Downloads · 30 days
7
14% of all-time downloads
hadith-finetuned-ner7
AhmedTaha012/hadith-finetuned-ner7
hadith-finetuned-ner7 is a token classification model from AhmedTaha012. 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
49
Public
Parameters
11.5M
368 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors46 MB · 96%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Nov 17, 2023
- Updated
- Nov 17, 2023
- SHA
- f311e1b5
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. -->
hadith-finetuned-ner7
This model is a fine-tuned version of asafaya/bert-mini-arabic on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4176
- Precision: 0.7766
- Recall: 0.8655
- F1: 0.8186
- Accuracy: 0.8686
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5731 | 1.0 | 468 | 0.7481 | 0.6098 | 0.6000 | 0.6049 | 0.7053 |
| 0.5834 | 2.0 | 937 | 0.6664 | 0.6260 | 0.8033 | 0.7036 | 0.7561 |
| 0.5302 | 3.0 | 1405 | 0.5467 | 0.7129 | 0.8154 | 0.7607 | 0.8199 |
| 0.5547 | 4.0 | 1874 | 0.4914 | 0.7503 | 0.8325 | 0.7892 | 0.8460 |
| 0.4274 | 5.0 | 2342 | 0.4517 | 0.7666 | 0.8459 | 0.8043 | 0.8587 |
| 0.3865 | 6.0 | 2811 | 0.4496 | 0.7543 | 0.8640 | 0.8055 | 0.8575 |
| 0.4777 | 7.0 | 3279 | 0.4187 | 0.7780 | 0.8613 | 0.8175 | 0.8683 |
| 0.3952 | 7.99 | 3744 | 0.4176 | 0.7766 | 0.8655 | 0.8186 | 0.8686 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Nov 17, 2023
- Updated
- Nov 17, 2023