--- 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: - 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 - query_active_dims - query_sparsity_ratio - corpus_active_dims - corpus_sparsity_ratio co2_eq_emissions: emissions: 105.88726450328866 energy_consumed: 0.27241245093487726 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: 0.75 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: NanoMSMARCO 4 type: NanoMSMARCO_4 metrics: - type: cosine_accuracy@1 value: 0.12 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.16 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.26 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.34 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.12 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.05333333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.052000000000000005 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.034 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.12 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.16 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.26 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.34 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.20848075322384305 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.16888095238095235 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.18291408151127517 name: Cosine 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: NanoNFCorpus 4 type: NanoNFCorpus_4 metrics: - type: cosine_accuracy@1 value: 0.06 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.14 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.24 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.3 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.06 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.06000000000000001 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.068 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.064 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.0009459743220542356 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.003449821160051155 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.007601209053812086 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.014969691928058278 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.06420092741811712 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.12744444444444444 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.014642071302654571 name: Cosine 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: NanoNQ 4 type: NanoNQ_4 metrics: - type: cosine_accuracy@1 value: 0.04 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.08 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.16 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.26 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.04 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.026666666666666665 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.032 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.026000000000000002 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.04 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.08 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.16 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.25 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.12446577906212845 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.08757936507936508 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.09936029341073244 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 4 type: NanoBEIR_mean_4 metrics: - type: cosine_accuracy@1 value: 0.07333333333333333 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.12666666666666668 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.22 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.3 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.07333333333333333 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.04666666666666667 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.05066666666666667 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.04133333333333333 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.053648658107351414 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.08114994038668372 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.14253373635127067 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.20165656397601942 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.13238248656802956 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.12796825396825398 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.09897214874155406 name: Cosine 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: NanoMSMARCO 8 type: NanoMSMARCO_8 metrics: - type: cosine_accuracy@1 value: 0.14 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.24 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.32 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.42 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.14 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.064 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.042 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.14 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.24 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.32 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.42 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2597698452054917 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.21088888888888888 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.22093158927995368 name: Cosine 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: NanoNFCorpus 8 type: NanoNFCorpus_8 metrics: - type: cosine_accuracy@1 value: 0.08 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.24 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.32 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.4 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.08 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.10666666666666666 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.1 