Downloads · 30 days
6
2% of all-time downloads
deberta-finetuned-answer-polarity-7e-adj
GCopoulos/deberta-finetuned-answer-polarity-7e-adj
deberta-finetuned-answer-polarity-7e-adj is a text classification model from GCopoulos. 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
313
Public
Repo size
6.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.6 GB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- deberta
- Access
- Public
- Created
- Jun 2, 2023
- Updated
- Jun 2, 2023
- SHA
- 12ee8d75
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-finetuned-answer-polarity-7e-adj
This model is a fine-tuned version of microsoft/deberta-large on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.7605
- F1: 0.8582
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: 7e-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 | F1 |
|---|---|---|---|---|
| No log | 1.0 | 262 | 0.3918 | 0.8901 |
| 0.4372 | 2.0 | 524 | 0.4592 | 0.9138 |
| 0.4372 | 3.0 | 786 | 0.7605 | 0.8582 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- deberta
- License
- mit
- Created
- Jun 2, 2023
- Updated
- Jun 2, 2023