| --- |
| tags: |
| - ColBERT |
| - PyLate |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - generated_from_trainer |
| - dataset_size:10000000 |
| - loss:Contrastive |
| base_model: answerdotai/ModernBERT-base |
| datasets: |
| - bclavie/msmarco-10m-triplets |
| pipeline_tag: sentence-similarity |
| library_name: PyLate |
| metrics: |
| - MaxSim_accuracy@1 |
| - MaxSim_accuracy@3 |
| - MaxSim_accuracy@5 |
| - MaxSim_accuracy@10 |
| - MaxSim_precision@1 |
| - MaxSim_precision@3 |
| - MaxSim_precision@5 |
| - MaxSim_precision@10 |
| - MaxSim_recall@1 |
| - MaxSim_recall@3 |
| - MaxSim_recall@5 |
| - MaxSim_recall@10 |
| - MaxSim_ndcg@10 |
| - MaxSim_mrr@10 |
| - MaxSim_map@100 |
| model-index: |
| - name: PyLate model based on answerdotai/ModernBERT-base |
| results: |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoClimateFEVER |
| type: NanoClimateFEVER |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.3 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.46 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.54 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.72 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.3 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.15999999999999998 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.12800000000000003 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.09399999999999999 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.145 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.20066666666666666 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.25566666666666665 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.3723333333333333 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.29984094041575976 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.40457936507936504 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.23154243919711487 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoDBPedia |
| type: NanoDBPedia |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.84 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.92 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.92 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.92 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.84 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.6599999999999998 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.6000000000000001 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.53 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.11978017136836354 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.19320640931807406 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.2474564677729374 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.35362762531754766 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.6642857997687286 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.8766666666666666 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.5056362918461486 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoFEVER |
| type: NanoFEVER |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.86 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 1.0 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 1.0 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 1.0 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.86 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.34666666666666657 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.20799999999999996 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.10799999999999997 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.8066666666666668 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.9566666666666667 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.9566666666666667 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.9733333333333333 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.9143032727772558 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.92 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.8848835412953059 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoFiQA2018 |
| type: NanoFiQA2018 |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.5 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.68 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.72 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.8 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.5 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.33333333333333326 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.236 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.14 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.29724603174603176 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.49257142857142855 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.5465079365079365 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.6031746031746033 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.5453834796894957 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.604079365079365 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.49074315182112516 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoHotpotQA |
| type: NanoHotpotQA |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.9 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.96 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.96 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 1.0 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.9 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.5266666666666666 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.32799999999999996 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.17799999999999996 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.45 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.79 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.82 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.89 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.8430810883372716 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.9353571428571428 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.778500350140056 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoMSMARCO |
