--- language: - en license: apache-2.0 tags: - sentence-transformers - sparse-encoder - sparse - csr - generated_from_trainer - dataset_size:99000 - loss:CSRLoss - loss:SparseMultipleNegativesRankingLoss base_model: mixedbread-ai/mxbai-embed-large-v1 widget: - text: Saudi Arabia–United Arab Emirates relations However, the UAE and Saudi Arabia continue to take somewhat differing stances on regional conflicts such the Yemeni Civil War, where the UAE opposes Al-Islah, and supports the Southern Movement, which has fought against Saudi-backed forces, and the Syrian Civil War, where the UAE has disagreed with Saudi support for Islamist movements.[4] - text: Economy of New Zealand New Zealand's diverse market economy has a sizable service sector, accounting for 63% of all GDP activity in 2013.[17] Large scale manufacturing industries include aluminium production, food processing, metal fabrication, wood and paper products. Mining, manufacturing, electricity, gas, water, and waste services accounted for 16.5% of GDP in 2013.[17] The primary sector continues to dominate New Zealand's exports, despite accounting for 6.5% of GDP in 2013.[17] - text: who was the first president of indian science congress meeting held in kolkata in 1914 - text: Get Over It (Eagles song) "Get Over It" is a song by the Eagles released as a single after a fourteen-year breakup. It was also the first song written by bandmates Don Henley and Glenn Frey when the band reunited. "Get Over It" was played live for the first time during their Hell Freezes Over tour in 1994. It returned the band to the U.S. Top 40 after a fourteen-year absence, peaking at No. 31 on the Billboard Hot 100 chart. It also hit No. 4 on the Billboard Mainstream Rock Tracks chart. The song was not played live by the Eagles after the "Hell Freezes Over" tour in 1994. It remains the group's last Top 40 hit in the U.S. - text: 'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.' datasets: - sentence-transformers/natural-questions 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 co2_eq_emissions: emissions: 44.61605747039671 energy_consumed: 0.11478216595334396 source: codecarbon training_type: fine-tuning on_cloud: false cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K ram_total_size: 31.777088165283203 hours_used: 0.29 hardware_used: 1 x NVIDIA GeForce RTX 3090 model-index: - name: Sparse CSR model trained on Natural Questions results: - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 4 type: nq_eval_4 metrics: - type: dot_accuracy@1 value: 0.213 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.332 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.384 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.471 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.213 name: Dot Precision@1 - type: dot_precision@3 value: 0.11066666666666666 name: Dot Precision@3 - type: dot_precision@5 value: 0.0768 name: Dot Precision@5 - type: dot_precision@10 value: 0.047099999999999996 name: Dot Precision@10 - type: dot_recall@1 value: 0.213 name: Dot Recall@1 - type: dot_recall@3 value: 0.332 name: Dot Recall@3 - type: dot_recall@5 value: 0.384 name: Dot Recall@5 - type: dot_recall@10 value: 0.471 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.3320214744887544 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.28887976190476183 name: Dot Mrr@10 - type: dot_map@100 value: 0.29887106812161607 name: Dot Map@100 - type: query_active_dims value: 4.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.9990234375 name: Query Sparsity Ratio - type: corpus_active_dims value: 4.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9990234375 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 8 type: nq_eval_8 metrics: - type: dot_accuracy@1 value: 0.399 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.547 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.605 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.676 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.399 name: Dot Precision@1 - type: dot_precision@3 value: 0.18233333333333332 name: Dot Precision@3 - type: dot_precision@5 value: 0.12099999999999998 name: Dot Precision@5 - type: dot_precision@10 value: 0.0676 name: Dot Precision@10 - type: dot_recall@1 value: 0.399 name: Dot Recall@1 - type: dot_recall@3 value: 0.547 name: Dot Recall@3 - type: dot_recall@5 value: 0.605 name: Dot Recall@5 - type: dot_recall@10 value: 0.676 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.5318512792107337 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.48622857142857107 name: Dot Mrr@10 - type: dot_map@100 value: 0.494199623751254 name: Dot Map@100 - type: query_active_dims value: 8.