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08199999999999999 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.003534803921568628 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.01332319047951684 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.018603958472557434 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.027472535276451802 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.08639423970883567 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.16755555555555557 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.02734093319516609 name: Cosine 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: NanoNQ 8 type: NanoNQ_8 metrics: - type: cosine_accuracy@1 value: 0.08 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.24 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.44 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.08 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.07999999999999999 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.06000000000000001 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.046000000000000006 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.08 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.22 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.28 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.42 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2376977753947817 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.1862142857142857 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.18701815429415725 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 8 type: NanoBEIR_mean_8 metrics: - type: cosine_accuracy@1 value: 0.10000000000000002 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.24 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.3133333333333333 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.42 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.10000000000000002 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.08888888888888886 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07466666666666667 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.05666666666666667 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.07451160130718955 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.15777439682650563 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2062013194908525 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.28915751175881726 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.19462062010303635 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.1882195767195767 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.14509689225642566 name: Cosine 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: NanoMSMARCO 16 type: NanoMSMARCO_16 metrics: - type: cosine_accuracy@1 value: 0.22 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.48 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.58 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.22 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.15999999999999998 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11599999999999999 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.07 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.22 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.48 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.58 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.7 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.45695469767923136 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.37962698412698415 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3855020346571363 name: Cosine 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: NanoNFCorpus 16 type: NanoNFCorpus_16 metrics: - type: cosine_accuracy@1 value: 0.18 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.34 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.44 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.54 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.18 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.15333333333333332 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14400000000000002 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.12399999999999999 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.006630871390546997 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.015107785892825198 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.023769342657046163 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.03915909301380926 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.134487928424105 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.28135714285714286 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.04034378873464851 name: Cosine 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: NanoNQ 16 type: NanoNQ_16 metrics: - type: cosine_accuracy@1 value: 0.22 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.32 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.36 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.22 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.10666666666666665 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.07200000000000001 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.052000000000000005 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.22 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.3 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.33 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.48 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.33052122676463463 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.2881904761904762 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2997157011386181 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 16 type: NanoBEIR_mean_16 metrics: - type: cosine_accuracy@1 value: 0.20666666666666667 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.38000000000000006 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.45999999999999996 