---
language:
- ar
library_name: sentence-transformers
tags:
- mteb
- transformers
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:557850
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
model-index:
- name: Omartificial-Intelligence-Space/Arabert-all-nli-triplet-Matryoshka
results:
- dataset:
config: default
name: MTEB BIOSSES (default)
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
split: test
type: mteb/biosses-sts
metrics:
- type: cosine_pearson
value: 67.88078975738149
- type: cosine_spearman
value: 67.36900492799694
- type: euclidean_pearson
value: 66.00402957388015
- type: euclidean_spearman
value: 65.70270189991112
- type: main_score
value: 67.36900492799694
- type: manhattan_pearson
value: 66.54937895501651
- type: manhattan_spearman
value: 66.12198856207587
task:
type: STS
- dataset:
config: default
name: MTEB SICK-R (default)
revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
split: test
type: mteb/sickr-sts
metrics:
- type: cosine_pearson
value: 62.931439439697044
- type: cosine_spearman
value: 57.64441663261227
- type: euclidean_pearson
value: 61.119408834167835
- type: euclidean_spearman
value: 57.42332323654558
- type: main_score
value: 57.64441663261227
- type: manhattan_pearson
value: 60.692516462749204
- type: manhattan_spearman
value: 56.99349446063643
task:
type: STS
- dataset:
config: default
name: MTEB STS12 (default)
revision: a0d554a64d88156834ff5ae9920b964011b16384
split: test
type: mteb/sts12-sts
metrics:
- type: cosine_pearson
value: 70.42631404785132
- type: cosine_spearman
value: 69.67060431422327
- type: euclidean_pearson
value: 68.70261457119209
- type: euclidean_spearman
value: 68.99597672902992
- type: main_score
value: 69.67060431422327
- type: manhattan_pearson
value: 67.99048393745159
- type: manhattan_spearman
value: 68.1853179140009
task:
type: STS
- dataset:
config: default
name: MTEB STS13 (default)
revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
split: test
type: mteb/sts13-sts
metrics:
- type: cosine_pearson
value: 49.46916157874787
- type: cosine_spearman
value: 51.95037157769884
- type: euclidean_pearson
value: 55.17336596392549
- type: euclidean_spearman
value: 54.312304378478835
- type: main_score
value: 51.95037157769884
- type: manhattan_pearson
value: 55.09060773902408
- type: manhattan_spearman
value: 53.96813218977611
task:
type: STS
- dataset:
config: default
name: MTEB STS14 (default)
revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
split: test
type: mteb/sts14-sts
metrics:
- type: cosine_pearson
value: 54.37699141667456
- type: cosine_spearman
value: 57.36607721958864
- type: euclidean_pearson
value: 57.98000825695592
- type: euclidean_spearman
value: 59.08844527739818
- type: main_score
value: 57.36607721958864
- type: manhattan_pearson
value: 57.588062173142106
- type: manhattan_spearman
value: 58.35590953779109
task:
type: STS
- dataset:
config: default
name: MTEB STS15 (default)
revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
split: test
type: mteb/sts15-sts
metrics:
- type: cosine_pearson
value: 67.37948361289261
- type: cosine_spearman
value: 70.0994395240558
- type: euclidean_pearson
value: 70.28341277052768
- type: euclidean_spearman
value: 70.11050982217422
- type: main_score
value: 70.0994395240558
- type: manhattan_pearson
value: 70.66000566140171
- type: manhattan_spearman
value: 70.41742785288693
task:
type: STS
- dataset:
config: default
name: MTEB STS16 (default)
revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
split: test
type: mteb/sts16-sts
metrics:
- type: cosine_pearson
value: 61.559501698409434
- type: cosine_spearman
value: 65.04903130808405
- type: euclidean_pearson
value: 63.92021058086694
- type: euclidean_spearman
value: 64.22673046991633
- type: main_score
value: 65.04903130808405
- type: manhattan_pearson
value: 63.958100692077956
- type: manhattan_spearman
value: 64.15057001708075
task:
type: STS
- dataset:
