---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:457216
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
base_model: aubmindlab/bert-base-arabertv02
widget:
- source_sentence: الناس يسيرون
  sentences:
  - شخصان يصعدان على الدرج
  - الناس يجلسون
  - رجل يجلس ويستمع للمحادثات
- source_sentence: لاعب كرة قدم يرتدي زيًا أحمر وأسود يحمل الرقم 3 وخوذة سوداء يحمل
    الكرة ويحيط به لاعبون معارضون يرتدون زيًا أبيض وأرجواني بيكسفيل.
  sentences:
  - لاعب كرة قدم يحمل كرة
  - الرجل مستعد لالتقاط كرة القدم
  - الكلاب بالخارج
- source_sentence: بعثة لوس أنجلوس هي عيادة مجانية
  sentences:
  - إنها مساعدة ممرضة في بعثة لوس أنجلوس
  - تعمل كطبيبة رئيسة في "لوس أنجلوس ميسيون" عيادة مجانية في حي فقير
  - التوافق مطلوب من الأجهزة أو البرمجيات.
- source_sentence: رجل يرتدي قميصًا بنيًا مخططًا يقف يثني ذراعيه على قمة مبنى على
    سطح منزل.
  sentences:
  - رجل ينظر من نافذة المطبخ
  - شخص على السطح
  - لا يجوز إظهار أي مبلغ من الأصول في الميزانية العمومية للمهمة الفيدرالية
- source_sentence: الحيوانات الأليفة تلعب دور الجدار
  sentences:
  - كلبان يلعبان في منطقة محصورة من الحصى.
  - الكلاب تجري لالتقاط عصا عبر الشارع.
  - يمكن تطوير التكنولوجيا.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
model-index:
- name: SentenceTransformer based on aubmindlab/bert-base-arabertv02
  results:
  - task:
      type: semantic-similarity
      name: Semantic Similarity
    dataset:
      name: arabic nli dev
      type: arabic-nli-dev
    metrics:
    - type: pearson_cosine
      value: 0.5891378532917348
      name: Pearson Cosine
    - type: spearman_cosine
      value: 0.5933477548023721
      name: Spearman Cosine
---

# SentenceTransformer based on aubmindlab/bert-base-arabertv02

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

## Model Details

### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) <!-- at revision 016fb9d6768f522a59c6e0d2d5d5d43a4e1bff60 -->
- **Maximum Sequence Length:** 75 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### Model Sources

- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

### Full Model Architecture

```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```

## Usage

### Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

```bash
pip install -U sentence-transformers
```

Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'الحيوانات الأليفة تلعب دور الجدار',
    'كلبان يلعبان في منطقة محصورة من الحصى.',
    'الكلاب تجري لالتقاط عصا عبر الشارع.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```

<!--
### Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details>
-->

<!--
### Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details>
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

## Evaluation

### Metrics

#### Semantic Similarity

* Dataset: `arabic-nli-dev`
* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

| Metric              | Value      |
|:--------------------|:-----------|
| pearson_cosine      | 0.5891     |
| **spearman_cosine** | **0.5933** |

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Dataset

#### Unnamed Dataset

* Size: 457,216 training samples
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
* Approximate statistics based on the first 1000 samples:
  |         | sentence_0                                                                       | sentence_1                                                                        | sentence_2                                                                       |
  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
  | type    | string                                                                           | string                                                                            | string                                                                           |
  | details | <ul><li>min: 4 tokens</li><li>mean: 12.5 tokens</li><li>max: 66 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 12.33 tokens</li><li>max: 68 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.59 tokens</li><li>max: 33 tokens</li></ul> |
* Samples:
  | sentence_0                                                                                            | sentence_1                                                                   | sentence_2                                                    |
  |:------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:--------------------------------------------------------------|
  | <code>يجلس طفل أحمر الشعر ينظر من خلال السور إلى الماء بينما يلعب الناس على الشاطئ في المسافة.</code> | <code>طفل أحمر الشعر مهتم بالماء والناس يلعبون على الشاطئ في المسافة.</code> | <code>فتى شقراء يراقب القارب مع الناس عليه يبحر بعيدا.</code> |
  | <code>عامل نظافة على وشك التنظيف في محطة القطار</code>                                                | <code>البواب سيقوم بتنظيف محطة القطار</code>                                 | <code>البواب يجلس في محطة القطار</code>                       |
  | <code>رجل يرتدي قميصاً أخضر وبنطال جينز ينحني فوق مرمى الهوكي الأحمر مع ثقب فوقه.</code>              | <code>رجل يرتدي قميصاً أخضر.</code>                                          | <code>امرأة ترتدي قميصاً أخضر.</code>                         |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
  ```json
  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  ```

