--- tags: - sentence-transformers - sparse-encoder - sparse - splade - generated_from_trainer - dataset_size:1000000 - loss:SpladeLoss - loss:SparseMarginMSELoss - loss:FlopsLoss base_model: yosefw/SPLADE-BERT-Mini-BS256 widget: - text: Caffeine is a central nervous system stimulant. It works by stimulating the brain. Caffeine is found naturally in foods and beverages such as coffee, tea, colas, energy and chocolate. Botanical sources of caffeine include kola nuts, guarana, and yerba mate. - text: Tim Hardaway, Jr. Compared To My 5ft 10in (177cm) Height. Tim Hardaway, Jr.'s height is 6ft 6in or 198cm while I am 5ft 10in or 177cm. I am shorter compared to him. To find out how much shorter I am, we would have to subtract my height from Tim Hardaway, Jr.'s height. Therefore I am shorter to him for about 21cm. - text: benefits of honey and lemon - text: 'How To Cook Corn on the Cob in the Microwave What You Need. Ingredients 1 or more ears fresh, un-shucked sweet corn Equipment Microwave Cooling rack or cutting board Instructions. Place 1 to 4 ears of corn in the microwave: Arrange 1 to 4 ears of corn, un-shucked, in the microwave. If you prefer, you can set them on a microwaveable plate or tray. If you need to cook more than 4 ears of corn, cook them in batches. Microwave for 3 to 5 minutes: For just 1 or 2 ears of corn, microwave for 3 minutes. For 3 or 4 ears, microwave for 4 minutes. If you like softer corn or if your ears are particularly large, microwave for an additional minute.' - text: The law recognizes two basic kinds of warrantiesimplied warranties and express warranties. Implied Warranties. Implied warranties are unspoken, unwritten promises, created by state law, that go from you, as a seller or merchant, to your customers. pipeline_tag: feature-extraction library_name: sentence-transformers metrics: - dot_accuracy@1 - dot_accuracy@3 - dot_accuracy@5 - dot_accuracy@10 - dot_precision@1 - dot_precision@3 - dot_precision@5 - dot_precision@10 - dot_recall@1 - dot_recall@3 - dot_recall@5 - dot_recall@10 - dot_ndcg@10 - dot_mrr@10 - dot_map@100 - query_active_dims - query_sparsity_ratio - corpus_active_dims - corpus_sparsity_ratio model-index: - name: SPLADE Sparse Encoder results: - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: Unknown type: unknown metrics: - type: dot_accuracy@1 value: 0.5018 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.8286 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.9194 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.9746 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.5018 name: Dot Precision@1 - type: dot_precision@3 value: 0.2839333333333333 name: Dot Precision@3 - type: dot_precision@5 value: 0.19103999999999996 name: Dot Precision@5 - type: dot_precision@10 value: 0.10255999999999998 name: Dot Precision@10 - type: dot_recall@1 value: 0.4867666666666667 name: Dot Recall@1 - type: dot_recall@3 value: 0.81485 name: Dot Recall@3 - type: dot_recall@5 value: 0.9096166666666667 name: Dot Recall@5 - type: dot_recall@10 value: 0.9709333333333334 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.7457042059559617 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.6749323809523842 name: Dot Mrr@10 - type: dot_map@100 value: 0.670785161566693 name: Dot Map@100 - type: query_active_dims value: 22.584999084472656 name: Query Active Dims - type: query_sparsity_ratio value: 0.9992600419669592 name: Query Sparsity Ratio - type: corpus_active_dims value: 174.85202722777373 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9942712788405814 name: Corpus Sparsity Ratio --- # SPLADE Sparse Encoder This is a [SPLADE Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [yosefw/SPLADE-BERT-Mini-BS256](https://huggingface.co/yosefw/SPLADE-BERT-Mini-BS256) using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval. ## Model Details ### Model Description - **Model Type:** SPLADE Sparse Encoder - **Base model:** [yosefw/SPLADE-BERT-Mini-BS256](https://huggingface.co/yosefw/SPLADE-BERT-Mini-BS256) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 30522 dimensions - **Similarity Function:** Dot Product ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Documentation:** [Sparse Encoder Documentation](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sparse Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=sparse-encoder) ### Full Model Architecture ``` SparseEncoder( (0): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'BertForMaskedLM'}) (1): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522}) ) ``` ## 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 SparseEncoder # Download from the 🤗 Hub model = SparseEncoder("yosefw/SPLADE-BERT-Mini-BS256-distil") # Run inference queries = [ "common law implied warranty", ] documents = [ 'The law recognizes two basic kinds of warrantiesimplied warranties and express warranties. Implied Warranties. Implied warranties are unspoken, unwritten promises, created by state law, that go from you, as a seller or merchant, to your customers.', 'An implied warranty is a contract law term for certain assurances that are presumed in the sale of products or real property.', 'The implied warranty of fitness for a particular purpose is a promise that the law says you, as a seller, make when your customer relies on your advice that a product can be used for some specific purpose.', ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) print(query_embeddings.shape, document_embeddings.shape) # [1, 30522] [3, 30522] # Get the similarity scores for the embeddings similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) # tensor([[22.4364, 22.7160, 21.7330]]) ``` ## Evaluation ### Metrics #### Sparse Information Retrieval * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.5018 | | dot_accuracy@3 | 0.8286 | | dot_accuracy@5 | 0.9194 | | dot_accuracy@10 | 0.9746 | | dot_precision@1 | 0.5018 | | dot_precision@3 | 0.2839 | | dot_precision@5 | 0.191 | | dot_precision@10 | 0.1026 | | dot_recall@1 | 0.4868 | | dot_recall@3 | 0.8148 | | dot_recall@5 | 0.9096 | | dot_recall@10 | 0.9709 | | **dot_ndcg@10** | **0.7457** | | dot_mrr@10 | 0.6749 | | dot_map@100 | 0.6708 | | query_active_dims | 22.585 | | query_sparsity_ratio | 0.9993 | | corpus_active_dims | 174.852 | | corpus_sparsity_ratio | 0.9943 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 1,000,000 training samples * Columns: query, positive, negative_1, negative_2, and label * Approximate statistics based on the first 1000 samples: | | query | positive | negative_1 | negative_2 | label | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:-----------------------------------| | type | string | string | string | string | list | | details | | | | | | * Samples: | query | positive | negative_1 | negative_2 | label | |:-----------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------| | friendly home health care | Medicare Evaluation of the Quality of Care. The quality of care given at Friendly Care Home Health Services is periodically evaluated by Medicare. The results of the most recent evaluation period are listed below to help you compare home care agencies in your area. More Info. | Every participant took the same survey so it is a useful way to compare Friendly Care Home Health Services to other home care agencies. | It covers a wide range of services and can often delay the need for long-term nursing home care. More specifically, home health care may include occupational and physical therapy, speech therapy, and even skilled nursing. | [1.2647171020507812, 9.144136428833008] | | how much does the xbox elite controller weigh | How much does an Xbox 360 weigh? A: The weight of an Xbox 360 depends on the different model purchased, with an original Xbox 360 or Xbox 360 Elite weighing 7.7 pounds with a hard drive and a newer Xbox 360 Slim weighing 6.3 pounds. An Xbox 360 without a hard drive weighs 7 pounds. | How much does 6 xbox 360 games/cases weigh? How much does an xbox 360 elite weigh (in the box)? How much does an xbox 360 weigh? im going to fedex one? I am considering purchasing an Xbox 360, or a Playstation 3... | 1 You can only upload videos smaller than 600 MB. 2 You can only upload a photo (png, jpg, jpeg) or video (3gp, 3gpp, mp4, mov, avi, mpg, mpeg, rm). 3 You can only upload a photo or video. Video should be smaller than 600 MB/5 minutes. | [4.903870582580566, 18.162578582763672] | | what county is norfolk, ct in | Norfolk, Connecticut. Norfolk (local /ˈnɔːrfɔːrk/) is a town in Litchfield County, Connecticut, United States. The population was 1,787 at the 2010 census. | Norfolk Historic District. The Norfolk Historic District was listed on the National Register of Historic Places in 1979. Portions of the content on this web page were adapted from a copy of the original nomination document. [†] Adaptation copyright © 2010, The Gombach Group. Description. | Terms begin the first day of the month. Grand Juries, 1st and 3rd Wednesday of each month. Civil cases set by agreement of counsel and consent of the court; scheduling orders are mandatory in most cases. Civil and Criminal trials begin at 9:30 a.m. | [12.4237699508667, 21.46290397644043] | * Loss: [SpladeLoss](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#spladeloss) with these parameters: ```json { "loss": "SparseMarginMSELoss", "document_regularizer_weight": 0.12, "query_regularizer_weight": 0.2 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `learning_rate`: 4e-05 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.025 - `fp16`: True - `load_best_model_at_end`: True - `optim`: adamw_torch_fused #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `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`: 4e-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 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.025 - `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`: 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_fused - `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 - `hub_revision`: None - `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 - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | dot_ndcg@10 | |:-----:|:-----:|:-------------:|:-----------:| | 1.0 | 15625 | 9.3147 | 0.7353 | | 2.0 | 31250 | 7.5267 | 0.7429 | | 3.0 | 46875 | 6.3289 | 0.7457 | ### Framework Versions - Python: 3.11.13 - Sentence Transformers: 5.0.0 - Transformers: 4.53.3 - PyTorch: 2.6.0+cu124 - Accelerate: 1.9.0 - Datasets: 4.0.0 - Tokenizers: 0.21.2 ## 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", } ``` #### SpladeLoss ```bibtex @misc{formal2022distillationhardnegativesampling, title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective}, author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant}, year={2022}, eprint={2205.04733}, archivePrefix={arXiv}, primaryClass={cs.IR}, url={https://arxiv.org/abs/2205.04733}, } ``` #### SparseMarginMSELoss ```bibtex @misc{hofstätter2021improving, title={Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation}, author={Sebastian Hofstätter and Sophia Althammer and Michael Schröder and Mete Sertkan and Allan Hanbury}, year={2021}, eprint={2010.02666}, archivePrefix={arXiv}, primaryClass={cs.IR} } ``` #### FlopsLoss ```bibtex @article{paria2020minimizing, title={Minimizing flops to learn efficient sparse representations}, author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s}, journal={arXiv preprint arXiv:2004.05665}, year={2020} } ```