config: ar-ar
name: MTEB STS17 (ar-ar)
revision: faeb762787bd10488a50c8b5be4a3b82e411949c
split: test
type: mteb/sts17-crosslingual-sts
metrics:
- type: cosine_pearson
value: 82.35377320218275
- type: cosine_spearman
value: 83.15514468203664
- type: euclidean_pearson
value: 80.56116685008965
- type: euclidean_spearman
value: 82.38252301503367
- type: main_score
value: 83.15514468203664
- type: manhattan_pearson
value: 80.74794586574093
- type: manhattan_spearman
value: 82.54224799581789
task:
type: STS
- dataset:
config: ar
name: MTEB STS22 (ar)
revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
split: test
type: mteb/sts22-crosslingual-sts
metrics:
- type: cosine_pearson
value: 48.22154847597003
- type: cosine_spearman
value: 58.29235719729918
- type: euclidean_pearson
value: 51.54481297728728
- type: euclidean_spearman
value: 58.990627664376674
- type: main_score
value: 58.29235719729918
- type: manhattan_pearson
value: 52.195039627338126
- type: manhattan_spearman
value: 59.12018922641005
task:
type: STS
- dataset:
config: default
name: MTEB STSBenchmark (default)
revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
split: test
type: mteb/stsbenchmark-sts
metrics:
- type: cosine_pearson
value: 59.50286436994106
- type: cosine_spearman
value: 61.592426810014366
- type: euclidean_pearson
value: 63.268627193788916
- type: euclidean_spearman
value: 63.16239630067321
- type: main_score
value: 61.592426810014366
- type: manhattan_pearson
value: 62.95949714767757
- type: manhattan_spearman
value: 62.687737378385364
task:
type: STS
- dataset:
config: default
name: MTEB SummEval (default)
revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
split: test
type: mteb/summeval
metrics:
- type: cosine_pearson
value: 31.1427099547469
- type: cosine_spearman
value: 31.32880594576111
- type: dot_pearson
value: 25.98395652985614
- type: dot_spearman
value: 25.30831374828529
- type: main_score
value: 31.32880594576111
- type: pearson
value: 31.1427099547469
- type: spearman
value: 31.32880594576111
task:
type: Summarization
- name: SentenceTransformer based on aubmindlab/bert-base-arabertv02
results:
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 768
type: sts-test-768
metrics:
- type: pearson_cosine
value: 0.5949906740977448
name: Pearson Cosine
- type: spearman_cosine
value: 0.6159750250469712
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6295622269205102
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6269654283099967
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6326526932327604
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6317081341785673
name: Spearman Euclidean
- type: pearson_dot
value: 0.42816790752358297
name: Pearson Dot
- type: spearman_dot
value: 0.4295282086669423
name: Spearman Dot
- type: pearson_max
value: 0.6326526932327604
name: Pearson Max
- type: spearman_max
value: 0.6317081341785673
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 512
type: sts-test-512
metrics:
- type: pearson_cosine
value: 0.5846223235167534
name: Pearson Cosine
- type: spearman_cosine
value: 0.6064092420664184
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6287774004727389
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6263546541183983
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.631267664308041
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6301778108727977
name: Spearman Euclidean
- type: pearson_dot
value: 0.3788565672017437
name: Pearson Dot
- type: spearman_dot
value: 0.37680551461721923
name: Spearman Dot
- type: pearson_max
value: 0.631267664308041
name: Pearson Max
- type: spearman_max
value: 0.6301778108727977
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 256
type: sts-test-256
metrics:
- type: pearson_cosine
value: 0.5778623383989389
name: Pearson Cosine
- type: spearman_cosine
value: 0.5959667709300495
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6242980982402613
