---
library_name: transformers
license: apache-2.0
base_model: CAMeL-Lab/bert-base-arabic-camelbert-mix
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: arabertv2-sentiment
  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. -->

# arabertv2-sentiment

This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-mix](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-mix) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4552
- Accuracy: 0.8825
- Precision: 0.8864
- Recall: 0.8825
- F1: 0.8840

## 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: 32
- eval_batch_size: 32
- seed: 1234
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.2713        | 1.0   | 38   | 0.4964          | 0.8075   | 0.8601    | 0.8075 | 0.8181 |
| 0.1571        | 2.0   | 76   | 0.3297          | 0.865    | 0.8904    | 0.865  | 0.8699 |
| 0.1626        | 3.0   | 114  | 0.3481          | 0.885    | 0.8984    | 0.885  | 0.8883 |
| 0.0892        | 4.0   | 152  | 0.5528          | 0.8825   | 0.8799    | 0.8825 | 0.8801 |
| 0.0119        | 5.0   | 190  | 0.4552          | 0.8825   | 0.8864    | 0.8825 | 0.8840 |


### Framework versions

- Transformers 4.49.0
- Pytorch 2.1.1+cu121
- Datasets 3.3.2
- Tokenizers 0.21.1