--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:77455 - loss:ContrastiveLoss base_model: deepvk/USER-bge-m3 widget: - source_sentence: Исследование антигена хеликобактера (Helicobacter pylori) sentences: - 'Токсоплазма (Toxoplasma gondii): Антитела: IgG, (количественно). Метод: ИФА' - 'Хеликобактер пилори (Helicobacter pylori): Антитела: IgG, (количественно). Метод: ИФА' - УЗИ молочных желез с эластографией - source_sentence: Антитела к ХГЧ ( IgM и IgG) sentences: - Общий анализ мочи с микроскопией - Антитела к тканевой трансглутаминазе, IgG - Прием (осмотр, консультация) врача-онколога в клинике - source_sentence: Белок общий в суточной моче sentences: - Уран в моче - Белок общий в сыворотке - Исследование уровня антигена фактора Виллебранда - source_sentence: 'Развернутая диагностика склеродермии (иммуноблот антинуклеарных антител: анти-Scl-70, CENT-A, CENT-B, RP11, RP155, Fibrillarin, NOR90, Th/To, PM-Scl 75, Ku, PDGFR, Ro-52) и антинуклеарный фактор (АНФ), иммуноблот' sentences: - 'Токсоплазма (Toxoplasma gondii): Антитела: IgG, (количественно). Метод: ИФА' - 'Эпителий кролика, IgE, аллерген - e82. Метод: ImmunoCAP' - Антинуклеарные антитела, IgG (анти-Sm, RNP/Sm, SS-A, SS-B, Scl-70, PM-Scl, PCNA, dsDNA, CENT-B, Jo-1, к гистонам, к нуклеосомам, Ribo P, AMA-M2), иммуноблот - source_sentence: Определение активности амилазы в моче sentences: - Амилаза общая в суточной моче - 'Микоплазма гениталиум (Mycoplasma genitalium): ДНК, (качественно). Метод: реал-тайм ПЦР' - 'Пенициллин V, IgE, аллерген - c2. Метод: ИФА' pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy - cosine_accuracy_threshold - cosine_f1 - cosine_f1_threshold - cosine_precision - cosine_recall - cosine_ap - cosine_mcc model-index: - name: SentenceTransformer based on deepvk/USER-bge-m3 results: - task: type: binary-classification name: Binary Classification dataset: name: binary eval test type: binary-eval-test metrics: - type: cosine_accuracy value: 0.9442084651302907 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.7781298160552979 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.8599519663764634 name: Cosine F1 - type: cosine_f1_threshold value: 0.7724614143371582 name: Cosine F1 Threshold - type: cosine_precision value: 0.8569932685115931 name: Cosine Precision - type: cosine_recall value: 0.8629311643319777 name: Cosine Recall - type: cosine_ap value: 0.9223179041268369 name: Cosine Ap - type: cosine_mcc value: 0.824796426094371 name: Cosine Mcc --- # SentenceTransformer based on deepvk/USER-bge-m3 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [deepvk/USER-bge-m3](https://huggingface.co/deepvk/USER-bge-m3). It maps sentences & paragraphs to a 1024-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:** [deepvk/USER-bge-m3](https://huggingface.co/deepvk/USER-bge-m3) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 1024 dimensions - **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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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("EvgenyBondarenko/BIEncoderRanker") # Run inference sentences = [ 'Определение активности амилазы в моче', 'Амилаза общая в суточной моче', 'Пенициллин V, IgE, аллерген - c2. Метод: ИФА', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Binary Classification * Dataset: `binary-eval-test` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:--------------------------|:-----------| | cosine_accuracy | 0.9442 | | cosine_accuracy_threshold | 0.7781 | | cosine_f1 | 0.86 | | cosine_f1_threshold | 0.7725 | | cosine_precision | 0.857 | | cosine_recall | 0.8629 | | **cosine_ap** | **0.9223** | | cosine_mcc | 0.8248 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 77,455 training samples * Columns: sentence1, sentence2, and label * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | sentence1 | sentence2 | label | |:-------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------| | Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам | Посев кожи на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный | 1 | | Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам | Посев отделяемого с кожи/раны на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный | 0 | | Посев с кожи на аэробную микрофлору и определение чувствительности к антимикробным препаратам | Посев отделяемого из глаза на аэробную и факультативно-анаэробную флору: Определение чувствительности к антибиотикам. Метод: культуральный | 0 | * Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 33,195 evaluation samples * Columns: sentence1, sentence2, and label * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | sentence1 | sentence2 | label | |:---------------------------------------------|:-------------------------------------------------------------|:---------------| | транскраниальная допплерография | УЗИ сосудов головного мозга | 1 | | транскраниальная допплерография | УЗИ сосудов глаза (доплерография) | 0 | | транскраниальная допплерография | Магнитно-резонансная томография головного мозга | 0 | * Loss: [ContrastiveLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `learning_rate`: 2e-05 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `save_only_model`: True - `fp16`: True - `load_best_model_at_end`: True #### 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`: 2e-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`: 1 - `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`: True - `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`: True - `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`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `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 - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | binary-eval-test_cosine_ap | |:------:|:----:|:-------------:|:---------------:|:--------------------------:| | 0.2065 | 500 | 0.0125 | 0.0096 | 0.8634 | | 0.4131 | 1000 | 0.0094 | 0.0082 | 0.8940 | | 0.6196 | 1500 | 0.0086 | 0.0073 | 0.9150 | | 0.8261 | 2000 | 0.0078 | 0.0068 | 0.9223 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.4.1 - Transformers: 4.49.0 - PyTorch: 2.6.0+cu118 - Accelerate: 1.4.0 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## 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", } ``` #### ContrastiveLoss ```bibtex @inproceedings{hadsell2006dimensionality, author={Hadsell, R. and Chopra, S. and LeCun, Y.}, booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, title={Dimensionality Reduction by Learning an Invariant Mapping}, year={2006}, volume={2}, number={}, pages={1735-1742}, doi={10.1109/CVPR.2006.100} } ```