|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: arabic-dialect-model |
|
results: [] |
|
--- |
|
|
|
<!-- 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-dialect-model |
|
|
|
This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-msa](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-msa) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7129 |
|
- Accuracy: 0.1778 |
|
- F1: 0.1297 |
|
- Precision: 0.1777 |
|
- Recall: 0.1778 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 3.0984 | 1.0 | 16 | 3.0297 | 0.0444 | 0.05 | 0.0593 | 0.0444 | |
|
| 2.9882 | 2.0 | 32 | 2.9796 | 0.0889 | 0.0660 | 0.0526 | 0.0889 | |
|
| 2.904 | 3.0 | 48 | 2.9029 | 0.1111 | 0.0577 | 0.0399 | 0.1111 | |
|
| 2.7871 | 4.0 | 64 | 2.8040 | 0.1778 | 0.1057 | 0.1370 | 0.1778 | |
|
| 2.6578 | 5.0 | 80 | 2.7129 | 0.1778 | 0.1297 | 0.1777 | 0.1778 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.2 |
|
- Pytorch 2.0.1+cpu |
|
- Datasets 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