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.58 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.20666666666666667 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.13999999999999999 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.11066666666666668 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.082 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.14887695713018234 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.2650359286309417 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3112564475523487 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.4063863643379364 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.30732128428932365 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3163915343915344 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.2418538415101343 name: Cosine 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: NanoMSMARCO 32 type: NanoMSMARCO_32 metrics: - type: cosine_accuracy@1 value: 0.36 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.58 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.62 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.36 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.19333333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.124 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.07 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.36 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.58 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.62 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.7 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5319469082007623 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.47833333333333333 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.4895239579497892 name: Cosine 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: NanoNFCorpus 32 type: NanoNFCorpus_32 metrics: - type: cosine_accuracy@1 value: 0.36 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.48 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.52 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.64 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.36 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.24 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.21999999999999997 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.172 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.015057828440744998 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.03195263461978998 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.051589014542877495 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.07035182595749563 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.21044771940181314 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.4425476190476191 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.07089713098470313 name: Cosine 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: NanoNQ 32 type: NanoNQ_32 metrics: - type: cosine_accuracy@1 value: 0.28 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.4 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.52 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.62 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.28 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.13333333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.10400000000000002 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.066 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.26 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.37 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.47 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.59 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4160684104470306 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.3762142857142857 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.3702476731998177 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 32 type: NanoBEIR_mean_32 metrics: - type: cosine_accuracy@1 value: 0.3333333333333333 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.48666666666666664 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.5533333333333333 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.6533333333333333 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.3333333333333333 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.18888888888888888 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14933333333333335 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.10266666666666667 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.21168594281358166 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.3273175448732633 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.38052967151429246 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.45345060865249853 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.3861543460165353 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.43236507936507945 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.31022292071143664 name: Cosine 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: NanoMSMARCO 64 type: NanoMSMARCO_64 metrics: - type: cosine_accuracy@1 value: 0.42 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.66 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.42 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.13200000000000003 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.42 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.66 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.591232993639232 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5273015873015873 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5351182048005023 name: Cosine 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: NanoNFCorpus 64 type: NanoNFCorpus_64 metrics: - type: cosine_accuracy@1 value: 0.32 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.5 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.52 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.6 