Downloads · 30 days
9
14% of all-time downloads
arabic-ner-camelbert-wikiann
CIAZIZ/arabic-ner-camelbert-wikiann
arabic-ner-camelbert-wikiann is a token classification model from CIAZIZ. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
63
Public
Repo size
868 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin434 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025
- SHA
- b3641a35
Try a prompt
Base models
Spaces
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. -->
arabic-ner-camelbert-wikiann
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-mix on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2629
- Precision: 0.8994
- Recall: 0.9036
- F1: 0.9015
- Accuracy: 0.9551
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: 3e-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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2052 | 1.0 | 1250 | 0.2086 | 0.8600 | 0.8614 | 0.8607 | 0.9410 |
| 0.13 | 2.0 | 2500 | 0.1989 | 0.8829 | 0.8839 | 0.8834 | 0.9490 |
| 0.0904 | 3.0 | 3750 | 0.1971 | 0.8996 | 0.8958 | 0.8977 | 0.9543 |
| 0.0326 | 4.0 | 5000 | 0.2437 | 0.8897 | 0.9038 | 0.8967 | 0.9544 |
| 0.0245 | 5.0 | 6250 | 0.2629 | 0.8994 | 0.9036 | 0.9015 | 0.9551 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025