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.998046875 name: Query Sparsity Ratio - type: corpus_active_dims value: 8.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.998046875 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 16 type: nq_eval_16 metrics: - type: dot_accuracy@1 value: 0.625 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.772 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.817 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.864 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.625 name: Dot Precision@1 - type: dot_precision@3 value: 0.2573333333333333 name: Dot Precision@3 - type: dot_precision@5 value: 0.16340000000000002 name: Dot Precision@5 - type: dot_precision@10 value: 0.0864 name: Dot Precision@10 - type: dot_recall@1 value: 0.625 name: Dot Recall@1 - type: dot_recall@3 value: 0.772 name: Dot Recall@3 - type: dot_recall@5 value: 0.817 name: Dot Recall@5 - type: dot_recall@10 value: 0.864 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.745416578772242 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.7073369047619051 name: Dot Mrr@10 - type: dot_map@100 value: 0.7111386394401871 name: Dot Map@100 - type: query_active_dims value: 16.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.99609375 name: Query Sparsity Ratio - type: corpus_active_dims value: 16.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.99609375 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 32 type: nq_eval_32 metrics: - type: dot_accuracy@1 value: 0.796 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.914 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.935 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.96 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.796 name: Dot Precision@1 - type: dot_precision@3 value: 0.30466666666666664 name: Dot Precision@3 - type: dot_precision@5 value: 0.18700000000000003 name: Dot Precision@5 - type: dot_precision@10 value: 0.09600000000000002 name: Dot Precision@10 - type: dot_recall@1 value: 0.796 name: Dot Recall@1 - type: dot_recall@3 value: 0.914 name: Dot Recall@3 - type: dot_recall@5 value: 0.935 name: Dot Recall@5 - type: dot_recall@10 value: 0.96 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.8830518503020526 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.8578750000000005 name: Dot Mrr@10 - type: dot_map@100 value: 0.8592202466151189 name: Dot Map@100 - type: query_active_dims value: 32.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.9921875 name: Query Sparsity Ratio - type: corpus_active_dims value: 32.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9921875 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 64 type: nq_eval_64 metrics: - type: dot_accuracy@1 value: 0.874 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.964 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.975 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.984 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.874 name: Dot Precision@1 - type: dot_precision@3 value: 0.32133333333333325 name: Dot Precision@3 - type: dot_precision@5 value: 0.19500000000000003 name: Dot Precision@5 - type: dot_precision@10 value: 0.0984 name: Dot Precision@10 - type: dot_recall@1 value: 0.874 name: Dot Recall@1 - type: dot_recall@3 value: 0.964 name: Dot Recall@3 - type: dot_recall@5 value: 0.975 name: Dot Recall@5 - type: dot_recall@10 value: 0.984 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.9354420170940584 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.9191289682539683 name: Dot Mrr@10 - type: dot_map@100 value: 0.91983717784354 name: Dot Map@100 - type: query_active_dims value: 64.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.984375 name: Query Sparsity Ratio - type: corpus_active_dims value: 64.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.984375 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 128 type: nq_eval_128 metrics: - type: dot_accuracy@1 value: 0.917 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.982 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.987 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.993 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.917 name: Dot Precision@1 - type: dot_precision@3 value: 0.32733333333333325 name: Dot Precision@3 - type: dot_precision@5 value: 0.19740000000000005 name: Dot Precision@5 - type: dot_precision@10 value: 0.09930000000000001 name: Dot Precision@10 - type: dot_recall@1 value: 0.917 name: Dot Recall@1 - type: dot_recall@3 value: 0.982 name: Dot Recall@3 - type: dot_recall@5 value: 0.987 name: Dot Recall@5 - type: dot_recall@10 value: 0.993 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.9607072002272121 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.9497607142857144 name: Dot Mrr@10 - type: dot_map@100 value: 0.949953431875422 name: Dot Map@100 - type: query_active_dims value: 128.