### Training Hyperparameters
#### Non-Default Hyperparameters

- `eval_strategy`: steps
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `fp16`: True
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin

#### All Hyperparameters
<details><summary>Click to expand</summary>

- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: steps
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 1
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 5e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1
- `num_train_epochs`: 3
- `max_steps`: -1
- `lr_scheduler_type`: linear
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.0
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: False
- `fp16`: True
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: None
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: False
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `tp_size`: 0
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`: 
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `dispatch_batches`: None
- `split_batches`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin

</details>

### Training Logs
| Epoch  | Step  | Training Loss | arabic-nli-dev_spearman_cosine |
|:------:|:-----:|:-------------:|:------------------------------:|
| 0.1400 | 500   | 10.0831       | -                              |
| 0.1999 | 714   | -             | 0.4417                         |
| 0.2800 | 1000  | 5.6335        | -                              |
| 0.3998 | 1428  | -             | 0.5157                         |
| 0.4199 | 1500  | 4.7627        | -                              |
| 0.5599 | 2000  | 4.3656        | -                              |
| 0.5997 | 2142  | -             | 0.5443                         |
| 0.6999 | 2500  | 4.085         | -                              |
| 0.7996 | 2856  | -             | 0.5569                         |
| 0.8399 | 3000  | 3.8314        | -                              |
| 0.9798 | 3500  | 3.5961        | -                              |
| 0.9994 | 3570  | -             | 0.5612                         |
| 1.0    | 3572  | -             | 0.5617                         |
| 1.1198 | 4000  | 3.2502        | -                              |
| 1.1993 | 4284  | -             | 0.5819                         |
| 1.2598 | 4500  | 3.1274        | -                              |
| 1.3992 | 4998  | -             | 0.5848                         |
| 1.3998 | 5000  | 3.0461        | -                              |
| 1.5398 | 5500  | 2.9606        | -                              |
| 1.5991 | 5712  | -             | 0.5930                         |
| 1.6797 | 6000  | 2.9263        | -                              |
| 1.7990 | 6426  | -             | 0.5906                         |
| 1.8197 | 6500  | 2.8313        | -                              |
| 1.9597 | 7000  | 2.7663        | -                              |
| 1.9989 | 7140  | -             | 0.5868                         |
| 2.0    | 7144  | -             | 0.5888                         |
| 2.0997 | 7500  | 2.4814        | -                              |
| 2.1988 | 7854  | -             | 0.5864                         |
| 2.2396 | 8000  | 2.3545        | -                              |
| 2.3796 | 8500  | 2.3052        | -                              |
| 2.3987 | 8568  | -             | 0.5898                         |
| 2.5196 | 9000  | 2.3227        | -                              |
| 2.5985 | 9282  | -             | 0.5924                         |
| 2.6596 | 9500  | 2.3185        | -                              |
| 2.7984 | 9996  | -             | 0.5933                         |
| 2.7996 | 10000 | 2.2571        | -                              |
| 2.9395 | 10500 | 2.2335        | -                              |
| 2.9983 | 10710 | -             | 0.5925                         |
| 3.0    | 10716 | -             | 0.5933                         |


### Framework Versions
- Python: 3.11.11
- Sentence Transformers: 4.1.0
- Transformers: 4.50.0.dev0
- PyTorch: 2.6.0+cu124
- Accelerate: 1.4.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0

## Citation

### BibTeX

#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}
```

#### MatryoshkaLoss
```bibtex
@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}
```

#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->