fold_4_model_roberta_r
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5005
- F1: 0.7683
- Roc Auc: 0.8247
- Accuracy: 0.4851
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: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.0766 | 1.0 | 102 | 0.5332 | 0.7493 | 0.8125 | 0.4356 |
| 0.0799 | 2.0 | 204 | 0.5034 | 0.7429 | 0.8068 | 0.4257 |
| 0.0586 | 3.0 | 306 | 0.5005 | 0.7683 | 0.8247 | 0.4851 |
| 0.0509 | 4.0 | 408 | 0.5068 | 0.7644 | 0.8230 | 0.4455 |
| 0.0185 | 5.0 | 510 | 0.5013 | 0.7683 | 0.8247 | 0.4950 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0