| type: NanoMSMARCO |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.48 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.7 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.74 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.9 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.48 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.2333333333333333 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.14800000000000002 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.08999999999999998 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.48 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.7 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.74 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.9 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.681981684088073 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.6141031746031747 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.6195014186409419 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoNFCorpus |
| type: NanoNFCorpus |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.48 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.54 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.62 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.7 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.48 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.37333333333333335 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.36 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.29 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.024846700166746567 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.06745637325640307 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.1008052160248601 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.1497664943203363 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.34867256192135143 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.5346031746031746 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.13572305233276538 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoNQ |
| type: NanoNQ |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.54 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.8 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.86 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.9 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.54 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.2733333333333333 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.17599999999999993 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.09599999999999997 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.51 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.75 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.81 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.86 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.7009621199364733 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.6670238095238094 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.6421027387645034 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoQuoraRetrieval |
| type: NanoQuoraRetrieval |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.9 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.98 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.98 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 1.0 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.9 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.38666666666666655 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.24799999999999997 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.13799999999999998 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.7973333333333333 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.9246666666666666 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.9426666666666668 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.9966666666666666 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.9436609396356616 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.9366666666666665 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.9184467532467532 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoSCIDOCS |
| type: NanoSCIDOCS |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.44 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.66 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.68 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.8 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.44 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.31999999999999995 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.236 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.166 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.09366666666666668 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.19866666666666666 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.24366666666666664 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.3396666666666667 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.3404490877439103 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.5581666666666668 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.2561512796776031 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoArguAna |
