CS221-roberta-base-finetuned-semeval-custom
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3886
- F1 Micro: 0.7441
- Macro F1 Weighted: 0.6944
- Roc Auc: 0.8897
- Accuracy: 0.4116
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: 8
- eval_batch_size: 8
- 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 Micro | Macro F1 Weighted | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3091 | 1.0 | 277 | 0.3886 | 0.7441 | 0.6944 | 0.8897 | 0.4116 |
| 0.2611 | 2.0 | 554 | 0.3902 | 0.7340 | 0.6917 | 0.9001 | 0.4188 |
| 0.1948 | 3.0 | 831 | 0.4144 | 0.7328 | 0.6866 | 0.9012 | 0.4206 |
| 0.1586 | 4.0 | 1108 | 0.4738 | 0.7403 | 0.6906 | 0.8894 | 0.4134 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0