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.32 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2933333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.252 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.236 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.020044789335191174 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.04526010398813148 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.05627084683228478 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.08933472256987589 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.2628775829193256 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.4175000000000001 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.10566929023749187 name: Cosine 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: NanoNQ 64 type: NanoNQ_64 metrics: - type: cosine_accuracy@1 value: 0.4 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.62 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.66 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.72 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.20666666666666667 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.136 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.07600000000000001 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.38 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.58 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.61 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.67 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5342140484753161 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5065555555555555 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.49683164821698605 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 64 type: NanoBEIR_mean_64 metrics: - type: cosine_accuracy@1 value: 0.38000000000000006 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.5733333333333334 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6133333333333334 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7066666666666667 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.38000000000000006 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.2333333333333333 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.17333333333333334 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.13066666666666668 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.2733482631117304 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.4084200346627105 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.44209028227742825 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5197782408566253 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4627748750112912 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.48378571428571426 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.37920638108499344 name: Cosine 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: NanoMSMARCO 128 type: NanoMSMARCO_128 metrics: - type: cosine_accuracy@1 value: 0.34 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.64 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.68 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.34 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.21333333333333332 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.136 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.34 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.64 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.68 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.8 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5730777373893381 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5008015873015873 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5127463554963555 name: Cosine 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: NanoNFCorpus 128 type: NanoNFCorpus_128 metrics: - type: cosine_accuracy@1 value: 0.4 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.54 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.58 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.72 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.4 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.36666666666666664 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.308 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.276 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.04265347253746901 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.08086072465767052 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.0941496797136197 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.13775131432237744 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.33199374875578674 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.48576984126984124 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.15090058991053457 name: Cosine 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: NanoNQ 128 type: NanoNQ_128 metrics: - type: cosine_accuracy@1 value: 0.44 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.64 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.68 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.78 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.44 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.22 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14400000000000002 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08199999999999999 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.41 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.6 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.64 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.73 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5797743501932063 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5520714285714285 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.533573558140474 name: Cosine 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-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 128 type: NanoBEIR_mean_128 metrics: - type: cosine_accuracy@1 value: 