--- base_model: somosnlp-hackathon-2022/paraphrase-spanish-distilroberta library_name: sentence-transformers pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:44147 - loss:SoftmaxLoss widget: - source_sentence: Componentes y Equipos para Distribución y Sistemas de Acondicionamiento Instalaciones de tubos y entubamientos sentences: - Frijoles verdes congelados Fríjoles congelados - 'Brida reductora para tubos de plástico cpvc Bridas reductoras para tubos ' - Naranja hamlin orgánica en lata o en frasco Naranjas orgánicas en lata o en frasco - source_sentence: Componentes y Suministros de Manufactura Ferretería sentences: - Terfenadina Antihistamínicos (bloqueadores H1) - Tomates verde Tomates - Ciruela sloe seca Ciruelas secas - source_sentence: Servicios Públicos y Servicios Relacionados con el Sector Público Servicios públicos sentences: - Chalote pikant orgánico Chalotes orgánicos - Rosal cortado seco ciciolina Rosas cortadas secas rosados - Rosal vivo peach sherbet Rosales vivos anaranjados - source_sentence: Maquinaria y Accesorios para Manufactura y Procesamiento Industrial Maquinaria y accesorios para cortar metales sentences: - Pimentón peperoncini seco Pimientos Secos - Ciruela diamante rojo congelada orgánica Ciruelas orgánicas congeladas - Máquinas para dar formas al metal en la superficie Máquinas perforadoras de metales - source_sentence: Alimentos, Bebidas y Tabaco Vegetales orgánicos secos sentences: - Coliflo rdok elgon orgánica seca Coliflores orgánicas secas - Arame orgánica seca Vegetales marinos orgánicos secos - Cereza dark guines Cerezas --- # SentenceTransformer based on somosnlp-hackathon-2022/paraphrase-spanish-distilroberta This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [somosnlp-hackathon-2022/paraphrase-spanish-distilroberta](https://huggingface.co/somosnlp-hackathon-2022/paraphrase-spanish-distilroberta). 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:** [somosnlp-hackathon-2022/paraphrase-spanish-distilroberta](https://huggingface.co/somosnlp-hackathon-2022/paraphrase-spanish-distilroberta) - **Maximum Sequence Length:** 256 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': 256, 'do_lower_case': False}) with Transformer model: RobertaModel (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("dfsandovalp01/paraphrase-spanish-distilroberta-MDD-pucCO-V2") # Run inference sentences = [ 'Alimentos, Bebidas y Tabaco Vegetales orgánicos secos', 'Coliflo rdok elgon orgánica seca Coliflores orgánicas secas', 'Arame orgánica seca Vegetales marinos orgánicos secos', ] 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] ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 44,147 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 | int | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:-----------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:---------------| | Maquinaria y Accesorios para Generación y Distribución de Energía Generación de energía | Amortiguador de veleta Equipo de cribado o estructuras de tubo de escape | 0 | | Alimentos, Bebidas y Tabaco Fruta orgánica en lata o en frasco | Mangos mayaguez orgánico en lata o en frasco Mangos orgánicos en lata o en frasco | 0 | | Alimentos, Bebidas y Tabaco Fruta orgánica congelada | Bolsa para transportar quimioterapia Equipo y suministros de quimioterapia | 1 | * Loss: [SoftmaxLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#softmaxloss) ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 1 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `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`: 1 - `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 | |:------:|:----:|:-------------:| | 0.1812 | 500 | 0.6649 | | 0.3623 | 1000 | 0.4498 | | 0.5435 | 1500 | 0.3788 | | 0.7246 | 2000 | 0.3636 | | 0.9058 | 2500 | 0.353 | | 0.1812 | 500 | 0.3429 | | 0.3623 | 1000 | 0.3254 | | 0.5435 | 1500 | 0.3359 | | 0.7246 | 2000 | 0.3209 | | 0.9058 | 2500 | 0.3311 | ### 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 and SoftmaxLoss ```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", } ```