Downloads · 30 days
8
8% of all-time downloads
luganda-ner-v6
e4gl33y3/luganda-ner-v6
luganda-ner-v6 is a token classification model from e4gl33y3. 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
100
Public
Parameters
559M
90 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Apr 10, 2024
- Updated
- Apr 18, 2024
- SHA
- 5f6b3357
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. -->
luganda-ner-v6
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2811
- Precision: 0.7787
- Recall: 0.7703
- F1: 0.7745
- Accuracy: 0.9420
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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 261 | 0.6199 | 0.5211 | 0.0665 | 0.1179 | 0.8387 |
| 0.6777 | 2.0 | 522 | 0.3910 | 0.5614 | 0.5339 | 0.5473 | 0.8999 |
| 0.6777 | 3.0 | 783 | 0.3134 | 0.7396 | 0.5876 | 0.6549 | 0.9174 |
| 0.2838 | 4.0 | 1044 | 0.2843 | 0.7064 | 0.6998 | 0.7031 | 0.9241 |
| 0.2838 | 5.0 | 1305 | 0.2648 | 0.7800 | 0.6931 | 0.7340 | 0.9353 |
| 0.1659 | 6.0 | 1566 | 0.2841 | 0.7456 | 0.7461 | 0.7459 | 0.9310 |
| 0.1659 | 7.0 | 1827 | 0.2663 | 0.7737 | 0.7461 | 0.7597 | 0.9409 |
| 0.105 | 8.0 | 2088 | 0.2718 | 0.7756 | 0.7542 | 0.7647 | 0.9399 |
| 0.105 | 9.0 | 2349 | 0.2896 | 0.7623 | 0.7602 | 0.7613 | 0.9360 |
| 0.079 | 10.0 | 2610 | 0.2811 | 0.7787 | 0.7703 | 0.7745 | 0.9420 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Apr 10, 2024
- Updated
- Apr 18, 2024