0.3933333333333333 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6066666666666668 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.6466666666666666 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.7666666666666666 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.3933333333333333 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.26666666666666666 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19600000000000004 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.14600000000000002 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.26421782417915635 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.4402869082192235 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.47138322657120657 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5559171047741258 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.494948612112777 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5128809523809523 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.39907350118245466 name: Cosine 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: NanoMSMARCO 256 type: NanoMSMARCO_256 metrics: - type: cosine_accuracy@1 value: 0.36 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.62 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.7 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.84 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.36 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.20666666666666667 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.14 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08399999999999999 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.36 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.62 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.7 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.84 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.5934641617159162 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5158809523809523 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5228335563036209 name: Cosine 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 - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: NanoNFCorpus 256 type: NanoNFCorpus_256 metrics: - type: cosine_accuracy@1 value: 0.46 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.62 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.74 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.78 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.46 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.38666666666666666 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.364 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.29800000000000004 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.04750699466385613 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.08527169237328079 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.11543452383164411 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.1526866044864678 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.3632299338880757 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5608571428571427 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.16765768014542204 name: Cosine 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 - task: type: sparse-information-retrieval name: Sparse Information Retrieval dataset: name: NanoNQ 256 type: NanoNQ_256 metrics: - type: cosine_accuracy@1 value: 0.56 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.7 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.76 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.82 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.56 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.24666666666666665 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.16 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.08799999999999997 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.52 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.67 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.72 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.78 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.664653961269068 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.6482222222222223 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.6252713508893053 name: Cosine 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 - task: type: sparse-nano-beir name: Sparse Nano BEIR dataset: name: NanoBEIR mean 256 type: NanoBEIR_mean_256 metrics: - type: cosine_accuracy@1 value: 0.46 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.6466666666666666 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.7333333333333334 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.8133333333333334 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.46 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.27999999999999997 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.22133333333333335 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.15666666666666665 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.30916899822128535 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.4584238974577603 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.5118115079438813 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5908955348288226 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.54044935229102 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.5749867724867724 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.43858752911278276 name: Cosine 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:** Cosine Similarity - **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") # 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([[0.6570, 0.1768, 0.1651]]) ``` ## Evaluation ### Metrics #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_4`, `NanoNFCorpus_4` and `NanoNQ_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 | NanoMSMARCO_4 | NanoNFCorpus_4 | NanoNQ_4 | |:----------------------|:--------------|:---------------|:-----------| | cosine_accuracy@1 | 0.12 | 0.06 | 0.04 | | cosine_accuracy@3 | 0.16 | 0.14 | 0.08 | | cosine_accuracy@5 | 0.26 | 0.24 | 0.16 | | cosine_accuracy@10 | 0.34 | 0.3 | 0.26 | | cosine_precision@1 | 0.12 | 0.06 | 0.04 | | cosine_precision@3 | 0.0533 | 0.06 | 0.0267 | | cosine_precision@5 | 0.052 | 0.068 | 0.032 | | cosine_precision@10 | 0.034 | 0.064 | 0.026 | | cosine_recall@1 | 0.12 | 0.0009 | 0.04 | | cosine_recall@3 | 0.16 | 0.0034 | 0.08 | | cosine_recall@5 | 0.26 | 0.0076 | 0.16 | | cosine_recall@10 | 0.34 | 0.015 | 0.25 | | **cosine_ndcg@10** | **0.2085** | **0.0642** | **0.1245** | | cosine_mrr@10 | 0.1689 | 0.1274 | 0.0876 | | cosine_map@100 | 0.1829 | 0.0146 | 0.0994 | | query_active_dims | 4.0 | 4.0 | 4.0 | | query_sparsity_ratio | 0.999 | 0.999 | 0.999 | | corpus_active_dims | 4.0 | 4.0 | 4.0 | | corpus_sparsity_ratio | 0.999 | 0.999 | 0.999 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_4` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 4 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.0733 | | cosine_accuracy@3 | 0.1267 | | cosine_accuracy@5 | 0.22 | | cosine_accuracy@10 | 0.3 | | cosine_precision@1 | 0.0733 | | cosine_precision@3 | 0.0467 | | cosine_precision@5 | 0.0507 | | cosine_precision@10 | 0.0413 | | cosine_recall@1 | 0.0536 | | cosine_recall@3 | 0.0811 | | cosine_recall@5 | 0.1425 | | cosine_recall@10 | 0.2017 | | **cosine_ndcg@10** | **0.1324** | | cosine_mrr@10 | 0.128 | | cosine_map@100 | 0.099 | | query_active_dims | 4.0 | | query_sparsity_ratio | 0.999 | | corpus_active_dims | 4.0 | | corpus_sparsity_ratio | 0.999 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_8`, `NanoNFCorpus_8` and `NanoNQ_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 | NanoMSMARCO_8 | NanoNFCorpus_8 | NanoNQ_8 | |:----------------------|:--------------|:---------------|:-----------| | cosine_accuracy@1 | 0.14 | 0.08 | 0.08 | | cosine_accuracy@3 | 0.24 | 0.24 | 0.24 | | cosine_accuracy@5 | 0.32 | 0.32 | 0.3 | | cosine_accuracy@10 | 0.42 | 0.4 | 0.44 | | cosine_precision@1 | 0.14 | 0.08 | 0.08 | | cosine_precision@3 | 0.08 | 0.1067 | 0.08 | | cosine_precision@5 | 0.064 | 0.1 | 0.06 | | cosine_precision@10 | 0.042 | 0.082 | 0.046 | | cosine_recall@1 | 0.14 | 0.0035 | 0.08 | | cosine_recall@3 | 0.24 | 0.0133 | 0.22 | | cosine_recall@5 | 0.32 | 0.0186 | 0.28 | | cosine_recall@10 | 0.42 | 0.0275 | 0.42 | | **cosine_ndcg@10** | **0.2598** | **0.0864** | **0.2377** | | cosine_mrr@10 | 0.2109 | 0.1676 | 0.1862 | | cosine_map@100 | 0.2209 | 0.0273 | 0.187 | | query_active_dims | 8.0 | 8.0 | 8.0 | | query_sparsity_ratio | 0.998 | 0.998 | 0.998 | | corpus_active_dims | 8.0 | 8.0 | 8.0 | | corpus_sparsity_ratio | 0.998 | 0.998 | 0.998 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_8` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 8 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.1 | | cosine_accuracy@3 | 0.24 | | cosine_accuracy@5 | 0.3133 | | cosine_accuracy@10 | 0.42 | | cosine_precision@1 | 0.1 | | cosine_precision@3 | 0.0889 | | cosine_precision@5 | 0.0747 | | cosine_precision@10 | 0.0567 | | cosine_recall@1 | 0.0745 | | cosine_recall@3 | 0.1578 | | cosine_recall@5 | 0.2062 | | cosine_recall@10 | 0.2892 | | **cosine_ndcg@10** | **0.1946** | | cosine_mrr@10 | 0.1882 | | cosine_map@100 | 0.1451 | | query_active_dims | 8.0 | | query_sparsity_ratio | 0.998 | | corpus_active_dims | 8.0 | | corpus_sparsity_ratio | 0.998 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_16`, `NanoNFCorpus_16` and `NanoNQ_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 | NanoMSMARCO_16 | NanoNFCorpus_16 | NanoNQ_16 | |:----------------------|:---------------|:----------------|:-----------| | cosine_accuracy@1 | 0.22 | 0.18 | 0.22 | | cosine_accuracy@3 | 0.48 | 0.34 | 0.32 | | cosine_accuracy@5 | 0.58 | 0.44 | 0.36 | | cosine_accuracy@10 | 0.7 | 0.54 | 0.5 | | cosine_precision@1 | 0.22 | 0.18 | 0.22 | | cosine_precision@3 | 0.16 | 0.1533 | 0.1067 | | cosine_precision@5 | 0.116 | 0.144 | 0.072 | | cosine_precision@10 | 0.07 | 0.124 | 0.052 | | cosine_recall@1 | 0.22 | 0.0066 | 0.22 | | cosine_recall@3 | 0.48 | 0.0151 | 0.3 | | cosine_recall@5 | 0.58 | 0.0238 | 0.33 | | cosine_recall@10 | 0.7 | 0.0392 | 0.48 | | **cosine_ndcg@10** | **0.457** | **0.1345** | **0.3305** | | cosine_mrr@10 | 0.3796 | 0.2814 | 0.2882 | | cosine_map@100 | 0.3855 | 0.0403 | 0.2997 | | query_active_dims | 16.0 | 16.0 | 16.0 | | query_sparsity_ratio | 0.9961 | 0.9961 | 0.9961 | | corpus_active_dims | 16.0 | 16.0 | 16.0 | | corpus_sparsity_ratio | 0.9961 | 0.9961 | 0.9961 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_16` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 16 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.2067 | | cosine_accuracy@3 | 0.38 | | cosine_accuracy@5 | 0.46 | | cosine_accuracy@10 | 0.58 | | cosine_precision@1 | 0.2067 | | cosine_precision@3 | 0.14 | | cosine_precision@5 | 0.1107 | | cosine_precision@10 | 0.082 | | cosine_recall@1 | 0.1489 | | cosine_recall@3 | 0.265 | | cosine_recall@5 | 0.3113 | | cosine_recall@10 | 0.4064 | | **cosine_ndcg@10** | **0.3073** | | cosine_mrr@10 | 0.3164 | | cosine_map@100 | 0.2419 | | query_active_dims | 16.0 | | query_sparsity_ratio | 0.9961 | | corpus_active_dims | 16.0 | | corpus_sparsity_ratio | 0.9961 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_32`, `NanoNFCorpus_32` and `NanoNQ_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 | NanoMSMARCO_32 | NanoNFCorpus_32 | NanoNQ_32 | |:----------------------|:---------------|:----------------|:-----------| | cosine_accuracy@1 | 0.36 | 0.36 | 0.28 | | cosine_accuracy@3 | 0.58 | 0.48 | 0.4 | | cosine_accuracy@5 | 0.62 | 0.52 | 0.52 | | cosine_accuracy@10 | 0.7 | 0.64 | 0.62 | | cosine_precision@1 | 0.36 | 0.36 | 0.28 | | cosine_precision@3 | 0.1933 | 0.24 | 0.1333 | | cosine_precision@5 | 0.124 | 0.22 | 0.104 | | cosine_precision@10 | 0.07 | 0.172 | 0.066 | | cosine_recall@1 | 0.36 | 0.0151 | 0.26 | | cosine_recall@3 | 0.58 | 0.032 | 0.37 | | cosine_recall@5 | 0.62 | 0.0516 | 0.47 | | cosine_recall@10 | 0.7 | 0.0704 | 0.59 | | **cosine_ndcg@10** | **0.5319** | **0.2104** | **0.4161** | | cosine_mrr@10 | 0.4783 | 0.4425 | 0.3762 | | cosine_map@100 | 0.4895 | 0.0709 | 0.3702 | | query_active_dims | 32.0 | 32.0 | 32.0 | | query_sparsity_ratio | 0.9922 | 0.9922 | 0.9922 | | corpus_active_dims | 32.0 | 32.0 | 32.0 | | corpus_sparsity_ratio | 0.9922 | 0.9922 | 0.9922 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_32` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 32 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.3333 | | cosine_accuracy@3 | 0.4867 | | cosine_accuracy@5 | 0.5533 | | cosine_accuracy@10 | 0.6533 | | cosine_precision@1 | 0.3333 | | cosine_precision@3 | 0.1889 | | cosine_precision@5 | 0.1493 | | cosine_precision@10 | 0.1027 | | cosine_recall@1 | 0.2117 | | cosine_recall@3 | 0.3273 | | cosine_recall@5 | 0.3805 | | cosine_recall@10 | 0.4535 | | **cosine_ndcg@10** | **0.3862** | | cosine_mrr@10 | 0.4324 | | cosine_map@100 | 0.3102 | | query_active_dims | 32.0 | | query_sparsity_ratio | 0.9922 | | corpus_active_dims | 32.0 | | corpus_sparsity_ratio | 0.9922 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_64`, `NanoNFCorpus_64` and `NanoNQ_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 | NanoMSMARCO_64 | NanoNFCorpus_64 | NanoNQ_64 | |:----------------------|:---------------|:----------------|:-----------| | cosine_accuracy@1 | 0.42 | 0.32 | 0.4 | | cosine_accuracy@3 | 0.6 | 0.5 | 0.62 | | cosine_accuracy@5 | 0.66 | 0.52 | 0.66 | | cosine_accuracy@10 | 0.8 | 0.6 | 0.72 | | cosine_precision@1 | 0.42 | 0.32 | 0.4 | | cosine_precision@3 | 0.2 | 0.2933 | 0.2067 | | cosine_precision@5 | 0.132 | 0.252 | 0.136 | | cosine_precision@10 | 0.08 | 0.236 | 0.076 | | cosine_recall@1 | 0.42 | 0.02 | 0.38 | | cosine_recall@3 | 0.6 | 0.0453 | 0.58 | | cosine_recall@5 | 0.66 | 0.0563 | 0.61 | | cosine_recall@10 | 0.8 | 0.0893 | 0.67 | | **cosine_ndcg@10** | **0.5912** | **0.2629** | **0.5342** | | cosine_mrr@10 | 0.5273 | 0.4175 | 0.5066 | | cosine_map@100 | 0.5351 | 0.1057 | 0.4968 | | query_active_dims | 64.0 | 64.0 | 64.0 | | query_sparsity_ratio | 0.9844 | 0.9844 | 0.9844 | | corpus_active_dims | 64.0 | 64.0 | 64.0 | | corpus_sparsity_ratio | 0.9844 | 0.9844 | 0.9844 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_64` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 64 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.38 | | cosine_accuracy@3 | 0.5733 | | cosine_accuracy@5 | 0.6133 | | cosine_accuracy@10 | 0.7067 | | cosine_precision@1 | 0.38 | | cosine_precision@3 | 0.2333 | | cosine_precision@5 | 0.1733 | | cosine_precision@10 | 0.1307 | | cosine_recall@1 | 0.2733 | | cosine_recall@3 | 0.4084 | | cosine_recall@5 | 0.4421 | | cosine_recall@10 | 0.5198 | | **cosine_ndcg@10** | **0.4628** | | cosine_mrr@10 | 0.4838 | | cosine_map@100 | 0.3792 | | query_active_dims | 64.0 | | query_sparsity_ratio | 0.9844 | | corpus_active_dims | 64.0 | | corpus_sparsity_ratio | 0.9844 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_128`, `NanoNFCorpus_128` and `NanoNQ_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 | NanoMSMARCO_128 | NanoNFCorpus_128 | NanoNQ_128 | |:----------------------|:----------------|:-----------------|:-----------| | cosine_accuracy@1 | 0.34 | 0.4 | 0.44 | | cosine_accuracy@3 | 0.64 | 0.54 | 0.64 | | cosine_accuracy@5 | 0.68 | 0.58 | 0.68 | | cosine_accuracy@10 | 0.8 | 0.72 | 0.78 | | cosine_precision@1 | 0.34 | 0.4 | 0.44 | | cosine_precision@3 | 0.2133 | 0.3667 | 0.22 | | cosine_precision@5 | 0.136 | 0.308 | 0.144 | | cosine_precision@10 | 0.08 | 0.276 | 0.082 | | cosine_recall@1 | 0.34 | 0.0427 | 0.41 | | cosine_recall@3 | 0.64 | 0.0809 | 0.6 | | cosine_recall@5 | 0.68 | 0.0941 | 0.64 | | cosine_recall@10 | 0.8 | 0.1378 | 0.73 | | **cosine_ndcg@10** | **0.5731** | **0.332** | **0.5798** | | cosine_mrr@10 | 0.5008 | 0.4858 | 0.5521 | | cosine_map@100 | 0.5127 | 0.1509 | 0.5336 | | query_active_dims | 128.0 | 128.0 | 128.0 | | query_sparsity_ratio | 0.9688 | 0.9688 | 0.9688 | | corpus_active_dims | 128.0 | 128.0 | 128.0 | | corpus_sparsity_ratio | 0.9688 | 0.9688 | 0.9688 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_128` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 128 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.3933 | | cosine_accuracy@3 | 0.6067 | | cosine_accuracy@5 | 0.6467 | | cosine_accuracy@10 | 0.7667 | | cosine_precision@1 | 0.3933 | | cosine_precision@3 | 0.2667 | | cosine_precision@5 | 0.196 | | cosine_precision@10 | 0.146 | | cosine_recall@1 | 0.2642 | | cosine_recall@3 | 0.4403 | | cosine_recall@5 | 0.4714 | | cosine_recall@10 | 0.5559 | | **cosine_ndcg@10** | **0.4949** | | cosine_mrr@10 | 0.5129 | | cosine_map@100 | 0.3991 | | query_active_dims | 128.0 | | query_sparsity_ratio | 0.9688 | | corpus_active_dims | 128.0 | | corpus_sparsity_ratio | 0.9688 | #### Sparse Information Retrieval * Datasets: `NanoMSMARCO_256`, `NanoNFCorpus_256` and `NanoNQ_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 | NanoMSMARCO_256 | NanoNFCorpus_256 | NanoNQ_256 | |:----------------------|:----------------|:-----------------|:-----------| | cosine_accuracy@1 | 0.36 | 0.46 | 0.56 | | cosine_accuracy@3 | 0.62 | 0.62 | 0.7 | | cosine_accuracy@5 | 0.7 | 0.74 | 0.76 | | cosine_accuracy@10 | 0.84 | 0.78 | 0.82 | | cosine_precision@1 | 0.36 | 0.46 | 0.56 | | cosine_precision@3 | 0.2067 | 0.3867 | 0.2467 | | cosine_precision@5 | 0.14 | 0.364 | 0.16 | | cosine_precision@10 | 0.084 | 0.298 | 0.088 | | cosine_recall@1 | 0.36 | 0.0475 | 0.52 | | cosine_recall@3 | 0.62 | 0.0853 | 0.67 | | cosine_recall@5 | 0.7 | 0.1154 | 0.72 | | cosine_recall@10 | 0.84 | 0.1527 | 0.78 | | **cosine_ndcg@10** | **0.5935** | **0.3632** | **0.6647** | | cosine_mrr@10 | 0.5159 | 0.5609 | 0.6482 | | cosine_map@100 | 0.5228 | 0.1677 | 0.6253 | | query_active_dims | 256.0 | 256.0 | 256.0 | | query_sparsity_ratio | 0.9375 | 0.9375 | 0.9375 | | corpus_active_dims | 256.0 | 256.0 | 256.0 | | corpus_sparsity_ratio | 0.9375 | 0.9375 | 0.9375 | #### Sparse Nano BEIR * Dataset: `NanoBEIR_mean_256` * Evaluated with [SparseNanoBEIREvaluator](https://sbert.net/docs/package_reference/sparse_encoder/evaluation.html#sentence_transformers.sparse_encoder.evaluation.SparseNanoBEIREvaluator) with these parameters: ```json { "dataset_names": [ "msmarco", "nfcorpus", "nq" ], "max_active_dims": 256 } ``` | Metric | Value | |:----------------------|:-----------| | cosine_accuracy@1 | 0.46 | | cosine_accuracy@3 | 0.6467 | | cosine_accuracy@5 | 0.7333 | | cosine_accuracy@10 | 0.8133 | | cosine_precision@1 | 0.46 | | cosine_precision@3 | 0.28 | | cosine_precision@5 | 0.2213 | | cosine_precision@10 | 0.1567 | | cosine_recall@1 | 0.3092 | | cosine_recall@3 | 0.4584 | | cosine_recall@5 | 0.5118 | | cosine_recall@10 | 0.5909 | | **cosine_ndcg@10** | **0.5404** | | cosine_mrr@10 | 0.575 | | cosine_map@100 | 0.4386 | | 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=20.0, similarity_fct='cos_sim')" } ``` ### 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=20.0, similarity_fct='cos_sim')" } ``` ### 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 | NanoMSMARCO_4_cosine_ndcg@10 | NanoNFCorpus_4_cosine_ndcg@10 | NanoNQ_4_cosine_ndcg@10 | NanoBEIR_mean_4_cosine_ndcg@10 | NanoMSMARCO_8_cosine_ndcg@10 | NanoNFCorpus_8_cosine_ndcg@10 | NanoNQ_8_cosine_ndcg@10 | NanoBEIR_mean_8_cosine_ndcg@10 | NanoMSMARCO_16_cosine_ndcg@10 | NanoNFCorpus_16_cosine_ndcg@10 | NanoNQ_16_cosine_ndcg@10 | NanoBEIR_mean_16_cosine_ndcg@10 | NanoMSMARCO_32_cosine_ndcg@10 | NanoNFCorpus_32_cosine_ndcg@10 | NanoNQ_32_cosine_ndcg@10 | NanoBEIR_mean_32_cosine_ndcg@10 | NanoMSMARCO_64_cosine_ndcg@10 | NanoNFCorpus_64_cosine_ndcg@10 | NanoNQ_64_cosine_ndcg@10 | NanoBEIR_mean_64_cosine_ndcg@10 | NanoMSMARCO_128_cosine_ndcg@10 | NanoNFCorpus_128_cosine_ndcg@10 | NanoNQ_128_cosine_ndcg@10 | NanoBEIR_mean_128_cosine_ndcg@10 | NanoMSMARCO_256_cosine_ndcg@10 | NanoNFCorpus_256_cosine_ndcg@10 | NanoNQ_256_cosine_ndcg@10 | NanoBEIR_mean_256_cosine_ndcg@10 | |:------:|:----:|:-------------:|:---------------:|:----------------------------:|:-----------------------------:|:-----------------------:|:------------------------------:|:----------------------------:|:-----------------------------:|:-----------------------:|:------------------------------:|:-----------------------------:|:------------------------------:|:------------------------:|:-------------------------------:|:-----------------------------:|:------------------------------:|:------------------------:|:-------------------------------:|:-----------------------------:|:------------------------------:|:------------------------:|:-------------------------------:|:------------------------------:|:-------------------------------:|:-------------------------:|:--------------------------------:|:------------------------------:|:-------------------------------:|:-------------------------:|:--------------------------------:| | -1 | -1 | - | - | 0.1587 | 0.0673 | 0.0962 | 0.1074 | 0.2787 | 0.0843 | 0.2254 | 0.1962 | 0.4270 | 0.1786 | 0.3601 | 0.3219 | 0.5226 | 0.2079 | 0.4714 | 0.4006 | 0.6018 | 0.2616 | 0.5733 | 0.4789 | 0.6019 | 0.3201 | 0.6425 | 0.5215 | 0.6480 | 0.3496 | 0.6699 | 0.5558 | | 0.0646 | 100 | 0.3153 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.1293 | 200 | 0.2764 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.1939 | 300 | 0.2646 | 0.2497 | 0.1417 | 0.0671 | 0.1031 | 0.1040 | 0.2714 | 0.1042 | 0.2025 | 0.1927 | 0.3948 | 0.1421 | 0.3478 | 0.2949 | 0.5338 | 0.1954 | 0.4266 | 0.3852 | 0.6107 | 0.2885 | 0.5707 | 0.4900 | 0.5864 | 0.3582 | 0.6326 | 0.5257 | 0.6045 | 0.3607 | 0.6362 | 0.5338 | | 0.2586 | 400 | 0.2572 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.3232 | 500 | 0.2521 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.3878 | 600 | 0.2485 | 0.2365 | 0.1768 | 0.0722 | 0.1584 | 0.1358 | 0.2110 | 0.0697 | 0.2194 | 0.1667 | 0.3999 | 0.1301 | 0.3274 | 0.2858 | 0.5493 | 0.2184 | 0.4476 | 0.4051 | 0.5867 | 0.2808 | 0.5253 | 0.4643 | 0.5823 | 0.3298 | 0.5948 | 0.5023 | 0.5816 | 0.3532 | 0.6561 | 0.5303 | | 0.4525 | 700 | 0.2456 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.5171 | 800 | 0.2431 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.5818 | 900 | 0.2412 | 0.2301 | 0.1837 | 0.0763 | 0.1371 | 0.1324 | 0.2875 | 0.0834 | 0.2195 | 0.1968 | 0.4224 | 0.1298 | 0.3448 | 0.2990 | 0.5197 | 0.2075 | 0.4749 | 0.4007 | 0.6067 | 0.2714 | 0.5342 | 0.4708 | 0.6101 | 0.3247 | 0.6003 | 0.5117 | 0.5662 | 0.3652 | 0.6407 | 0.5240 | | 0.6464 | 1000 | 0.2397 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.7111 | 1100 | 0.2378 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.7757 | 1200 | 0.2375 | 0.2267 | 0.1783 | 0.0569 | 0.1241 | 0.1198 | 0.2543 | 0.1010 | 0.1927 | 0.1827 | 0.4190 | 0.1357 | 0.3332 | 0.2959 | 0.5284 | 0.2205 | 0.4416 | 0.3968 | 0.5786 | 0.2487 | 0.5570 | 0.4614 | 0.5783 | 0.3295 | 0.6148 | 0.5075 | 0.5860 | 0.3670 | 0.6558 | 0.5363 | | 0.8403 | 1300 | 0.2372 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.9050 | 1400 | 0.2357 | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | - | | 0.9696 | 1500 | 0.236 | 0.2255 | 0.2011 | 0.0670 | 0.1246 | 0.1309 | 0.2540 | 0.0858 | 0.2371 | 0.1923 | 0.4558 | 0.1372 | 0.3172 | 0.3034 | 0.5263 | 0.2110 | 0.4061 | 0.3811 | 0.5971 | 0.2639 | 0.5188 | 0.4599 | 0.5752 | 0.3326 | 0.5755 | 0.4945 | 0.5886 | 0.3658 | 0.6536 | 0.5360 | | -1 | -1 | - | - | 0.2085 | 0.0642 | 0.1245 | 0.1324 | 0.2598 | 0.0864 | 0.2377 | 0.1946 | 0.4570 | 0.1345 | 0.3305 | 0.3073 | 0.5319 | 0.2104 | 0.4161 | 0.3862 | 0.5912 | 0.2629 | 0.5342 | 0.4628 | 0.5731 | 0.3320 | 0.5798 | 0.4949 | 0.5935 | 0.3632 | 0.6647 | 0.5404 | ### Environmental Impact Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon). - **Energy Consumed**: 0.272 kWh - **Carbon Emitted**: 0.106 kg of CO2 - **Hours Used**: 0.75 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} } ```