.0 | 9194 | 0.5315 | 0.8081 |
| 0.2468 | 3.0 | 13791 | 0.7024 | 0.8048 |
| 0.1334 | 4.0 | 18388 | 0.9458 | 0.8055 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3