Downloads · 30 days
3
15% of all-time downloads
moumi_ner_combined
mouminach/moumi_ner_combined
moumi_ner_combined is a token classification model from mouminach. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
20
Public
Parameters
135M
38.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors538 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Apr 29, 2025
- Updated
- Jun 12, 2025
- SHA
- 35ac0ead
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. -->
moumi_ner_combined
This model is a fine-tuned version of aubmindlab/bert-base-arabertv2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0821
- Accuracy: 0.9856
- F1: 0.9043
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0747 | 1.0 | 1774 | 0.0660 | 0.9788 | 0.8597 |
| 0.0484 | 2.0 | 3548 | 0.0555 | 0.9823 | 0.8785 |
| 0.0333 | 3.0 | 5322 | 0.0578 | 0.9845 | 0.8960 |
| 0.0247 | 4.0 | 7096 | 0.0611 | 0.9843 | 0.8979 |
| 0.0151 | 5.0 | 8870 | 0.0674 | 0.9844 | 0.8989 |
| 0.0105 | 6.0 | 10644 | 0.0712 | 0.9848 | 0.8993 |
| 0.0088 | 7.0 | 12418 | 0.0745 | 0.9856 | 0.9043 |
| 0.0064 | 8.0 | 14192 | 0.0774 | 0.9853 | 0.9023 |
| 0.0051 | 9.0 | 15966 | 0.0806 | 0.9857 | 0.9037 |
| 0.0038 | 10.0 | 17740 | 0.0821 | 0.9856 | 0.9043 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Apr 29, 2025
- Updated
- Jun 12, 2025