--- language: - en tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:200000 - loss:MultipleNegativesRankingLoss - loss:ContrastiveLoss base_model: BAAI/bge-base-en-v1.5 widget: - source_sentence: What is the best sushi restaurant in Los Angeles, aside from Urasawa which is impractical for regular visits? sentences: - How do I stop feeling sorry for ignorant and arrogant people? - What are the best sushi restaurants in Los Angeles? - Why do people flirt on Quora? - source_sentence: Why are many Quora writers lonely and/ or unemployed? sentences: - Are writers on Quora mostly lonely or have no job (unemployed)? - What are the attributes of monkeys belongs to Japanese-macaque monkey Family? - I want to change the education system in India. How can I have such power? - source_sentence: What is the best, and painless way to kill myself? sentences: - What is a way to commit suicide and not damaging your organs so that they can be donated? - How do I beat insomnia? - What is the most painless way to commit suicide? - source_sentence: What are ETF'S and what is the difference between ETF'S and mutual funds? sentences: - What is the difference between ETF and mutual funds? - What's better, an index ETF or an index mutual fund? - 'Income Tax: How to check pan card status?' - source_sentence: For what reasons can't the Olympics be held in India? sentences: - What are the best hotels to stay in Goa? - When will Olympics be held in India? - When will India qualify for the FIFA World Cup? datasets: - sentence-transformers/quora-duplicates 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 - average_precision - f1 - precision - recall - threshold - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_precision@10 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_recall@10 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: SentenceTransformer based on BAAI/bge-base-en-v1.5 results: - task: type: binary-classification name: Binary Classification dataset: name: quora duplicates type: quora-duplicates metrics: - type: cosine_accuracy value: 0.833 name: Cosine Accuracy - type: cosine_accuracy_threshold value: 0.8065301179885864 name: Cosine Accuracy Threshold - type: cosine_f1 value: 0.7630522088353413 name: Cosine F1 - type: cosine_f1_threshold value: 0.745335042476654 name: Cosine F1 Threshold - type: cosine_precision value: 0.6705882352941176 name: Cosine Precision - type: cosine_recall value: 0.8850931677018633 name: Cosine Recall - type: cosine_ap value: 0.8120519897128382 name: Cosine Ap - type: cosine_mcc value: 0.641402259734116 name: Cosine Mcc - task: type: paraphrase-mining name: Paraphrase Mining dataset: name: quora duplicates dev type: quora-duplicates-dev metrics: - type: average_precision value: 0.6286866338232051 name: Average Precision - type: f1 value: 0.6032452480296708 name: F1 - type: precision value: 0.5627297495999654 name: Precision - type: recall value: 0.6500474596592896 name: Recall - type: threshold value: 0.7944510877132416 name: Threshold - task: type: information-retrieval name: Information Retrieval dataset: name: Unknown type: unknown metrics: - type: cosine_accuracy@1 value: 0.9732 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9944 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9958 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9994 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.9732 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.432 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.27652 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.14606 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.8392449568046333 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.9654790046130339 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9826052435636259 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.9955256342023989 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.9852328208350886 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.983879365079365 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.9794253454223505 name: Cosine Map@100 --- # SentenceTransformer based on BAAI/bge-base-en-v1.5 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) datasets. 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Datasets:** - [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - **Language:** en ### 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': 512, 'do_lower_case': True}) with Transformer model: BertModel (1): Pooling({'word_embedding_dimension': 768, '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("manestay/bge-base-en-v1.5-mnrl-cl-multi") # Run inference sentences = [ "For what reasons can't the Olympics be held in India?", 'When will Olympics be held in India?', 'When will India qualify for the FIFA World Cup?', ] 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 #### Binary Classification * Dataset: `quora-duplicates` * Evaluated with [BinaryClassificationEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:--------------------------|:-----------| | cosine_accuracy | 0.833 | | cosine_accuracy_threshold | 0.8065 | | cosine_f1 | 0.7631 | | cosine_f1_threshold | 0.7453 | | cosine_precision | 0.6706 | | cosine_recall | 0.8851 | | **cosine_ap** | **0.8121** | | cosine_mcc | 0.6414 | #### Paraphrase Mining * Dataset: `quora-duplicates-dev` * Evaluated with [ParaphraseMiningEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator) with these parameters: ```json {'add_transitive_closure': , 'max_pairs': 500000, 'top_k': 100} ``` | Metric | Value | |:----------------------|:-----------| | **average_precision** | **0.6287** | | f1 | 0.6032 | | precision | 0.5627 | | recall | 0.65 | | threshold | 0.7945 | #### Information Retrieval * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.9732 | | cosine_accuracy@3 | 0.9944 | | cosine_accuracy@5 | 0.9958 | | cosine_accuracy@10 | 0.9994 | | cosine_precision@1 | 0.9732 | | cosine_precision@3 | 0.432 | | cosine_precision@5 | 0.2765 | | cosine_precision@10 | 0.1461 | | cosine_recall@1 | 0.8392 | | cosine_recall@3 | 0.9655 | | cosine_recall@5 | 0.9826 | | cosine_recall@10 | 0.9955 | | **cosine_ndcg@10** | **0.9852** | | cosine_mrr@10 | 0.9839 | | cosine_map@100 | 0.9794 | ## Training Details ### Training Datasets #### mnrl * Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 100,000 training samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------| | Why in India do we not have one on one political debate as in USA? | Why cant we have a public debate between politicians in India like the one in US? | Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk? | | What is OnePlus One? | How is oneplus one? | Why is OnePlus One so good? | | Does our mind control our emotions? | How do smart and successful people control their emotions? | How can I control my positive emotions for the people whom I love but they don't care about me? | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### cl * Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 100,000 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 | |:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------| | What is the step by step guide to invest in share market in india? | What is the step by step guide to invest in share market? | 0 | | What is the story of Kohinoor (Koh-i-Noor) Diamond? | What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back? | 0 | | How can I increase the speed of my internet connection while using a VPN? | How can Internet speed be increased by hacking through DNS? | 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 Datasets #### mnrl * Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 1,000 evaluation samples * Columns: anchor, positive, and negative * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | | | | * Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Which programming language is best for developing low-end games? | What coding language should I learn first for making games? | I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages ​​I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms? | | Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump? | Should Meryl Streep be using her position to attack the president? | Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings? | | Where can I found excellent commercial fridges in Sydney? | Where can I found impressive range of commercial fridges in Sydney? | What is the best grocery delivery service in Sydney? | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### cl * Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 1,000 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 | |:--------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|:---------------| | What should I ask my friend to get from UK to India? | What is the process of getting a surgical residency in UK after completing MBBS from India? | 0 | | How can I learn hacking for free? | How can I learn to hack seriously? | 1 | | Which is the best website to learn programming language C++? | Which is the best website to learn C++ Programming language for free? | 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`: 400 - `per_device_eval_batch_size`: 400 - `num_train_epochs`: 100 - `warmup_ratio`: 0.1 - `bf16`: True - `load_best_model_at_end`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 400 - `per_device_eval_batch_size`: 400 - `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`: 1.0 - `num_train_epochs`: 100 - `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`: True - `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`: 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 - `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`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | mnrl loss | cl loss | quora-duplicates_cosine_ap | quora-duplicates-dev_average_precision | cosine_ndcg@10 | |:-------:|:-------:|:-------------:|:----------:|:----------:|:--------------------------:|:--------------------------------------:|:--------------:| | 0 | 0 | - | - | - | 0.7461 | 0.5988 | 0.9831 | | 0.2 | 100 | 0.2804 | - | - | - | - | - | | 0.4 | 200 | 0.2006 | - | - | - | - | - | | **0.5** | **250** | **-** | **0.1153** | **0.0157** | **0.7661** | **0.6165** | **0.9839** | | 0.6 | 300 | 0.1704 | - | - | - | - | - | | 0.8 | 400 | 0.1459 | - | - | - | - | - | | 1.0 | 500 | 0.1296 | 0.0835 | 0.0146 | 0.7860 | 0.6238 | 0.9843 | | 1.2 | 600 | 0.1344 | - | - | - | - | - | | 1.4 | 700 | 0.1181 | - | - | - | - | - | | 1.5 | 750 | - | 0.0737 | 0.0139 | 0.7983 | 0.6263 | 0.9847 | | 1.6 | 800 | 0.1176 | - | - | - | - | - | | 1.8 | 900 | 0.119 | - | - | - | - | - | | 2.0 | 1000 | 0.1127 | 0.0682 | 0.0133 | 0.8121 | 0.6287 | 0.9852 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.12.9 - Sentence Transformers: 4.1.0 - Transformers: 4.52.4 - PyTorch: 2.7.0+cu126 - Accelerate: 1.7.0 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## 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", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` #### 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} } ```