--- 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](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-xlm-r-multilingual](https://huggingface.co/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 Type:** Sentence Transformer - **Base model:** [sentence-transformers/stsb-xlm-r-multilingual](https://huggingface.co/sentence-transformers/stsb-xlm-r-multilingual) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity ### 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': 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: ```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("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 * Dataset: `eval` * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | 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 | | | | * 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](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "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 ```bibtex @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", } ```