bert-base-uncased-swag-full
This model is a fine-tuned version of google-bert/bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8572
- Accuracy: 0.7760
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: 5e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7762 | 1.0 | 4597 | 0.6281 | 0.7516 |
| 0.4259 | 2.0 | 9194 | 0.6857 | 0.7668 |
| 0.2108 | 3.0 | 13791 | 0.9799 | 0.7689 |
| 0.1207 | 4.0 | 18388 | 1.5455 | 0.7721 |
| 0.0523 | 5.0 | 22985 | 1.8572 | 0.7760 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for yefo-ufpe/bert-base-uncased-swag-full
Base model
google-bert/bert-base-uncased