CS221-deberta-large-finetuned-semeval-NT
This model is a fine-tuned version of microsoft/deberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7626
- F1: 0.7769
- Roc Auc: 0.8347
- Accuracy: 0.4711
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 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.3938 | 1.0 | 277 | 0.3549 | 0.7563 | 0.8155 | 0.4585 |
| 0.273 | 2.0 | 554 | 0.3731 | 0.7376 | 0.7993 | 0.4368 |
| 0.1452 | 3.0 | 831 | 0.3962 | 0.7548 | 0.8119 | 0.4729 |
| 0.1046 | 4.0 | 1108 | 0.4750 | 0.7572 | 0.8169 | 0.4495 |
| 0.0635 | 5.0 | 1385 | 0.5714 | 0.7714 | 0.8279 | 0.4621 |
| 0.0512 | 6.0 | 1662 | 0.6294 | 0.7610 | 0.8199 | 0.4567 |
| 0.0605 | 7.0 | 1939 | 0.7023 | 0.7663 | 0.8244 | 0.4639 |
| 0.0122 | 8.0 | 2216 | 0.7376 | 0.7752 | 0.8315 | 0.4765 |
| 0.0083 | 9.0 | 2493 | 0.7626 | 0.7769 | 0.8347 | 0.4711 |
| 0.0041 | 10.0 | 2770 | 0.7788 | 0.7738 | 0.8280 | 0.4856 |
| 0.0018 | 11.0 | 3047 | 0.8313 | 0.7760 | 0.8309 | 0.4910 |
| 0.0004 | 12.0 | 3324 | 0.8328 | 0.7758 | 0.8306 | 0.4856 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0