Downloads · 30 days
22
48% of all-time downloads
CS221-deberta-v3-large-finetuned-augmentation
Kuongan/CS221-deberta-v3-large-finetuned-augmentation
CS221-deberta-v3-large-finetuned-augmentation is a text classification model from Kuongan. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
46
Public
Parameters
435M
88.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Jan 22, 2025
- Updated
- Jan 23, 2025
- SHA
- 3fa0074c
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
CS221-deberta-v3-large-finetuned-augmentation
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: 0.6529
- F1: 0.7880
- Roc Auc: 0.8406
- Accuracy: 0.5840
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 |
|---|---|---|---|---|---|---|
| 0.4902 | 1.0 | 176 | 0.4605 | 0.5127 | 0.6705 | 0.3348 |
| 0.3638 | 2.0 | 352 | 0.4028 | 0.6279 | 0.7349 | 0.4231 |
| 0.2784 | 3.0 | 528 | 0.3874 | 0.6829 | 0.7651 | 0.4744 |
| 0.1717 | 4.0 | 704 | 0.3967 | 0.7436 | 0.8069 | 0.5199 |
| 0.1063 | 5.0 | 880 | 0.4247 | 0.7453 | 0.7992 | 0.5299 |
| 0.0744 | 6.0 | 1056 | 0.4844 | 0.7536 | 0.8159 | 0.5285 |
| 0.0359 | 7.0 | 1232 | 0.5120 | 0.7775 | 0.8318 | 0.5670 |
| 0.0306 | 8.0 | 1408 | 0.5876 | 0.7641 | 0.8250 | 0.5427 |
| 0.0164 | 9.0 | 1584 | 0.5693 | 0.7799 | 0.8296 | 0.5883 |
| 0.0101 | 10.0 | 1760 | 0.6193 | 0.7817 | 0.8309 | 0.5840 |
| 0.0042 | 11.0 | 1936 | 0.6293 | 0.7853 | 0.8397 | 0.5855 |
| 0.0025 | 12.0 | 2112 | 0.6529 | 0.7880 | 0.8406 | 0.5840 |
| 0.0056 | 13.0 | 2288 | 0.6672 | 0.7843 | 0.8416 | 0.5726 |
| 0.0022 | 14.0 | 2464 | 0.6656 | 0.7865 | 0.8408 | 0.5812 |
| 0.0011 | 15.0 | 2640 | 0.6695 | 0.7859 | 0.8427 | 0.5826 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Jan 22, 2025
- Updated
- Jan 23, 2025