AraBERT-finetuned-fnd
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5846
- Macro F1: 0.7751
- Accuracy: 0.7803
- Precision: 0.7740
- Recall: 0.7767
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: 25
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5538 | 1.0 | 1597 | 0.5104 | 0.7183 | 0.7352 | 0.7323 | 0.7142 |
| 0.4689 | 2.0 | 3194 | 0.4849 | 0.7435 | 0.7574 | 0.7551 | 0.7392 |
| 0.3876 | 3.0 | 4791 | 0.4828 | 0.7693 | 0.7747 | 0.7682 | 0.7708 |
| 0.3152 | 4.0 | 6388 | 0.5412 | 0.7702 | 0.7747 | 0.7686 | 0.7729 |
| 0.2627 | 5.0 | 7985 | 0.5846 | 0.7751 | 0.7803 | 0.7740 | 0.7767 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.