Downloads · 30 days
8
2% of all-time downloads
deberta-v3-small-finetuned-ner-2048
marksusol/deberta-v3-small-finetuned-ner-2048
deberta-v3-small-finetuned-ner-2048 is a token classification model from marksusol. Use it when you need labels on individual words, such as names. 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
417
Public
Parameters
141M
8.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors565 MB · 98%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- deberta-v2
- Access
- Public
- Created
- Apr 16, 2024
- Updated
- Apr 17, 2024
- SHA
- 2740ee14
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-small-finetuned-ner-2048
This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0036
- Recall: 0.9920
- Precision: 0.9866
- Fbeta Score: 0.9918
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Recall | Precision | Fbeta Score |
|---|---|---|---|---|---|---|
| 0.0085 | 1.0 | 3186 | 0.0058 | 0.9786 | 0.9693 | 0.9782 |
| 0.0032 | 2.0 | 6373 | 0.0036 | 0.9869 | 0.9764 | 0.9865 |
| 0.004 | 3.0 | 9559 | 0.0037 | 0.9791 | 0.9892 | 0.9795 |
| 0.0014 | 4.0 | 12746 | 0.0035 | 0.9908 | 0.9817 | 0.9905 |
| 0.0019 | 5.0 | 15932 | 0.0038 | 0.9903 | 0.9806 | 0.9899 |
| 0.0022 | 6.0 | 19119 | 0.0032 | 0.9929 | 0.9861 | 0.9927 |
| 0.0005 | 7.0 | 22305 | 0.0031 | 0.9906 | 0.9894 | 0.9905 |
| 0.0003 | 8.0 | 25492 | 0.0033 | 0.9915 | 0.9855 | 0.9913 |
| 0.0001 | 9.0 | 28678 | 0.0036 | 0.9920 | 0.9866 | 0.9918 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- deberta-v2
- License
- mit
- Created
- Apr 16, 2024
- Updated
- Apr 17, 2024