metadata

base_model: aubmindlab/bert-base-arabertv02
datasets: []
language: []
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1000000
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: فتى يرتدي اللون الأحمر ينزلق على متن عربة نفخة
    sentences:
      - اثنان من الشباب الآسيويين يتسكعون
      - فتى يلعب على عربة نفخة
      - فتى يثقب سكيناً في عربة نفخة
  - source_sentence: عامل بناء يقف على رافعة يضع ذراعًا كبيرًا على قمة قمة قيد الإنشاء.
    sentences:
      - الاطفال يركبون عربة متعة
      - شخص يقف
      - لا أحد يقف
  - source_sentence: رجل مع حفرة طاقة كبيرة يقف بجانب ابنته مع خرطوم المكنسة الكهربائية.
    sentences:
      - جنديان يحملان أسلحة
      - رجل يحمل مثقاب يقف بجانب فتاة تحمل خرطوم كهربائي
      - الرجل والفتاة يرسمون الجدران
  - source_sentence: رجل يرتدي قميص أسود يعزف على الجيتار.
    sentences:
      - الرجل يرتدي الأسود.
      - هناك رجل يفرغ
      - الرجل يرتدي قميصاً أزرق.
  - source_sentence: رجل يرتدي قميص (فيجاس) الأحمر يجلس على طاولة ويلعب بالكاميرا
    sentences:
      - رجل يلعب بالكاميرا
      - فتى يقفز في الهواء
      - الرجل يقف ويأخذ الصور
model-index:
  - 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: 0.8137491067613172
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8139804248887779
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.805239691712325
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8071457719582591
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8053105962459932
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8078084689219578
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8019135317246738
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7961388104098682
            name: Spearman Dot
          - type: pearson_max
            value: 0.8137491067613172
            name: Pearson Max
          - type: spearman_max
            value: 0.8139804248887779
            name: Spearman Max
          - type: pearson_cosine
            value: 0.8137491067613172
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8139804248887779
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.805239691712325
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8071457719582591
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8053105962459932
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8078084689219578
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.8019135317246738
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7961388104098682
            name: Spearman Dot
          - type: pearson_max
            value: 0.8137491067613172
            name: Pearson Max
          - type: spearman_max
            value: 0.8139804248887779
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.8127890716639393
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.813769735512917
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8045619532064516
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.806084784718251
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8047817340341926
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8067787363048019
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7985706834990611
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7926669266198092
            name: Spearman Dot
          - type: pearson_max
            value: 0.8127890716639393
            name: Pearson Max
          - type: spearman_max
            value: 0.813769735512917
            name: Spearman Max
          - type: pearson_cosine
            value: 0.8127890716639393
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.813769735512917
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8045619532064516
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.806084784718251
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8047817340341926
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8067787363048019
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7985706834990611
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7926669266198092
            name: Spearman Dot
          - type: pearson_max
            value: 0.8127890716639393
            name: Pearson Max
          - type: spearman_max
            value: 0.813769735512917
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.810388221021721
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8138356923403065
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8015100804443567
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8026219149891689
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8016089017435591
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8030480833628191
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.792265476718613
            name: Pearson Dot
          - type: spearman_dot
            value: 0.787067391010805
            name: Spearman Dot
          - type: pearson_max
            value: 0.810388221021721
            name: Pearson Max
          - type: spearman_max
            value: 0.8138356923403065
            name: Spearman Max
          - type: pearson_cosine
            value: 0.810388221021721
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8138356923403065
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8015100804443567
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8026219149891689
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8016089017435591
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8030480833628191
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.792265476718613
            name: Pearson Dot
          - type: spearman_dot
            value: 0.787067391010805
            name: Spearman Dot
          - type: pearson_max
            value: 0.810388221021721
            name: Pearson Max
          - type: spearman_max
            value: 0.8138356923403065
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.8071777671061434
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8128987608664245
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7969339482985063
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7972524285093451
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7971979787664204
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.797866628579141
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7752745908442699
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7685950685903284
            name: Spearman Dot
          - type: pearson_max
            value: 0.8071777671061434
            name: Pearson Max
          - type: spearman_max
            value: 0.8128987608664245
            name: Spearman Max
          - type: pearson_cosine
            value: 0.8071777671061434
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8128987608664245
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7969339482985063
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7972524285093451
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7971979787664204
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.797866628579141
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7752745908442699
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7685950685903284
            name: Spearman Dot
          - type: pearson_max
            value: 0.8071777671061434
            name: Pearson Max
          - type: spearman_max
            value: 0.8128987608664245
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.7992861493805723
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.809205854296297
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7841737408240652
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7848704254075567
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7865782078684138
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7874610680426495
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7341564461014968
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7244607540987561
            name: Spearman Dot
          - type: pearson_max
            value: 0.7992861493805723
            name: Pearson Max
          - type: spearman_max
            value: 0.809205854296297
            name: Spearman Max
          - type: pearson_cosine
            value: 0.7992861493805723
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.809205854296297
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7841737408240652
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7848704254075567
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7865782078684138
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7874610680426495
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.7341564461014968
            name: Pearson Dot
          - type: spearman_dot
            value: 0.7244607540987561
            name: Spearman Dot
          - type: pearson_max
            value: 0.7992861493805723
            name: Pearson Max
          - type: spearman_max
            value: 0.809205854296297
            name: Spearman Max

