Downloads · 30 days
8
22% of all-time downloads
wikidyk-scope-clf-deberta-v3-large-1_cluster
YWZBrandon/wikidyk-scope-clf-deberta-v3-large-1_cluster
wikidyk-scope-clf-deberta-v3-large-1_cluster is a text classification model from YWZBrandon. 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
36
Public
Parameters
435M
1.7 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
- May 8, 2025
- Updated
- May 8, 2025
- SHA
- c4868567
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. -->
wikidyk-scope-clf-deberta-v3-large-1_cluster
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: 1.5455
- Accuracy: 0.8204
- F1: 0.8462
- Precision: 0.8141
- Recall: 0.8808
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: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.0921 | 1.0 | 902 | 0.6758 | 0.7565 | 0.7654 | 0.8326 | 0.7082 |
| 0.0634 | 2.0 | 1804 | 0.7185 | 0.8174 | 0.8362 | 0.8414 | 0.8310 |
| 0.0212 | 3.0 | 2706 | 0.9475 | 0.7725 | 0.8024 | 0.7821 | 0.8238 |
| 0.0079 | 4.0 | 3608 | 1.2432 | 0.7445 | 0.7991 | 0.7149 | 0.9057 |
| 0.0021 | 5.0 | 4510 | 1.4449 | 0.8024 | 0.8339 | 0.7889 | 0.8843 |
| 0.0003 | 6.0 | 5412 | 1.3861 | 0.7934 | 0.8262 | 0.7822 | 0.8754 |
| 0.0001 | 7.0 | 6314 | 1.5118 | 0.7934 | 0.8265 | 0.7813 | 0.8772 |
| 0.0058 | 8.0 | 7216 | 1.8437 | 0.7475 | 0.8019 | 0.7161 | 0.9110 |
| 0.0002 | 9.0 | 8118 | 1.6242 | 0.7874 | 0.8253 | 0.7656 | 0.8950 |
| 0.0037 | 10.0 | 9020 | 1.5455 | 0.8204 | 0.8462 | 0.8141 | 0.8808 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- May 8, 2025
- Updated
- May 8, 2025