Downloads · 30 days
5
17% of all-time downloads
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT
sercetexam9/deberta-v3-large-finetuned-augmentation-LUNAR-TAPT
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT is a text classification model from sercetexam9. 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
30
Public
Parameters
435M
27.8 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 28, 2025
- Updated
- Jan 28, 2025
- SHA
- 374822c4
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. -->
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT
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: 0.5533
- F1: 0.8318
- Roc Auc: 0.8690
- Accuracy: 0.6467
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.3563 | 1.0 | 317 | 0.3408 | 0.7270 | 0.7871 | 0.4582 |
| 0.2479 | 2.0 | 634 | 0.3140 | 0.7602 | 0.8190 | 0.5292 |
| 0.1544 | 3.0 | 951 | 0.3197 | 0.7959 | 0.8429 | 0.5749 |
| 0.1019 | 4.0 | 1268 | 0.3359 | 0.8007 | 0.8498 | 0.5915 |
| 0.0594 | 5.0 | 1585 | 0.3837 | 0.8097 | 0.8503 | 0.6057 |
| 0.043 | 6.0 | 1902 | 0.4182 | 0.8095 | 0.8530 | 0.5994 |
| 0.034 | 7.0 | 2219 | 0.4901 | 0.7914 | 0.8334 | 0.5915 |
| 0.0311 | 8.0 | 2536 | 0.5068 | 0.8041 | 0.8447 | 0.6151 |
| 0.0118 | 9.0 | 2853 | 0.5300 | 0.8105 | 0.8559 | 0.6080 |
| 0.0072 | 10.0 | 3170 | 0.5500 | 0.8258 | 0.8604 | 0.6301 |
| 0.0084 | 11.0 | 3487 | 0.5559 | 0.8235 | 0.8614 | 0.6333 |
| 0.0012 | 12.0 | 3804 | 0.5533 | 0.8318 | 0.8690 | 0.6467 |
| 0.0023 | 13.0 | 4121 | 0.5862 | 0.8190 | 0.8590 | 0.6270 |
| 0.0008 | 14.0 | 4438 | 0.5803 | 0.8300 | 0.8671 | 0.6443 |
| 0.0004 | 15.0 | 4755 | 0.5811 | 0.8306 | 0.8681 | 0.6459 |
| 0.0003 | 16.0 | 5072 | 0.5844 | 0.8308 | 0.8688 | 0.6467 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Jan 28, 2025
- Updated
- Jan 28, 2025