cs221-CS221-roberta-base-finetuned-semeval-new-finetuned-40-epochs
This model is a fine-tuned version of Kuongan/CS221-roberta-base-finetuned-semeval-new on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1719
- F1: 0.9001
- Roc Auc: 0.9249
- Accuracy: 0.7329
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2151 | 1.0 | 70 | 0.1750 | 0.8938 | 0.9193 | 0.7238 |
| 0.1997 | 2.0 | 140 | 0.1719 | 0.9001 | 0.9249 | 0.7329 |
| 0.1282 | 3.0 | 210 | 0.1794 | 0.8969 | 0.9221 | 0.7274 |
| 0.0865 | 4.0 | 280 | 0.1858 | 0.8920 | 0.9188 | 0.7202 |
| 0.0766 | 5.0 | 350 | 0.2013 | 0.8829 | 0.9104 | 0.6968 |
| 0.0608 | 6.0 | 420 | 0.2105 | 0.8888 | 0.9194 | 0.7130 |
| 0.0418 | 7.0 | 490 | 0.2157 | 0.8831 | 0.9150 | 0.6913 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0