SentenceTransformer based on aubmindlab/bert-base-arabertv02

This is a sentence-transformers model finetuned from 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
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity

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': 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:

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/Arabert-matro-v4")
# Run inference
sentences = [
    'رجل يرتدي قميص (فيجاس) الأحمر يجلس على طاولة ويلعب بالكاميرا',
    'رجل يلعب بالكاميرا',
    'الرجل يقف ويأخذ الصور',
]
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	0.8137
spearman_cosine	0.814
pearson_manhattan	0.8052
spearman_manhattan	0.8071
pearson_euclidean	0.8053
spearman_euclidean	0.8078
pearson_dot	0.8019
spearman_dot	0.7961
pearson_max	0.8137
spearman_max	0.814

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8128
spearman_cosine	0.8138
pearson_manhattan	0.8046
spearman_manhattan	0.8061
pearson_euclidean	0.8048
spearman_euclidean	0.8068
pearson_dot	0.7986
spearman_dot	0.7927
pearson_max	0.8128
spearman_max	0.8138

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8104
spearman_cosine	0.8138
pearson_manhattan	0.8015
spearman_manhattan	0.8026
pearson_euclidean	0.8016
spearman_euclidean	0.803
pearson_dot	0.7923
spearman_dot	0.7871
pearson_max	0.8104
spearman_max	0.8138

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8072
spearman_cosine	0.8129
pearson_manhattan	0.7969
spearman_manhattan	0.7973
pearson_euclidean	0.7972
spearman_euclidean	0.7979
pearson_dot	0.7753
spearman_dot	0.7686
pearson_max	0.8072
spearman_max	0.8129

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7993
spearman_cosine	0.8092
pearson_manhattan	0.7842
spearman_manhattan	0.7849
pearson_euclidean	0.7866
spearman_euclidean	0.7875
pearson_dot	0.7342
spearman_dot	0.7245
pearson_max	0.7993
spearman_max	0.8092

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8137
spearman_cosine	0.814
pearson_manhattan	0.8052
spearman_manhattan	0.8071
pearson_euclidean	0.8053
spearman_euclidean	0.8078
pearson_dot	0.8019
spearman_dot	0.7961
pearson_max	0.8137
spearman_max	0.814

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8128
spearman_cosine	0.8138
pearson_manhattan	0.8046
spearman_manhattan	0.8061
pearson_euclidean	0.8048
spearman_euclidean	0.8068
pearson_dot	0.7986
spearman_dot	0.7927
pearson_max	0.8128
spearman_max	0.8138

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8104
spearman_cosine	0.8138
pearson_manhattan	0.8015
spearman_manhattan	0.8026
pearson_euclidean	0.8016
spearman_euclidean	0.803
pearson_dot	0.7923
spearman_dot	0.7871
pearson_max	0.8104
spearman_max	0.8138

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8072
spearman_cosine	0.8129
pearson_manhattan	0.7969
spearman_manhattan	0.7973
pearson_euclidean	0.7972
spearman_euclidean	0.7979
pearson_dot	0.7753
spearman_dot	0.7686
pearson_max	0.8072
spearman_max	0.8129

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7993
spearman_cosine	0.8092
pearson_manhattan	0.7842
spearman_manhattan	0.7849
pearson_euclidean	0.7866
spearman_euclidean	0.7875
pearson_dot	0.7342
spearman_dot	0.7245
pearson_max	0.7993
spearman_max	0.8092

Training Details

Training Dataset

Unnamed Dataset

Size: 1,000,000 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 4 tokens mean: 12.0 tokens max: 69 tokens	min: 4 tokens mean: 31.78 tokens max: 174 tokens	min: 4 tokens mean: 30.79 tokens max: 216 tokens

Samples:

anchor	positive	negative
`ما الذي تتجنبه؟`	`ما الذي تحاولين تجنبه دائماً؟`	`أنا في حالة اكتئاب ماذا يجب أن أفعل؟`
`رجل يقف عند لافتة صفراء`	`رجل يقترب من علامة`	`رجل بجانب لافتة زرقاء`
`لماذا قام (مودي) بحظر أوراق نقدية بقيمة 500 و 1000 روبية؟`	`لماذا قام مودي بإلغاء عملة الـ 500 و 1000 روبية؟ وما سبب إدخال عملة الـ 2000 روبية فجأة؟`	`ما هو أفضل خيار بعد الانتهاء من البكالوريوس في الهندسة الميكانيكية؟`

