Downloads · 30 days
9
2% of all-time downloads
deberta-base-finetuned-cola
Tomor0720/deberta-base-finetuned-cola
deberta-base-finetuned-cola is a text classification model from Tomor0720. 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
516
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin557 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta
- Access
- Public
- Created
- Jan 18, 2023
- Updated
- Jan 18, 2023
- SHA
- 7324aca8
Try a prompt
Datasets
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-base-finetuned-cola
This model is a fine-tuned version of microsoft/deberta-base on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.5812
- Matthews Correlation: 0.6332
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: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.4826 | 1.0 | 535 | 0.5277 | 0.5443 |
| 0.28 | 2.0 | 1070 | 0.4723 | 0.6331 |
| 0.1893 | 3.0 | 1605 | 0.5812 | 0.6332 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- deberta
- License
- mit
- Created
- Jan 18, 2023
- Updated
- Jan 18, 2023