| type: NanoArguAna |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.22 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.52 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.64 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.8 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.22 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.1733333333333333 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.128 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.08 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.22 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.52 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.64 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.8 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.4988624746761941 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.40369047619047616 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.40858139686400563 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoSciFact |
| type: NanoSciFact |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.7 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.8 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.84 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.88 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.7 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.2866666666666666 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.184 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.09799999999999999 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.675 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.785 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.825 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.87 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.7836102750432731 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.7577777777777777 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.7575977078477077 |
| name: Maxsim Map@100 |
| - task: |
| type: py-late-information-retrieval |
| name: Py Late Information Retrieval |
| dataset: |
| name: NanoTouche2020 |
| type: NanoTouche2020 |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.7551020408163265 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.9795918367346939 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.9795918367346939 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.9795918367346939 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.7551020408163265 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.7142857142857143 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.6204081632653061 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.5061224489795919 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.05215472128680775 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.14371450561336085 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.20898774766999936 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.3295518520522591 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.5852674107635566 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.8639455782312924 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.43897324704873364 |
| name: Maxsim Map@100 |
| - task: |
| type: nano-beir |
| name: Nano BEIR |
| dataset: |
| name: NanoBEIR mean |
| type: NanoBEIR_mean |
| metrics: |
| - type: MaxSim_accuracy@1 |
| value: 0.6088540031397175 |
| name: Maxsim Accuracy@1 |
| - type: MaxSim_accuracy@3 |
| value: 0.769199372056515 |
| name: Maxsim Accuracy@3 |
| - type: MaxSim_accuracy@5 |
| value: 0.8061224489795917 |
| name: Maxsim Accuracy@5 |
| - type: MaxSim_accuracy@10 |
| value: 0.8768916797488226 |
| name: Maxsim Accuracy@10 |
| - type: MaxSim_precision@1 |
| value: 0.6088540031397175 |
| name: Maxsim Precision@1 |
| - type: MaxSim_precision@3 |
| value: 0.3682783882783882 |
| name: Maxsim Precision@3 |
| - type: MaxSim_precision@5 |
| value: 0.27695447409733126 |
| name: Maxsim Precision@5 |
| - type: MaxSim_precision@10 |
| value: 0.19339403453689166 |
| name: Maxsim Precision@10 |
| - type: MaxSim_recall@1 |
| value: 0.35936109932573973 |
| name: Maxsim Recall@1 |
| - type: MaxSim_recall@3 |
| value: 0.5171242602635334 |
| name: Maxsim Recall@3 |
| - type: MaxSim_recall@5 |
| value: 0.5644172334340307 |
| name: Maxsim Recall@5 |
| - type: MaxSim_recall@10 |
| value: 0.6490861980665189 |
| name: Maxsim Recall@10 |
| - type: MaxSim_ndcg@10 |
| value: 0.6269508565228465 |
| name: Maxsim Ndcg@10 |
| - type: MaxSim_mrr@10 |
| value: 0.6982046049188907 |
| name: Maxsim Mrr@10 |
| - type: MaxSim_map@100 |
| value: 0.5437217975940587 |
| name: Maxsim Map@100 |
| --- |
| |
| # PyLate model based on answerdotai/ModernBERT-base |
|
|
| This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the [msmarco-10m-triplets](https://huggingface.co/datasets/bclavie/msmarco-10m-triplets) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. |
|
|
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** PyLate model |
| - **Base model:** [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) <!-- at revision 8949b909ec900327062f0ebf497f51aef5e6f0c8 --> |
| - **Document Length:** 512 tokens |
| - **Query Length:** 32 tokens |
| - **Output Dimensionality:** 128 tokens |
| - **Similarity Function:** MaxSim |
| - **Training Dataset:** |
| - [msmarco-10m-triplets](https://huggingface.co/datasets/bclavie/msmarco-10m-triplets) |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/) |
| - **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate) |
| - **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| ColBERT( |
| (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'ModernBertModel'}) |
| (1): Dense({'in_features': 768, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False}) |
| ) |
| ``` |
|
|
| ## Usage |
| First install the PyLate library: |
|
|
| ```bash |
| pip install -U pylate |
| ``` |
|
|
| ### Retrieval |
|
|
| Use this model with PyLate to index and retrieve documents. The index uses [FastPLAID](https://github.com/lightonai/fast-plaid) for efficient similarity search. |
|
|
| #### Indexing documents |
|
|
| Load the ColBERT model and initialize the PLAID index, then encode and index your documents: |
|
|
| ```python |
| from pylate import indexes, models, retrieve |
| |
| # Step 1: Load the ColBERT model |
| model = models.ColBERT( |