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6217473192873829
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6237908608463304
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6215304658549996
name: Spearman Euclidean
- type: pearson_dot
value: 0.35968442092444003
name: Pearson Dot
- type: spearman_dot
value: 0.35304547874806785
name: Spearman Dot
- type: pearson_max
value: 0.6242980982402613
name: Pearson Max
- type: spearman_max
value: 0.6217473192873829
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 128
type: sts-test-128
metrics:
- type: pearson_cosine
value: 0.5830782075122916
name: Pearson Cosine
- type: spearman_cosine
value: 0.6022044167653756
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6151866925343435
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.6121950064533626
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6162225316000448
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.615301209345362
name: Spearman Euclidean
- type: pearson_dot
value: 0.40438461342780957
name: Pearson Dot
- type: spearman_dot
value: 0.40153111017443666
name: Spearman Dot
- type: pearson_max
value: 0.6162225316000448
name: Pearson Max
- type: spearman_max
value: 0.615301209345362
name: Spearman Max
- task:
type: semantic-similarity
name: Semantic Similarity
dataset:
name: sts test 64
type: sts-test-64
metrics:
- type: pearson_cosine
value: 0.5724838823862283
name: Pearson Cosine
- type: spearman_cosine
value: 0.5914127847098
name: Spearman Cosine
- type: pearson_manhattan
value: 0.6023812283389073
name: Pearson Manhattan
- type: spearman_manhattan
value: 0.5967205030284914
name: Spearman Manhattan
- type: pearson_euclidean
value: 0.6069294574719372
name: Pearson Euclidean
- type: spearman_euclidean
value: 0.6041440553344074
name: Spearman Euclidean
- type: pearson_dot
value: 0.36315938245739166
name: Pearson Dot
- type: spearman_dot
value: 0.358512645020771
name: Spearman Dot
- type: pearson_max
value: 0.6069294574719372
name: Pearson Max
- type: spearman_max
value: 0.6041440553344074
name: Spearman Max
base_model: aubmindlab/bert-base-arabertv02
datasets:
- Omartificial-Intelligence-Space/Arabic-NLi-Triplet
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
widget:
- source_sentence: ذكر متوازن بعناية يقف على قدم واحدة بالقرب من منطقة شاطئ المحيط النظيفة
sentences:
- رجل يقدم عرضاً
- هناك رجل بالخارج قرب الشاطئ
- رجل يجلس على أريكه
- source_sentence: رجل يقفز إلى سريره القذر
sentences:
- السرير قذر.
- رجل يضحك أثناء غسيل الملابس
- الرجل على القمر
- source_sentence: الفتيات بالخارج
sentences:
- امرأة تلف الخيط إلى كرات بجانب كومة من الكرات
- فتيان يركبان في جولة متعة
- >-
ثلاث فتيات يقفون سوية في غرفة واحدة تستمع وواحدة تكتب على الحائط والثالثة
تتحدث إليهن
- source_sentence: الرجل يرتدي قميصاً أزرق.
sentences:
- >-
رجل يرتدي قميصاً أزرق يميل إلى الجدار بجانب الطريق مع شاحنة زرقاء وسيارة
حمراء مع الماء في الخلفية.
- كتاب القصص مفتوح
- رجل يرتدي قميص أسود يعزف على الجيتار.
- source_sentence: يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شابة.
sentences:
- ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه
- رجل يستلقي على وجهه على مقعد في الحديقة.
- الشاب نائم بينما الأم تقود ابنتها إلى الحديقة
pipeline_tag: sentence-similarity
license: apache-2.0
---
# Arabert All NLI Triplet Matryoshka Model
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on the Omartificial-Intelligence-Space/arabic-n_li-triplet dataset. 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)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- Omartificial-Intelligence-Space/arabic-n_li-triplet
### 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': 512, '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("Omartificial-Intelligence-Space/Arabic-arabert-all-nli-triplet")
# Run inference
sentences = [
'يجلس شاب ذو شعر أشقر على الحائط يقرأ جريدة بينما تمر امرأة وفتاة شابة.',
'ذكر شاب ينظر إلى جريدة بينما تمر إمرأتان بجانبه',
