Downloads · 30 days
13
30% of all-time downloads
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-MICRO
sercetexam9/deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-MICRO
deberta-v3-large-finetuned-augmentation-LUNAR-TAPT-MICRO 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
44
Public
Parameters
435M
34.8 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 30, 2025
- Updated
- Jan 30, 2025
- SHA
- d7008040
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-MICRO
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: 0.6264
- F1: 0.8388
- Roc Auc: 0.8832
- Accuracy: 0.6210
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 |
|---|---|---|---|---|---|---|
| 0.3567 | 1.0 | 318 | 0.3385 | 0.7625 | 0.8279 | 0.4720 |
| 0.2167 | 2.0 | 636 | 0.3214 | 0.7789 | 0.8343 | 0.5169 |
| 0.1671 | 3.0 | 954 | 0.3344 | 0.7993 | 0.8525 | 0.5563 |
| 0.1232 | 4.0 | 1272 | 0.3564 | 0.8105 | 0.8688 | 0.5508 |
| 0.0628 | 5.0 | 1590 | 0.3811 | 0.8240 | 0.8722 | 0.5942 |
| 0.0429 | 6.0 | 1908 | 0.4519 | 0.8175 | 0.8731 | 0.5642 |
| 0.0299 | 7.0 | 2226 | 0.5019 | 0.8210 | 0.8728 | 0.5776 |
| 0.0249 | 8.0 | 2544 | 0.5133 | 0.8249 | 0.8735 | 0.5863 |
| 0.0137 | 9.0 | 2862 | 0.5349 | 0.8311 | 0.8793 | 0.5981 |
| 0.0087 | 10.0 | 3180 | 0.5533 | 0.8320 | 0.8801 | 0.5934 |
| 0.01 | 11.0 | 3498 | 0.5680 | 0.8289 | 0.8775 | 0.5871 |
| 0.0051 | 12.0 | 3816 | 0.6149 | 0.8307 | 0.8774 | 0.5950 |
| 0.0009 | 13.0 | 4134 | 0.6066 | 0.8343 | 0.8805 | 0.6060 |
| 0.0028 | 14.0 | 4452 | 0.6163 | 0.8348 | 0.8829 | 0.6028 |
| 0.0048 | 15.0 | 4770 | 0.6236 | 0.8345 | 0.8801 | 0.6044 |
| 0.0015 | 16.0 | 5088 | 0.6220 | 0.8385 | 0.8833 | 0.6186 |
| 0.0003 | 17.0 | 5406 | 0.6260 | 0.8369 | 0.8819 | 0.6178 |
| 0.0004 | 18.0 | 5724 | 0.6264 | 0.8388 | 0.8832 | 0.6210 |
| 0.0004 | 19.0 | 6042 | 0.6271 | 0.8388 | 0.8829 | 0.6202 |
| 0.0004 | 20.0 | 6360 | 0.6274 | 0.8385 | 0.8828 | 0.6194 |
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 30, 2025
- Updated
- Jan 30, 2025