Hugging Face's logo

amahdaouy
/
xlmrsim-mar_2ep

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:15642
loss:CosineSimilarityLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
xlmrsim-mar_2ep / README.md
amahdaouy's picture
amahdaouy
Add new SentenceTransformer model.
05a5666 verified
preview code
|
raw
history blame contribute delete
14.6 kB
metadata
base_model: sentence-transformers/stsb-xlm-r-multilingual
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:15642
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: Certificat d'admission universitaire
    sentences:
      - شهادة القبول الجامعي
      - شهادة الحياة الفردية
      - Film Production Center Creation Permit
  - source_sentence: دبلوم الدراسات الجامعية التقنية
    sentences:
      - Wind Energy Equipment Registration Certificate
      - Industrial Safety Standards Compliance Certificate
      - Virtual Reality Technologies Import License
  - source_sentence: شهادة المطابقة للمعايير المغربية
    sentences:
      - Certificate of Good Conduct
      - Commercial Lease Contract
      - Marriage Contract Document
  - source_sentence: رخصة استغلال مركز دراسات الطاقة المتجددة
    sentences:
      - Permis d'importation de matériel médical
      - Permis d'exploitation d'un centre d'études des énergies renouvelables
      - >-
        Autorisation d'exercer une activité dans le domaine des énergies
        renouvelables
  - source_sentence: Certificat de qualification en conception de systèmes intelligents
    sentences:
      - شهادة فحص منشآت الطاقة
      - Permis de création d'une centrale électrique éolienne
      - رخصة صناعية
model-index:
  - name: SentenceTransformer based on sentence-transformers/stsb-xlm-r-multilingual
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: eval
          type: eval
        metrics:
          - type: pearson_cosine
            value: 0.9932857106529867
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8659282642227534
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.9872002912590794
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8659382004848898
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9873391899791255
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8659392197992224
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.9762599450100259
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8656650063924476
            name: Spearman Dot
          - type: pearson_max
            value: 0.9932857106529867
            name: Pearson Max
          - type: spearman_max
            value: 0.8659392197992224
            name: Spearman Max

SentenceTransformer based on sentence-transformers/stsb-xlm-r-multilingual

This is a sentence-transformers model finetuned from sentence-transformers/stsb-xlm-r-multilingual. 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 Sources

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("amahdaouy/xlmrsim-mar_2ep")
# Run inference
sentences = [
    'Certificat de qualification en conception de systèmes intelligents',
    'رخصة صناعية',
    "Permis de création d'une centrale électrique éolienne",
]
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

Metric Value
pearson_cosine 0.9933
spearman_cosine 0.8659
pearson_manhattan 0.9872
spearman_manhattan 0.8659
pearson_euclidean 0.9873
spearman_euclidean 0.8659
pearson_dot 0.9763
spearman_dot 0.8657
pearson_max 0.9933
spearman_max 0.8659

Training Details

Training Dataset

Unnamed Dataset

  • Size: 15,642 training samples
  • Columns: sentence_0, sentence_1, and label
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 label
    type string string float
    details
    • min: 4 tokens
    • mean: 10.38 tokens
    • max: 33 tokens
    • min: 4 tokens
    • mean: 10.47 tokens
    • max: 28 tokens
    • min: 0.0
    • mean: 0.5
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    License to Produce and Distribute TV Programs Licence de production et de distribution de programmes télévisés 1.0
    Certificat de qualification en conception de systèmes intelligents رخصة صناعية 0.0
    عقد الشراء المشترك Shared Purchase Act 1.0
  • Loss: CosineSimilarityLoss with these parameters:
    {
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 32
  • num_train_epochs: 2
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 32
  • per_device_eval_batch_size: 32
  • 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: 2
  • 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: False
  • 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: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step Training Loss eval_spearman_max
0.2045 100 - 0.8638
0.4090 200 - 0.8651
0.6135 300 - 0.8655
0.8180 400 - 0.8659
1.0 489 - 0.8659
1.0225 500 0.0221 0.8659
1.2270 600 - 0.8659
1.4315 700 - 0.8660
1.6360 800 - 0.8659
1.8405 900 - 0.8659
2.0 978 - 0.8659

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.1.0
  • Transformers: 4.44.2
  • PyTorch: 2.4.0+cu121
  • Accelerate: 0.34.2
  • Datasets: 3.0.0
  • 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",
}