CS221-distilroberta-base-finetuned-semeval
This model is a fine-tuned version of distilbert/distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4024
- F1: 0.7444
- Roc Auc: 0.8104
- Accuracy: 0.4170
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: 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.478 | 1.0 | 139 | 0.5067 | 0.6015 | 0.7052 | 0.2401 |
| 0.4164 | 2.0 | 278 | 0.4079 | 0.6864 | 0.7642 | 0.3953 |
| 0.353 | 3.0 | 417 | 0.3992 | 0.7077 | 0.7808 | 0.3736 |
| 0.2987 | 4.0 | 556 | 0.4084 | 0.7239 | 0.7929 | 0.3899 |
| 0.193 | 5.0 | 695 | 0.4024 | 0.7444 | 0.8104 | 0.4170 |
| 0.1561 | 6.0 | 834 | 0.4017 | 0.7351 | 0.7995 | 0.4314 |
| 0.14 | 7.0 | 973 | 0.4404 | 0.7112 | 0.7816 | 0.4007 |
| 0.1035 | 8.0 | 1112 | 0.4463 | 0.7357 | 0.8001 | 0.4350 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0