|
--- |
|
license: apache-2.0 |
|
base_model: CAMeL-Lab/bert-base-arabic-camelbert-da |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Improved-CAMEL-attempt2 |
|
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. --> |
|
|
|
# Improved-CAMEL-attempt2 |
|
|
|
This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-da](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-da) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7469 |
|
- Accuracy: 0.86 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.07 | 50 | 0.3638 | 0.85 | |
|
| No log | 0.14 | 100 | 0.3945 | 0.79 | |
|
| No log | 0.21 | 150 | 0.3206 | 0.87 | |
|
| No log | 0.27 | 200 | 0.6859 | 0.64 | |
|
| No log | 0.34 | 250 | 0.3078 | 0.84 | |
|
| No log | 0.41 | 300 | 0.4524 | 0.79 | |
|
| No log | 0.48 | 350 | 0.3414 | 0.84 | |
|
| No log | 0.55 | 400 | 0.3479 | 0.85 | |
|
| No log | 0.62 | 450 | 0.3317 | 0.83 | |
|
| 0.3497 | 0.68 | 500 | 0.3214 | 0.85 | |
|
| 0.3497 | 0.75 | 550 | 0.2614 | 0.87 | |
|
| 0.3497 | 0.82 | 600 | 0.4143 | 0.84 | |
|
| 0.3497 | 0.89 | 650 | 0.3211 | 0.88 | |
|
| 0.3497 | 0.96 | 700 | 0.2593 | 0.89 | |
|
| 0.3497 | 1.03 | 750 | 0.7586 | 0.77 | |
|
| 0.3497 | 1.1 | 800 | 0.3171 | 0.91 | |
|
| 0.3497 | 1.16 | 850 | 0.5458 | 0.84 | |
|
| 0.3497 | 1.23 | 900 | 0.7450 | 0.83 | |
|
| 0.3497 | 1.3 | 950 | 0.2748 | 0.86 | |
|
| 0.2194 | 1.37 | 1000 | 0.5666 | 0.81 | |
|
| 0.2194 | 1.44 | 1050 | 0.9014 | 0.82 | |
|
| 0.2194 | 1.51 | 1100 | 0.4580 | 0.86 | |
|
| 0.2194 | 1.58 | 1150 | 0.4560 | 0.87 | |
|
| 0.2194 | 1.64 | 1200 | 0.2445 | 0.9 | |
|
| 0.2194 | 1.71 | 1250 | 0.4808 | 0.87 | |
|
| 0.2194 | 1.78 | 1300 | 0.5491 | 0.86 | |
|
| 0.2194 | 1.85 | 1350 | 0.3435 | 0.87 | |
|
| 0.2194 | 1.92 | 1400 | 0.4169 | 0.87 | |
|
| 0.2194 | 1.99 | 1450 | 0.4190 | 0.86 | |
|
| 0.1739 | 2.05 | 1500 | 0.6567 | 0.87 | |
|
| 0.1739 | 2.12 | 1550 | 0.9203 | 0.84 | |
|
| 0.1739 | 2.19 | 1600 | 0.6931 | 0.85 | |
|
| 0.1739 | 2.26 | 1650 | 0.8531 | 0.83 | |
|
| 0.1739 | 2.33 | 1700 | 0.6863 | 0.87 | |
|
| 0.1739 | 2.4 | 1750 | 0.7469 | 0.86 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.14.1 |
|
|
