Downloads · 30 days
7
3% of all-time downloads
deberta-finetuned-ner-microsoft-disaster
ML-GOD/deberta-finetuned-ner-microsoft-disaster
deberta-finetuned-ner-microsoft-disaster is a token classification model from ML-GOD. 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
223
Public
Parameters
139M
9.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors555 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- deberta
- Access
- Public
- Created
- Jul 24, 2024
- Updated
- Jul 24, 2024
- SHA
- 9c53c20a
Try a prompt
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-ner-microsoft-disaster
This model is a fine-tuned version of ML-GOD/deberta-finetuned-ner-microsoft-disaster on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1757
- Precision: 0.9219
- Recall: 0.9294
- F1: 0.9257
- Accuracy: 0.9797
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.024 | 1.0 | 1799 | 0.1107 | 0.9149 | 0.9263 | 0.9206 | 0.9790 |
| 0.0201 | 2.0 | 3598 | 0.1197 | 0.9154 | 0.9225 | 0.9190 | 0.9782 |
| 0.014 | 3.0 | 5397 | 0.1249 | 0.9190 | 0.9279 | 0.9235 | 0.9794 |
| 0.0089 | 4.0 | 7196 | 0.1327 | 0.9151 | 0.9221 | 0.9186 | 0.9781 |
| 0.0057 | 5.0 | 8995 | 0.1432 | 0.9117 | 0.9268 | 0.9192 | 0.9789 |
| 0.0049 | 6.0 | 10794 | 0.1610 | 0.9164 | 0.9240 | 0.9202 | 0.9781 |
| 0.0031 | 7.0 | 12593 | 0.1740 | 0.9197 | 0.9273 | 0.9235 | 0.9791 |
| 0.0028 | 8.0 | 14392 | 0.1701 | 0.9222 | 0.9288 | 0.9255 | 0.9797 |
| 0.0022 | 9.0 | 16191 | 0.1750 | 0.9247 | 0.9290 | 0.9268 | 0.9799 |
| 0.0009 | 10.0 | 17990 | 0.1757 | 0.9219 | 0.9294 | 0.9257 | 0.9797 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- deberta
- License
- mit
- Created
- Jul 24, 2024
- Updated
- Jul 24, 2024