roberta-base-uncased-finetuned-swag
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4967
- Accuracy: 0.8099
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.791 | 1.0 | 2299 | 0.5549 | 0.7824 |
| 0.5334 | 2.0 | 4598 | 0.4967 | 0.8099 |
| 0.3262 | 3.0 | 6897 | 0.5730 | 0.8157 |
| 0.1798 | 4.0 | 9196 | 0.6544 | 0.8257 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3