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.96875 name: Query Sparsity Ratio - type: corpus_active_dims value: 128.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.96875 name: Corpus Sparsity Ratio - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: nq eval 256 type: nq_eval_256 metrics: - type: dot_accuracy@1 value: 0.94 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.989 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.992 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 0.995 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.94 name: Dot Precision@1 - type: dot_precision@3 value: 0.3296666666666666 name: Dot Precision@3 - type: dot_precision@5 value: 0.19840000000000002 name: Dot Precision@5 - type: dot_precision@10 value: 0.09950000000000002 name: Dot Precision@10 - type: dot_recall@1 value: 0.94 name: Dot Recall@1 - type: dot_recall@3 value: 0.989 name: Dot Recall@3 - type: dot_recall@5 value: 0.992 name: Dot Recall@5 - type: dot_recall@10 value: 0.995 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.9722726693687288 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.9645107142857143 name: Dot Mrr@10 - type: dot_map@100 value: 0.9645748509204045 name: Dot Map@100 - type: query_active_dims value: 256.0 name: Query Active Dims - type: query_sparsity_ratio value: 0.9375 name: Query Sparsity Ratio - type: corpus_active_dims value: 256.0 name: Corpus Active Dims - type: corpus_sparsity_ratio value: 0.9375 name: Corpus Sparsity Ratio --- # Sparse CSR model trained on Natural Questions This is a [CSR Sparse Encoder](https://www.sbert.net/docs/sparse_encoder/usage/usage.html) model finetuned from [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) on the [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space with 256 maximum active dimensions and can be used for semantic search and sparse retrieval. ## Model Details ### Model Description - **Model Type:** CSR Sparse Encoder - **Base model:** [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 4096 dimensions (trained with 256 maximum active dimensions) - **Similarity Function:** Dot Product - **Training Dataset:** - [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) - **Language:** en - **License:** apache-2.0 ### 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): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel (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): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30}) ) ``` ## 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("tomaarsen/csr-mxbai-embed-large-v1-nq-dot-scale-1-gamma-0.1-detach-2") # Run inference queries = [ "who is cornelius in the book of acts", ] documents = [ 'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.', "Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in 1991 as their head of story.[1] There he worked on all of their films produced up to 2006; this included Toy Story (for which he received an Academy Award nomination) and A Bug's Life, as the co-story writer and others as story supervisor. His final film was Cars. He also voiced characters in many of the films, including Heimlich the caterpillar in A Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in Finding Nemo.[1]", 'Wonderful Tonight "Wonderful Tonight" is a ballad written by Eric Clapton. It was included on Clapton\'s 1977 album Slowhand. Clapton wrote the song about Pattie Boyd.[1] The female vocal harmonies on the song are provided by Marcella Detroit (then Marcy Levy) and Yvonne Elliman.', ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) print(query_embeddings.shape, document_embeddings.shape) # [1, 4096] [3, 4096] # Get the similarity scores for the embeddings similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) # tensor([[119.9615, 28.3687, 21.7583]]) ``` ## Evaluation ### Metrics #### Sparse Information Retrieval * Dataset: `nq_eval_4` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 4 } ``` | Metric | Value | |:----------------------|:----------| | dot_accuracy@1 | 0.213 | | dot_accuracy@3 | 0.332 | | dot_accuracy@5 | 0.384 | | dot_accuracy@10 | 0.471 | | dot_precision@1 | 0.213 | | dot_precision@3 | 0.1107 | | dot_precision@5 | 0.0768 | | dot_precision@10 | 0.0471 | | dot_recall@1 | 0.213 | | dot_recall@3 | 0.332 | | dot_recall@5 | 0.384 | | dot_recall@10 | 0.471 | | **dot_ndcg@10** | **0.332** | | dot_mrr@10 | 0.2889 | | dot_map@100 | 0.2989 | | query_active_dims | 4.0 | | query_sparsity_ratio | 0.999 | | corpus_active_dims | 4.0 | | corpus_sparsity_ratio | 0.999 | #### Sparse Information Retrieval * Dataset: `nq_eval_8` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 8 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.399 | | dot_accuracy@3 | 0.547 | | dot_accuracy@5 | 0.605 | | dot_accuracy@10 | 0.676 | | dot_precision@1 | 0.399 | | dot_precision@3 | 0.1823 | | dot_precision@5 | 0.121 | | dot_precision@10 | 0.0676 | | dot_recall@1 | 0.399 | | dot_recall@3 | 0.547 | | dot_recall@5 | 0.605 | | dot_recall@10 | 0.676 | | **dot_ndcg@10** | **0.5319** | | dot_mrr@10 | 0.4862 | | dot_map@100 | 0.4942 | | query_active_dims | 8.0 | | query_sparsity_ratio | 0.998 | | corpus_active_dims | 8.0 | | corpus_sparsity_ratio | 0.998 | #### Sparse Information Retrieval * Dataset: `nq_eval_16` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 16 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.625 | | dot_accuracy@3 | 0.772 | | dot_accuracy@5 | 0.817 | | dot_accuracy@10 | 0.864 | | dot_precision@1 | 0.625 | | dot_precision@3 | 0.2573 | | dot_precision@5 | 0.1634 | | dot_precision@10 | 0.0864 | | dot_recall@1 | 0.625 | | dot_recall@3 | 0.772 | | dot_recall@5 | 0.817 | | dot_recall@10 | 0.864 | | **dot_ndcg@10** | **0.7454** | | dot_mrr@10 | 0.7073 | | dot_map@100 | 0.7111 | | query_active_dims | 16.0 | | query_sparsity_ratio | 0.9961 | | corpus_active_dims | 16.0 | | corpus_sparsity_ratio | 0.9961 | #### Sparse Information Retrieval * Dataset: `nq_eval_32` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 32 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.796 | | dot_accuracy@3 | 0.914 | | dot_accuracy@5 | 0.935 | | dot_accuracy@10 | 0.96 | | dot_precision@1 | 0.796 | | dot_precision@3 | 0.3047 | | dot_precision@5 | 0.187 | | dot_precision@10 | 0.096 | | dot_recall@1 | 0.796 | | dot_recall@3 | 0.914 | | dot_recall@5 | 0.935 | | dot_recall@10 | 0.96 | | **dot_ndcg@10** | **0.8831** | | dot_mrr@10 | 0.8579 | | dot_map@100 | 0.8592 | | query_active_dims | 32.0 | | query_sparsity_ratio | 0.9922 | | corpus_active_dims | 32.0 | | corpus_sparsity_ratio | 0.9922 | #### Sparse Information Retrieval * Dataset: `nq_eval_64` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 64 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.874 | | dot_accuracy@3 | 0.964 | | dot_accuracy@5 | 0.975 | | dot_accuracy@10 | 0.984 | | dot_precision@1 | 0.874 | | dot_precision@3 | 0.3213 | | dot_precision@5 | 0.195 | | dot_precision@10 | 0.0984 | | dot_recall@1 | 0.874 | | dot_recall@3 | 0.964 | | dot_recall@5 | 0.975 | | dot_recall@10 | 0.984 | | **dot_ndcg@10** | **0.9354** | | dot_mrr@10 | 0.9191 | | dot_map@100 | 0.9198 | | query_active_dims | 64.0 | | query_sparsity_ratio | 0.9844 | | corpus_active_dims | 64.0 | | corpus_sparsity_ratio | 0.9844 | #### Sparse Information Retrieval * Dataset: `nq_eval_128` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 128 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.917 | | dot_accuracy@3 | 0.982 | | dot_accuracy@5 | 0.987 | | dot_accuracy@10 | 0.993 | | dot_precision@1 | 0.917 | | dot_precision@3 | 0.3273 | | dot_precision@5 | 0.1974 | | dot_precision@10 | 0.0993 | | dot_recall@1 | 0.917 | | dot_recall@3 | 0.982 | | dot_recall@5 | 0.987 | | dot_recall@10 | 0.993 | | **dot_ndcg@10** | **0.9607** | | dot_mrr@10 | 0.9498 | | dot_map@100 | 0.95 | | query_active_dims | 128.0 | | query_sparsity_ratio | 0.9688 | | corpus_active_dims | 128.0 | | corpus_sparsity_ratio | 0.9688 | #### Sparse Information Retrieval * Dataset: `nq_eval_256` * Evaluated with [SparseInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseInformationRetrievalEvaluator) with these parameters: ```json { "max_active_dims": 256 } ``` | Metric | Value | |:----------------------|:-----------| | dot_accuracy@1 | 0.94 | | dot_accuracy@3 | 0.989 | | dot_accuracy@5 | 0.992 | | dot_accuracy@10 | 0.995 | | dot_precision@1 | 0.94 | | dot_precision@3 | 0.3297 | | dot_precision@5 | 0.1984 | | dot_precision@10 | 0.0995 | | dot_recall@1 | 0.94 | | dot_recall@3 | 0.989 | | dot_recall@5 | 0.992 | | dot_recall@10 | 0.995 | | **dot_ndcg@10** | **0.9723** | | dot_mrr@10 | 0.9645 | | dot_map@100 | 0.9646 | | query_active_dims | 256.0 | | query_sparsity_ratio | 0.9375 | | corpus_active_dims | 256.0 | | corpus_sparsity_ratio | 0.9375 | ## Training Details ### Training Dataset #### natural-questions * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17) * Size: 99,000 training samples * Columns: query and answer * Approximate statistics based on the first 1000 samples: | | query | answer | |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | query | answer | |:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | who played the father in papa don't preach | Alex McArthur Alex McArthur (born March 6, 1957) is an American actor. | | where was the location of the battle of hastings | Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory. | | how many puppies can a dog give birth to | Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22] | * Loss: [CSRLoss](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters: ```json { "beta": 0.1, "gamma": 0.1, "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')" } ``` ### Evaluation Dataset #### natural-questions * Dataset: [natural-questions](https://huggingface.co/datasets/sentence-transformers/natural-questions) at [f9e894e](https://huggingface.co/datasets/sentence-transformers/natural-questions/tree/f9e894e1081e206e577b4eaa9ee6de2b06ae6f17) * Size: 1,000 evaluation samples * Columns: query and answer * Approximate statistics based on the first 1000 samples: | | query | answer | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | query | answer | |:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | where is the tiber river located in italy | Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks. | | what kind of car does jay gatsby drive | Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry. | | who sings if i can dream about you | I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1] | * Loss: [CSRLoss](https://sbert.net/docs/package_reference/sparse_encoder/losses.html#csrloss) with these parameters: ```json { "beta": 0.1, "gamma": 0.1, "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `learning_rate`: 4e-05 - `num_train_epochs`: 1 - `bf16`: 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`: 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`: 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`: 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`: 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`: 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 - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | Validation Loss | nq_eval_4_dot_ndcg@10 | nq_eval_8_dot_ndcg@10 | nq_eval_16_dot_ndcg@10 | nq_eval_32_dot_ndcg@10 | nq_eval_64_dot_ndcg@10 | nq_eval_128_dot_ndcg@10 | nq_eval_256_dot_ndcg@10 | |:------:|:----:|:-------------:|:---------------:|:---------------------:|:---------------------:|:----------------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:| | -1 | -1 | - | - | 0.2464 | 0.4430 | 0.6677 | 0.8417 | 0.9258 | 0.9545 | 0.9654 | | 0.0646 | 100 | 0.2916 | - | - | - | - | - | - | - | - | | 0.1293 | 200 | 0.2606 | - | - | - | - | - | - | - | - | | 0.1939 | 300 | 0.2553 | 0.2534 | 0.3060 | 0.4995 | 0.7232 | 0.8641 | 0.9406 | 0.9621 | 0.9697 | | 0.2586 | 400 | 0.2496 | - | - | - | - | - | - | - | - | | 0.3232 | 500 | 0.2488 | - | - | - | - | - | - | - | - | | 0.3878 | 600 | 0.2475 | 0.2474 | 0.3331 | 0.5247 | 0.7336 | 0.8778 | 0.9350 | 0.9598 | 0.9692 | | 0.4525 | 700 | 0.2477 | - | - | - | - | - | - | - | - | | 0.5171 | 800 | 0.2471 | - | - | - | - | - | - | - | - | | 0.5818 | 900 | 0.246 | 0.2452 | 0.3490 | 0.5252 | 0.7368 | 0.8760 | 0.9326 | 0.9634 | 0.9678 | | 0.6464 | 1000 | 0.2449 | - | - | - | - | - | - | - | - | | 0.7111 | 1100 | 0.2444 | - | - | - | - | - | - | - | - | | 0.7757 | 1200 | 0.2422 | 0.2418 | 0.3356 | 0.5366 | 0.7431 | 0.8839 | 0.9358 | 0.9601 | 0.9703 | | 0.8403 | 1300 | 0.2438 | - | - | - | - | - | - | - | - | | 0.9050 | 1400 | 0.2388 | - | - | - | - | - | - | - | - | | 0.9696 | 1500 | 0.2406 | 0.2410 | 0.3318 | 0.5338 | 0.7452 | 0.8818 | 0.9345 | 0.9618 | 0.9713 | | -1 | -1 | - | - | 0.3320 | 0.5319 | 0.7454 | 0.8831 | 0.9354 | 0.9607 | 0.9723 | ### Environmental Impact Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon). - **Energy Consumed**: 0.115 kWh - **Carbon Emitted**: 0.045 kg of CO2 - **Hours Used**: 0.29 hours ### Training Hardware - **On Cloud**: No - **GPU Model**: 1 x NVIDIA GeForce RTX 3090 - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K - **RAM Size**: 31.78 GB ### Framework Versions - Python: 3.11.6 - Sentence Transformers: 4.2.0.dev0 - Transformers: 4.52.4 - PyTorch: 2.6.0+cu124 - Accelerate: 1.5.1 - Datasets: 2.21.0 - 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", } ``` #### CSRLoss ```bibtex @misc{wen2025matryoshkarevisitingsparsecoding, title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation}, author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You}, year={2025}, eprint={2503.01776}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2503.01776}, } ``` #### SparseMultipleNegativesRankingLoss ```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} } ```