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: 4 tokens mean: 14.87 tokens max: 70 tokens	min: 4 tokens mean: 7.54 tokens max: 26 tokens	min: 4 tokens mean: 8.14 tokens max: 23 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: 64
per_device_eval_batch_size: 64
warmup_ratio: 0.1
fp16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
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: 1.0
num_train_epochs: 3
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
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}
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: 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_eval_metrics: False
eval_on_start: False
eval_use_gather_object: False
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
0.0384	200	9.7813	-	-	-	-	-
0.0768	400	4.4771	-	-	-	-	-
0.1152	600	3.754	-	-	-	-	-
0.1536	800	3.4086	-	-	-	-	-
0.1920	1000	3.1323	-	-	-	-	-
0.2304	1200	2.9257	-	-	-	-	-
0.2688	1400	2.8363	-	-	-	-	-
0.3072	1600	2.6156	-	-	-	-	-
0.3456	1800	2.5428	-	-	-	-	-
0.3840	2000	2.4927	-	-	-	-	-
0.4223	2200	2.4	-	-	-	-	-
0.4607	2400	2.3193	-	-	-	-	-
0.4991	2600	2.2363	-	-	-	-	-
0.5375	2800	2.1929	-	-	-	-	-
0.5759	3000	2.1396	-	-	-	-	-
0.6143	3200	2.0481	-	-	-	-	-
0.6527	3400	2.0299	-	-	-	-	-
0.6911	3600	1.9895	-	-	-	-	-
0.7295	3800	1.9889	-	-	-	-	-
0.7679	4000	1.9319	-	-	-	-	-
0.8063	4200	1.8865	-	-	-	-	-
0.8447	4400	1.8349	-	-	-	-	-
0.8831	4600	1.8047	-	-	-	-	-
0.9215	4800	1.8009	-	-	-	-	-
0.9599	5000	1.7962	-	-	-	-	-
0.9983	5200	1.7231	-	-	-	-	-
1.0367	5400	0.0288	-	-	-	-	-
1.0751	5600	0.0	-	-	-	-	-
1.1135	5800	0.0	-	-	-	-	-
1.1519	6000	0.0	-	-	-	-	-
1.1902	6200	0.0	-	-	-	-	-
1.0056	6400	0.2935	-	-	-	-	-
1.0440	6600	1.7571	-	-	-	-	-
1.0824	6800	1.6487	-	-	-	-	-
1.1208	7000	1.6513	-	-	-	-	-
1.1591	7200	1.5466	-	-	-	-	-
1.1975	7400	1.4583	-	-	-	-	-
1.2359	7600	1.3805	-	-	-	-	-
1.2743	7800	1.3264	-	-	-	-	-
1.3127	8000	1.1898	-	-	-	-	-
1.3511	8200	1.1961	-	-	-	-	-
1.3895	8400	1.1749	-	-	-	-	-
1.4279	8600	1.1438	-	-	-	-	-
1.4663	8800	1.1481	-	-	-	-	-
1.5047	9000	1.089	-	-	-	-	-
1.5431	9200	1.1063	-	-	-	-	-
1.5815	9400	1.0759	-	-	-	-	-
1.6199	9600	1.0215	-	-	-	-	-
1.6583	9800	1.0244	-	-	-	-	-
1.6967	10000	1.0546	-	-	-	-	-
1.7351	10200	1.0355	-	-	-	-	-
1.7735	10400	1.0078	-	-	-	-	-
1.8119	10600	1.0102	-	-	-	-	-
1.8503	10800	0.9899	-	-	-	-	-
1.8887	11000	0.971	-	-	-	-	-
1.9270	11200	0.9676	-	-	-	-	-
1.9654	11400	0.9707	-	-	-	-	-
2.0038	11600	0.8222	-	-	-	-	-
2.0422	11800	0.0	-	-	-	-	-
2.0806	12000	0.0	-	-	-	-	-
2.1190	12200	0.0	-	-	-	-	-
2.1574	12400	0.0	-	-	-	-	-
2.1958	12600	0.0	-	-	-	-	-
2.0111	12800	0.2783	-	-	-	-	-
2.0495	13000	0.8261	-	-	-	-	-
2.0879	13200	0.868	-	-	-	-	-
2.1263	13400	0.8653	-	-	-	-	-
2.1647	13600	0.8647	-	-	-	-	-
2.2031	13800	0.8085	-	-	-	-	-
2.2415	14000	0.8122	-	-	-	-	-
2.2799	14200	0.7647	-	-	-	-	-
2.3183	14400	0.6959	-	-	-	-	-
2.3567	14600	0.7228	-	-	-	-	-
2.3951	14800	0.7303	-	-	-	-	-
2.4335	15000	0.7056	-	-	-	-	-
2.4719	15200	0.737	-	-	-	-	-
2.5103	15400	0.7016	-	-	-	-	-
2.5487	15600	0.7183	-	-	-	-	-
2.5538	15627	-	0.8129	0.8138	0.8138	0.8092	0.8140

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.43.1
PyTorch: 2.2.2
Accelerate: 0.33.0
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}
}