metadata
license: apache-2.0
base_model: CAMeL-Lab/bert-base-arabic-camelbert-msa-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: hadith-finetuned-ner2
results: []
hadith-finetuned-ner2
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-msa-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1591
- Precision: 0.8899
- Recall: 0.9602
- F1: 0.9237
- Accuracy: 0.9452
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5252 | 1.0 | 468 | 0.4358 | 0.7801 | 0.7819 | 0.7810 | 0.8478 |
| 0.228 | 2.0 | 937 | 0.2789 | 0.8225 | 0.9172 | 0.8673 | 0.9055 |
| 0.1561 | 3.0 | 1405 | 0.2077 | 0.8648 | 0.9395 | 0.9006 | 0.9301 |
| 0.1759 | 4.0 | 1874 | 0.1692 | 0.8914 | 0.9506 | 0.9201 | 0.9434 |
| 0.1496 | 4.99 | 2340 | 0.1591 | 0.8899 | 0.9602 | 0.9237 | 0.9452 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1