--- base_model: sentence-transformers/all-MiniLM-L6-v2 datasets: [] language: [] library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:1053 - loss:CosineSimilarityLoss widget: - source_sentence: 'question: Radiateur électrique à inertie fluide pas cher disponible à Bastia ? ----->query: query=radiateur électrique inertie fluide&sort=price-asc&context=298' sentences: - 'question: Je recherche un pied de table disponible dans le magasin d''Ivry sur Seine. ----->query: query=Pied de table&context=142' - 'question: Peinture intérieure Luxens disponible dans le magasin de Vitry ? ----->query: query=luxens peinture interieure&context=21' - 'question: Radiateur disponible dans le magasin de Montauban ? ----->query: query=Radiateur&context=189' - source_sentence: 'question: Avez-vous des produits bio ? ----->query: query=Bio' sentences: - 'question: Je cherche des parpaings creux disponibles dans le magasin de Pau. ----->query: query=parpaing creux&context=41' - 'question: Je recherche des profilés disponibles dans le magasin de Bordeaux. ----->query: query=profilé&context=37' - 'question: Avez-vous des supports collecteurs disponibles dans le magasin de Strasbourg ? ----->query: query=Support collecteur&context=40' - source_sentence: 'question: Donnez-moi les pieds de table les moins chers disponibles dans le magasin de Thoiry. ----->query: query=pieds table&sort=price-asc&context=167' sentences: - 'question: Je cherche des pieds pour meuble. ----->query: query=Pieds meuble' - 'question: J''ai besoin d''enduit de rebouchage pour un chantier, est-ce que vous en avez en stock dans le magasin d''Osny ? ----->query: query=enduit de rebouchage&context=23' - 'question: Avez-vous du mastic d''étanchéité disponible dans le magasin de Clermont Ferrand ? ----->query: query=mastic d''etancheite&context=133' - source_sentence: 'question: Donnez-moi les pieds de table les moins chers disponibles dans le magasin de Thoiry. ----->query: query=pieds table&sort=price-asc&context=167' sentences: - 'question: Je recherche du parquet. ----->query: query=parket' - 'question: J''aimerais savoir si vous avez des pinces à dénuder dans le magasin de Cabries. ----->query: query=pince a denuder&context=66' - 'question: Parquet contrecollé pas cher dans le magasin de Nice. ----->query: query=parquet contrecolle&sort=price-asc&context=6' - source_sentence: 'question: Je cherche une scie dans le magasin de Dinard. ----->query: query=Scie&context=178' sentences: - 'question: Dalles pour l''extérieur ----->query: query=dalle exterieur' - 'question: J''ai besoin d''une goulotte pour câble électrique, disponible dans le magasin de Vitry. ----->query: query=goulotte pour cable electrique&context=21' - 'question: J''aimerais savoir si vous avez des pinces à dénuder dans le magasin de Cabries. ----->query: query=pince a denuder&context=66' --- # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2) - **Maximum Sequence Length:** 256 tokens - **Output Dimensionality:** 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 384, '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}) (2): Normalize() ) ``` ## 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("yandac/embedding_model_search_api") # Run inference sentences = [ 'question: Je cherche une scie dans le magasin de Dinard. ----->query: query=Scie&context=178', "question: J'aimerais savoir si vous avez des pinces à dénuder dans le magasin de Cabries. ----->query: query=pince a denuder&context=66", "question: J'ai besoin d'une goulotte pour câble électrique, disponible dans le magasin de Vitry. ----->query: query=goulotte pour cable electrique&context=21", ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 1,053 training samples * Columns: sentence1, sentence2, and label * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence1 | sentence2 | label | |:--------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | question: Peinture pour bois extérieur disponible dans le magasin de Mundolsheim ? ----->query: query=Peinture bois extérieur&context=197 | question: Avez-vous des plans de travail d'angle disponibles dans le magasin de Douai ? ----->query: query=plan de travail d'angle&context=183 | 0.0 | | question: Sac de granulés de bois disponible dans le magasin de Brive ? ----->query: query=sac granule bois&context=175 | question: Avez-vous des 1/2 ronds disponibles dans le magasin de Compiegne ? ----->query: query=1/2 rond&context=78 | 0.0 | | question: Je cherche un rouleau d'étanchéité disponible dans le magasin de Cabries. ----->query: query=rouleau etancheite&context=66 | question: Je recherche un pied de table disponible dans le magasin d'Ivry sur Seine. ----->query: query=Pied de table&context=142 | 0.0 | * 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 - `per_device_train_batch_size`: 1 - `num_train_epochs`: 4.8 - `warmup_ratio`: 0.1 - `fp16`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 1 - `per_device_eval_batch_size`: 8 - `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`: 4.8 - `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 - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 1.5152 | 100 | 0.0071 | | 0.4748 | 500 | 0.0076 | | 0.9497 | 1000 | 0.0162 | | 1.4245 | 1500 | 0.0164 | | 1.8993 | 2000 | 0.0155 | | 2.3742 | 2500 | 0.0112 | | 2.8490 | 3000 | 0.0106 | | 3.3238 | 3500 | 0.0064 | | 3.7987 | 4000 | 0.0055 | | 4.2735 | 4500 | 0.0043 | | 4.7483 | 5000 | 0.0027 | | 0.4748 | 500 | 0.0046 | | 0.9497 | 1000 | 0.0102 | | 1.4245 | 1500 | 0.0134 | | 1.8993 | 2000 | 0.0133 | | 2.3742 | 2500 | 0.0086 | | 2.8490 | 3000 | 0.007 | | 3.3238 | 3500 | 0.0049 | | 3.7987 | 4000 | 0.0037 | | 4.2735 | 4500 | 0.0031 | | 4.7483 | 5000 | 0.0022 | ### Framework Versions - Python: 3.11.9 - Sentence Transformers: 3.0.1 - Transformers: 4.42.4 - PyTorch: 2.3.1+cu118 - Accelerate: 0.33.0 - Datasets: 2.20.0 - 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", } ```