CS221-roberta-large-finetuned-semeval
This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5173
- F1: 0.7871
- Roc Auc: 0.8376
- Accuracy: 0.5108
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 |
|---|---|---|---|---|---|---|
| 0.4397 | 1.0 | 139 | 0.4066 | 0.7281 | 0.7978 | 0.3791 |
| 0.3197 | 2.0 | 278 | 0.3492 | 0.7382 | 0.7989 | 0.4531 |
| 0.2545 | 3.0 | 417 | 0.3468 | 0.7768 | 0.8311 | 0.4747 |
| 0.1612 | 4.0 | 556 | 0.3863 | 0.7558 | 0.8140 | 0.4603 |
| 0.1024 | 5.0 | 695 | 0.4171 | 0.7790 | 0.8313 | 0.4892 |
| 0.0534 | 6.0 | 834 | 0.4549 | 0.7776 | 0.8310 | 0.4856 |
| 0.0508 | 7.0 | 973 | 0.4772 | 0.7857 | 0.8374 | 0.4838 |
| 0.026 | 8.0 | 1112 | 0.5173 | 0.7871 | 0.8376 | 0.5108 |
| 0.0263 | 9.0 | 1251 | 0.5434 | 0.7840 | 0.8369 | 0.4856 |
| 0.0129 | 10.0 | 1390 | 0.5710 | 0.7811 | 0.8338 | 0.4819 |
| 0.009 | 11.0 | 1529 | 0.5823 | 0.7854 | 0.8368 | 0.5072 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0