CS221-deberta-v3-large-finetuned
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4156
- F1: 0.7642
- Roc Auc: 0.8241
- Accuracy: 0.4874
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 |
|---|---|---|---|---|---|---|
| 0.4887 | 1.0 | 139 | 0.4524 | 0.5213 | 0.6932 | 0.3664 |
| 0.3704 | 2.0 | 278 | 0.3749 | 0.6683 | 0.7557 | 0.4097 |
| 0.2598 | 3.0 | 417 | 0.3470 | 0.7212 | 0.7918 | 0.4928 |
| 0.1556 | 4.0 | 556 | 0.3898 | 0.7290 | 0.7896 | 0.4783 |
| 0.0954 | 5.0 | 695 | 0.4156 | 0.7642 | 0.8241 | 0.4874 |
| 0.0705 | 6.0 | 834 | 0.5013 | 0.7267 | 0.7851 | 0.4910 |
| 0.0415 | 7.0 | 973 | 0.5330 | 0.7498 | 0.8087 | 0.4819 |
| 0.0293 | 8.0 | 1112 | 0.6317 | 0.7278 | 0.7910 | 0.4621 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0