cs221-deberta-v3-base-finetuned
This model is a fine-tuned version of microsoft/deberta-v3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3618
- F1: 0.7829
- Roc Auc: 0.8382
- Accuracy: 0.5054
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: 32
- eval_batch_size: 32
- 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: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.58 | 1.0 | 70 | 0.5815 | 0.4288 | 0.6088 | 0.1300 |
| 0.4446 | 2.0 | 140 | 0.4356 | 0.6621 | 0.7496 | 0.3556 |
| 0.3545 | 3.0 | 210 | 0.3941 | 0.7160 | 0.7893 | 0.4007 |
| 0.26 | 4.0 | 280 | 0.3702 | 0.7387 | 0.8056 | 0.4368 |
| 0.2425 | 5.0 | 350 | 0.3622 | 0.7641 | 0.8231 | 0.4783 |
| 0.1971 | 6.0 | 420 | 0.3565 | 0.7689 | 0.8270 | 0.4892 |
| 0.1582 | 7.0 | 490 | 0.3657 | 0.7703 | 0.8268 | 0.4892 |
| 0.161 | 8.0 | 560 | 0.3618 | 0.7829 | 0.8382 | 0.5054 |
| 0.14 | 9.0 | 630 | 0.3613 | 0.7789 | 0.8345 | 0.5 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.21.0