'الشاب نائم بينما الأم تقود ابنتها إلى الحديقة',
]
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]
```
## Evaluation
### Metrics
#### Semantic Similarity
* Dataset: `sts-test-768`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:----------|
| pearson_cosine | 0.595 |
| **spearman_cosine** | **0.616** |
| pearson_manhattan | 0.6296 |
| spearman_manhattan | 0.627 |
| pearson_euclidean | 0.6327 |
| spearman_euclidean | 0.6317 |
| pearson_dot | 0.4282 |
| spearman_dot | 0.4295 |
| pearson_max | 0.6327 |
| spearman_max | 0.6317 |
#### Semantic Similarity
* Dataset: `sts-test-512`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.5846 |
| **spearman_cosine** | **0.6064** |
| pearson_manhattan | 0.6288 |
| spearman_manhattan | 0.6264 |
| pearson_euclidean | 0.6313 |
| spearman_euclidean | 0.6302 |
| pearson_dot | 0.3789 |
| spearman_dot | 0.3768 |
| pearson_max | 0.6313 |
| spearman_max | 0.6302 |
#### Semantic Similarity
* Dataset: `sts-test-256`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:----------|
| pearson_cosine | 0.5779 |
| **spearman_cosine** | **0.596** |
| pearson_manhattan | 0.6243 |
| spearman_manhattan | 0.6217 |
| pearson_euclidean | 0.6238 |
| spearman_euclidean | 0.6215 |
| pearson_dot | 0.3597 |
| spearman_dot | 0.353 |
| pearson_max | 0.6243 |
| spearman_max | 0.6217 |
#### Semantic Similarity
* Dataset: `sts-test-128`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.5831 |
| **spearman_cosine** | **0.6022** |
| pearson_manhattan | 0.6152 |
| spearman_manhattan | 0.6122 |
| pearson_euclidean | 0.6162 |
| spearman_euclidean | 0.6153 |
| pearson_dot | 0.4044 |
| spearman_dot | 0.4015 |
| pearson_max | 0.6162 |
| spearman_max | 0.6153 |
#### Semantic Similarity
* Dataset: `sts-test-64`
* Evaluated with [EmbeddingSimilarityEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| pearson_cosine | 0.5725 |
| **spearman_cosine** | **0.5914** |
| pearson_manhattan | 0.6024 |
| spearman_manhattan | 0.5967 |
| pearson_euclidean | 0.6069 |
| spearman_euclidean | 0.6041 |
| pearson_dot | 0.3632 |
| spearman_dot | 0.3585 |
| pearson_max | 0.6069 |
| spearman_max | 0.6041 |
## Training Details
### Training Dataset
#### Omartificial-Intelligence-Space/arabic-n_li-triplet
* Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
* Size: 557,850 training samples
* Columns: anchor
, positive
, and negative
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
| type | string | string | string |
| details |
شخص على حصان يقفز فوق طائرة معطلة
| شخص في الهواء الطلق، على حصان.
| شخص في مطعم، يطلب عجة.
|
| أطفال يبتسمون و يلوحون للكاميرا
| هناك أطفال حاضرون
| الاطفال يتجهمون
|
| صبي يقفز على لوح التزلج في منتصف الجسر الأحمر.
| الفتى يقوم بخدعة التزلج
| الصبي يتزلج على الرصيف
|
* Loss: [MatryoshkaLoss
](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
}
```
### Evaluation Dataset
#### Omartificial-Intelligence-Space/arabic-n_li-triplet
* Dataset: Omartificial-Intelligence-Space/arabic-n_li-triplet
* Size: 6,584 evaluation samples
* Columns: anchor
, positive
, and negative
* Approximate statistics based on the first 1000 samples:
| | anchor | positive | negative |
|:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
| type | string | string | string |
| details | امرأتان يتعانقان بينما يحملان حزمة
| إمرأتان يحملان حزمة
| الرجال يتشاجرون خارج مطعم
|
| طفلين صغيرين يرتديان قميصاً أزرق، أحدهما يرتدي الرقم 9 والآخر يرتدي الرقم 2 يقفان على خطوات خشبية في الحمام ويغسلان أيديهما في المغسلة.
| طفلين يرتديان قميصاً مرقماً يغسلون أيديهم
| طفلين يرتديان سترة يذهبان إلى المدرسة
|
| رجل يبيع الدونات لعميل خلال معرض عالمي أقيم في مدينة أنجليس
| رجل يبيع الدونات لعميل
| امرأة تشرب قهوتها في مقهى صغير
|
* Loss: [MatryoshkaLoss
](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
- `per_device_train_batch_size`: 64
- `per_device_eval_batch_size`: 64
- `num_train_epochs`: 1
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters