metadata

inference: false
language:
  - ar
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:557850
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
  - mteb
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
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
model-index:
  - name: Omartificial-Intelligence-Space/Arabic-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: 81.20578037912223
          - type: cosine_spearman
            value: 77.43670420687278
          - type: euclidean_pearson
            value: 74.60444698819703
          - type: euclidean_spearman
            value: 72.25767053642666
          - type: main_score
            value: 77.43670420687278
          - type: manhattan_pearson
            value: 73.86951335383257
          - type: manhattan_spearman
            value: 71.41608509527123
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB SICK-R (default)
          revision: 20a6d6f312dd54037fe07a32d58e5e168867909d
          split: test
          type: mteb/sickr-sts
        metrics:
          - type: cosine_pearson
            value: 83.11155556919923
          - type: cosine_spearman
            value: 79.39435627520159
          - type: euclidean_pearson
            value: 81.05225024180342
          - type: euclidean_spearman
            value: 79.09926890001618
          - type: main_score
            value: 79.39435627520159
          - type: manhattan_pearson
            value: 80.74351302609706
          - type: manhattan_spearman
            value: 78.826254748334
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS12 (default)
          revision: a0d554a64d88156834ff5ae9920b964011b16384
          split: test
          type: mteb/sts12-sts
        metrics:
          - type: cosine_pearson
            value: 85.10074960888633
          - type: cosine_spearman
            value: 78.93043293576132
          - type: euclidean_pearson
            value: 84.1168219787408
          - type: euclidean_spearman
            value: 78.44739559202252
          - type: main_score
            value: 78.93043293576132
          - type: manhattan_pearson
            value: 83.79447841594396
          - type: manhattan_spearman
            value: 77.94028171700384
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS13 (default)
          revision: 7e90230a92c190f1bf69ae9002b8cea547a64cca
          split: test
          type: mteb/sts13-sts
        metrics:
          - type: cosine_pearson
            value: 81.34459901517775
          - type: cosine_spearman
            value: 82.73032633919925
          - type: euclidean_pearson
            value: 82.83546499367434
          - type: euclidean_spearman
            value: 83.29701673615389
          - type: main_score
            value: 82.73032633919925
          - type: manhattan_pearson
            value: 82.63480502797324
          - type: manhattan_spearman
            value: 83.05016589615636
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS14 (default)
          revision: 6031580fec1f6af667f0bd2da0a551cf4f0b2375
          split: test
          type: mteb/sts14-sts
        metrics:
          - type: cosine_pearson
            value: 82.53179983763488
          - type: cosine_spearman
            value: 81.64974497557361
          - type: euclidean_pearson
            value: 83.03981070806898
          - type: euclidean_spearman
            value: 82.65556168300631
          - type: main_score
            value: 81.64974497557361
          - type: manhattan_pearson
            value: 82.83722360191446
          - type: manhattan_spearman
            value: 82.4164264119
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS15 (default)
          revision: ae752c7c21bf194d8b67fd573edf7ae58183cbe3
          split: test
          type: mteb/sts15-sts
        metrics:
          - type: cosine_pearson
            value: 86.5684162475647
          - type: cosine_spearman
            value: 87.62163215009723
          - type: euclidean_pearson
            value: 87.3068288651339
          - type: euclidean_spearman
            value: 88.03508640722863
          - type: main_score
            value: 87.62163215009723
          - type: manhattan_pearson
            value: 87.21818681800193
          - type: manhattan_spearman
            value: 87.94690511382603
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STS16 (default)
          revision: 4d8694f8f0e0100860b497b999b3dbed754a0513
          split: test
          type: mteb/sts16-sts
        metrics:
          - type: cosine_pearson
            value: 81.70518105237446
          - type: cosine_spearman
            value: 83.66083698795428
          - type: euclidean_pearson
            value: 82.80400684544435
          - type: euclidean_spearman
            value: 83.39926895275799
          - type: main_score
            value: 83.66083698795428
          - type: manhattan_pearson
            value: 82.44430538731845
          - type: manhattan_spearman
            value: 82.99600783826028
        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: 82.23229967696153
          - type: cosine_spearman
            value: 82.40039006538706
          - type: euclidean_pearson
            value: 79.21322872573518
          - type: euclidean_spearman
            value: 79.14230529579783
          - type: main_score
            value: 82.40039006538706
          - type: manhattan_pearson
            value: 79.1476348987964
          - type: manhattan_spearman
            value: 78.82381660638143
        task:
          type: STS
      - dataset:
          config: ar
          name: MTEB STS22 (ar)
          revision: de9d86b3b84231dc21f76c7b7af1f28e2f57f6e3
          split: test
          type: mteb/sts22-crosslingual-sts
        metrics:
          - type: cosine_pearson
            value: 45.95767124518871
          - type: cosine_spearman
            value: 51.37922888872568
          - type: euclidean_pearson
            value: 45.519471121310126
          - type: euclidean_spearman
            value: 51.45605803385654
          - type: main_score
            value: 51.37922888872568
          - type: manhattan_pearson
            value: 45.98761117909666
          - type: manhattan_spearman
            value: 51.48451973989366
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB STSBenchmark (default)
          revision: b0fddb56ed78048fa8b90373c8a3cfc37b684831
          split: test
          type: mteb/stsbenchmark-sts
        metrics:
          - type: cosine_pearson
            value: 85.38916827757183
          - type: cosine_spearman
            value: 86.16303183485594
          - type: euclidean_pearson
            value: 85.16406897245115
          - type: euclidean_spearman
            value: 85.40364087457081
          - type: main_score
            value: 86.16303183485594
          - type: manhattan_pearson
            value: 84.96853193915084
          - type: manhattan_spearman
            value: 85.13238442843544
        task:
          type: STS
      - dataset:
          config: default
          name: MTEB SummEval (default)
          revision: cda12ad7615edc362dbf25a00fdd61d3b1eaf93c
          split: test
          type: mteb/summeval
        metrics:
          - type: cosine_pearson
            value: 30.077426987171158
          - type: cosine_spearman
            value: 30.163682020271608
          - type: dot_pearson
            value: 27.31125295906803
          - type: dot_spearman
            value: 29.138235153208193
          - type: main_score
            value: 30.163682020271608
          - type: pearson
            value: 30.077426987171158
          - type: spearman
            value: 30.163682020271608
        task:
          type: Summarization
  - name: >-
      SentenceTransformer based on
      sentence-transformers/paraphrase-multilingual-mpnet-base-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.8538831619509135
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.861625750018802
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8496745674597512
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8513333417508545
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8516261261374778
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8540549341060195
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7281308266536204
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7230282720855726
            name: Spearman Dot
          - type: pearson_max
            value: 0.8538831619509135
            name: Pearson Max
          - type: spearman_max
            value: 0.861625750018802
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.8542379189261009
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8609329396560859
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8486657899695456
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8512120732504748
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8505249483849495
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8538738365440234
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7075618032859148
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7028728329509918
            name: Spearman Dot
          - type: pearson_max
            value: 0.8542379189261009
            name: Pearson Max
          - type: spearman_max
            value: 0.8609329396560859
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.8486308733045101
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8578681811996274
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8404506123980291
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.845565163232125
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8414758099131773
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8471566121478254
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6668664182302968
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6651222481800894
            name: Spearman Dot
          - type: pearson_max
            value: 0.8486308733045101
            name: Pearson Max
          - type: spearman_max
            value: 0.8578681811996274
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.8389761445410956
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8499312736457453
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8287388421834582
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8353046807483782
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8297699263897746
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8371843253238523
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5855876200722326
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5834920267418124
            name: Spearman Dot
          - type: pearson_max
            value: 0.8389761445410956
            name: Pearson Max
          - type: spearman_max
            value: 0.8499312736457453
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.8290685425698586
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8429054799136109
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8100968316314205
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8221121550434057
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8129044863346081
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8255133471709527
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5067257944655903
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5109761436588146
            name: Spearman Dot
          - type: pearson_max
            value: 0.8290685425698586
            name: Pearson Max
          - type: spearman_max
            value: 0.8429054799136109
            name: Spearman Max
license: apache-2.0

SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-mpnet-base-v2 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: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- Omartificial-Intelligence-Space/arabic-n_li-triplet

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Omartificial-Intelligence-Space/Arabic-Nli-Matryoshka")
# 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

Metric	Value
pearson_cosine	0.8539
spearman_cosine	0.8616
pearson_manhattan	0.8497
spearman_manhattan	0.8513
pearson_euclidean	0.8516
spearman_euclidean	0.8541
pearson_dot	0.7281
spearman_dot	0.723
pearson_max	0.8539
spearman_max	0.8616

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8542
spearman_cosine	0.8609
pearson_manhattan	0.8487
spearman_manhattan	0.8512
pearson_euclidean	0.8505
spearman_euclidean	0.8539
pearson_dot	0.7076
spearman_dot	0.7029
pearson_max	0.8542
spearman_max	0.8609

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8486
spearman_cosine	0.8579
pearson_manhattan	0.8405
spearman_manhattan	0.8456
pearson_euclidean	0.8415
spearman_euclidean	0.8472
pearson_dot	0.6669
spearman_dot	0.6651
pearson_max	0.8486
spearman_max	0.8579

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.839
spearman_cosine	0.8499
pearson_manhattan	0.8287
spearman_manhattan	0.8353
pearson_euclidean	0.8298
spearman_euclidean	0.8372
pearson_dot	0.5856
spearman_dot	0.5835
pearson_max	0.839
spearman_max	0.8499

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8291
spearman_cosine	0.8429
pearson_manhattan	0.8101
spearman_manhattan	0.8221
pearson_euclidean	0.8129
spearman_euclidean	0.8255
pearson_dot	0.5067
spearman_dot	0.511
pearson_max	0.8291
spearman_max	0.8429

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	min: 5 tokens mean: 10.33 tokens max: 52 tokens	min: 5 tokens mean: 13.21 tokens max: 49 tokens	min: 5 tokens mean: 15.32 tokens max: 53 tokens

Samples:

anchor	positive	negative
`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 with these parameters:

{
    "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	min: 5 tokens mean: 21.86 tokens max: 105 tokens	min: 4 tokens mean: 10.22 tokens max: 49 tokens	min: 4 tokens mean: 11.2 tokens max: 33 tokens

Samples:

anchor	positive	negative
`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 with these parameters:

{
    "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: 256
per_device_eval_batch_size: 256
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_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: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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
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}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, '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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	sts-test-128_spearman_cosine	sts-test-256_spearman_cosine	sts-test-512_spearman_cosine	sts-test-64_spearman_cosine	sts-test-768_spearman_cosine
0.2294	500	10.1279	-	-	-	-	-
0.4587	1000	8.0384	-	-	-	-	-
0.6881	1500	7.3484	-	-	-	-	-
0.9174	2000	4.2216	-	-	-	-	-
1.0	2180	-	0.8499	0.8579	0.8609	0.8429	0.8616

Framework Versions

Python: 3.9.18
Sentence Transformers: 3.0.1
Transformers: 4.40.0
PyTorch: 2.2.2+cu121
Accelerate: 0.26.1
Datasets: 2.19.0
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@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

@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

@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}
}