Hugging Face's logo

amahdaouy
/
xlmrsim-mar_cos

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:19755
loss:CosineSimilarityLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
xlmrsim-mar_cos / README.md
amahdaouy's picture
amahdaouy
Add new SentenceTransformer model.
0a5d763 verified
preview code
|
raw
history blame
14.9 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:19755
  - loss:CosineSimilarityLoss
widget:
  - source_sentence: Authorization to Hold a Cultural Event
    sentences:
      - Renewable Energy Accreditation Certificate
      - شهادة إدارة الموارد المائية
      - شهادة السلامة الصناعية
  - source_sentence: Phosphate Fertilizer Import License
    sentences:
      - >-
        Licence d'exploitation d'une usine de production de matériaux avancés
        pour la construction
      - Certificat de propriété conjointe
      - ' "Guarantee Form Filled and Signed"'
  - source_sentence: ' "Application for the Adaptation and Classification of Construction and Public Works Laboratories."'
    sentences:
      - ' "Demande d''adaptation et de classification des laboratoires de construction et de travaux publics"'
      - رخصة بناء مصنع للصناعات الخفيفة
      - Certificat de non-bénéfice de programmes d'aide sociale
  - source_sentence: Certificat d'importation d'équipements médicaux
    sentences:
      - دبلوم التكوين في علوم البحار
      - رخصة استغلال محطة كهربائية
      - Nuclear Equipment Factory Creation License
  - source_sentence: Virtual Reality Innovation Center Exploitation License
    sentences:
      - ' "نسخة من بطاقة التعريف الوطنية أو جواز السفر."'
      - رخصة استغلال مركز ابتكار تقنيات الواقع الافتراضي
      - Medical Equipment Import Certificate
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: 0.9937461553619508
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8656711043975902
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.9862199187169717
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8646030016681072
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9863097776981202
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8646004452560553
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.9687884311170258
            name: Pearson Dot
          - type: spearman_dot
            value: 0.8657032187055717
            name: Spearman Dot
          - type: pearson_max
            value: 0.9937461553619508
            name: Pearson Max
          - type: spearman_max
            value: 0.8657032187055717
            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_cos")
# Run inference
sentences = [
    'Virtual Reality Innovation Center Exploitation License',
    'رخصة استغلال مركز ابتكار تقنيات الواقع الافتراضي',
    ' "نسخة من بطاقة التعريف الوطنية أو جواز السفر."',
]
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 0.9937
spearman_cosine 0.8657
pearson_manhattan 0.9862
spearman_manhattan 0.8646
pearson_euclidean 0.9863
spearman_euclidean 0.8646
pearson_dot 0.9688
spearman_dot 0.8657
pearson_max 0.9937
spearman_max 0.8657

Training Details

Training Dataset

Unnamed Dataset

  • Size: 19,755 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: 12.66 tokens
    • max: 110 tokens
    • min: 4 tokens
    • mean: 12.34 tokens
    • max: 110 tokens
    • min: 0.0
    • mean: 0.5
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    Seasonal Commercial Activity License Certificat de participation aux activités sportives 0.0
    Authorization to Hold a Cultural Event شهادة إدارة الموارد المائية 0.0
    Permis d'exploitation des ports maritimes Seaport Exploitation Permit 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
0.1618 100 - 0.8617
0.3236 200 - 0.8639
0.4854 300 - 0.8639
0.6472 400 - 0.8644
0.8091 500 0.0228 0.8652
0.9709 600 - 0.8652
1.0 618 - 0.8652
1.1327 700 - 0.8650
1.2945 800 - 0.8653
1.4563 900 - 0.8651
1.6181 1000 0.0055 0.8651
1.7799 1100 - 0.8657
1.9417 1200 - 0.8657
2.0 1236 - 0.8657

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",
}