| model_name_or_path="pylate_model_id", |
| ) |
| |
| # Step 2: Initialize the PLAID index |
| index = indexes.PLAID( |
| index_folder="pylate-index", |
| index_name="index", |
| override=True, # This overwrites the existing index if any |
| ) |
| |
| # Step 3: Encode the documents |
| documents_ids = ["1", "2", "3"] |
| documents = ["document 1 text", "document 2 text", "document 3 text"] |
| |
| documents_embeddings = model.encode( |
| documents, |
| batch_size=32, |
| is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries |
| show_progress_bar=True, |
| ) |
| |
| # Step 4: Add document embeddings to the index by providing embeddings and corresponding ids |
| index.add_documents( |
| documents_ids=documents_ids, |
| documents_embeddings=documents_embeddings, |
| ) |
| ``` |
|
|
| Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it: |
|
|
| ```python |
| # To load an index, simply instantiate it with the correct folder/name and without overriding it |
| index = indexes.PLAID( |
| index_folder="pylate-index", |
| index_name="index", |
| ) |
| ``` |
|
|
| #### Retrieving top-k documents for queries |
|
|
| Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. |
| To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores: |
|
|
| ```python |
| # Step 1: Initialize the ColBERT retriever |
| retriever = retrieve.ColBERT(index=index) |
| |
| # Step 2: Encode the queries |
| queries_embeddings = model.encode( |
| ["query for document 3", "query for document 1"], |
| batch_size=32, |
| is_query=True, # # Ensure that it is set to False to indicate that these are queries |
| show_progress_bar=True, |
| ) |
| |
| # Step 3: Retrieve top-k documents |
| scores = retriever.retrieve( |
| queries_embeddings=queries_embeddings, |
| k=10, # Retrieve the top 10 matches for each query |
| ) |
| ``` |
|
|
| ### Reranking |
| If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank: |
|
|
| ```python |
| from pylate import rank, models |
| |
| queries = [ |
| "query A", |
| "query B", |
| ] |
| |
| documents = [ |
| ["document A", "document B"], |
| ["document 1", "document C", "document B"], |
| ] |
| |
| documents_ids = [ |
| [1, 2], |
| [1, 3, 2], |
| ] |
| |
| model = models.ColBERT( |
| model_name_or_path="pylate_model_id", |
| ) |
| |
| queries_embeddings = model.encode( |
| queries, |
| is_query=True, |
| ) |
| |
| documents_embeddings = model.encode( |
| documents, |
| is_query=False, |
| ) |
| |
| reranked_documents = rank.rerank( |
| documents_ids=documents_ids, |
| queries_embeddings=queries_embeddings, |
| documents_embeddings=documents_embeddings, |
| ) |
| ``` |
|
|
| <!-- |
| ### Direct Usage (Transformers) |
|
|
| <details><summary>Click to see the direct usage in Transformers</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Downstream Usage (Sentence Transformers) |
|
|
| You can finetune this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Out-of-Scope Use |
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| --> |
|
|
| ## Evaluation |
|
|
| ### Metrics |
|
|
| #### Py Late Information Retrieval |
| * Dataset: `['NanoClimateFEVER', 'NanoDBPedia', 'NanoFEVER', 'NanoFiQA2018', 'NanoHotpotQA', 'NanoMSMARCO', 'NanoNFCorpus', 'NanoNQ', 'NanoQuoraRetrieval', 'NanoSCIDOCS', 'NanoArguAna', 'NanoSciFact', 'NanoTouche2020']` |
| * Evaluated with <code>pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator</code> |
| |
| | Metric | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoFiQA2018 | NanoHotpotQA | NanoMSMARCO | NanoNFCorpus | NanoNQ | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 | |
| |:--------------------|:-----------------|:------------|:-----------|:-------------|:-------------|:------------|:-------------|:----------|:-------------------|:------------|:------------|:------------|:---------------| |
| | MaxSim_accuracy@1 | 0.3 | 0.84 | 0.86 | 0.5 | 0.9 | 0.48 | 0.48 | 0.54 | 0.9 | 0.44 | 0.22 | 0.7 | 0.7551 | |
| | MaxSim_accuracy@3 | 0.46 | 0.92 | 1.0 | 0.68 | 0.96 | 0.7 | 0.54 | 0.8 | 0.98 | 0.66 | 0.52 | 0.8 | 0.9796 | |
| | MaxSim_accuracy@5 | 0.54 | 0.92 | 1.0 | 0.72 | 0.96 | 0.74 | 0.62 | 0.86 | 0.98 | 0.68 | 0.64 | 0.84 | 0.9796 | |
| | MaxSim_accuracy@10 | 0.72 | 0.92 | 1.0 | 0.8 | 1.0 | 0.9 | 0.7 | 0.9 | 1.0 | 0.8 | 0.8 | 0.88 | 0.9796 | |
| | MaxSim_precision@1 | 0.3 | 0.84 | 0.86 | 0.5 | 0.9 | 0.48 | 0.48 | 0.54 | 0.9 | 0.44 | 0.22 | 0.7 | 0.7551 | |
| | MaxSim_precision@3 | 0.16 | 0.66 | 0.3467 | 0.3333 | 0.5267 | 0.2333 | 0.3733 | 0.2733 | 0.3867 | 0.32 | 0.1733 | 0.2867 | 0.7143 | |
| | MaxSim_precision@5 | 0.128 | 0.6 | 0.208 | 0.236 | 0.328 | 0.148 | 0.36 | 0.176 | 0.248 | 0.236 | 0.128 | 0.184 | 0.6204 | |
| | MaxSim_precision@10 | 0.094 | 0.53 | 0.108 | 0.14 | 0.178 | 0.09 | 0.29 | 0.096 | 0.138 | 0.166 | 0.08 | 0.098 | 0.5061 | |
| | MaxSim_recall@1 | 0.145 | 0.1198 | 0.8067 | 0.2972 | 0.45 | 0.48 | 0.0248 | 0.51 | 0.7973 | 0.0937 | 0.22 | 0.675 | 0.0522 | |
| | MaxSim_recall@3 | 0.2007 | 0.1932 | 0.9567 | 0.4926 | 0.79 | 0.7 | 0.0675 | 0.75 | 0.9247 | 0.1987 | 0.52 | 0.785 | 0.1437 | |
| | MaxSim_recall@5 | 0.2557 | 0.2475 | 0.9567 | 0.5465 | 0.82 | 0.74 | 0.1008 | 0.81 | 0.9427 | 0.2437 | 0.64 | 0.825 | 0.209 | |
| | MaxSim_recall@10 | 0.3723 | 0.3536 | 0.9733 | 0.6032 | 0.89 | 0.9 | 0.1498 | 0.86 | 0.9967 | 0.3397 | 0.8 | 0.87 | 0.3296 | |
| | **MaxSim_ndcg@10** | **0.2998** | **0.6643** | **0.9143** | **0.5454** | **0.8431** | **0.682** | **0.3487** | **0.701** | **0.9437** | **0.3404** | **0.4989** | **0.7836** | **0.5853** | |
| | MaxSim_mrr@10 | 0.4046 | 0.8767 | 0.92 | 0.6041 | 0.9354 | 0.6141 | 0.5346 | 0.667 | 0.9367 | 0.5582 | 0.4037 | 0.7578 | 0.8639 | |
| | MaxSim_map@100 | 0.2315 | 0.5056 | 0.8849 | 0.4907 | 0.7785 | 0.6195 | 0.1357 | 0.6421 | 0.9184 | 0.2562 | 0.4086 | 0.7576 | 0.439 | |
| |
| #### Nano BEIR |
| * Dataset: `NanoBEIR_mean` |
| * Evaluated with <code>pylate.evaluation.nano_beir_evaluator.NanoBEIREvaluator</code> |
|
|
| | Metric | Value | |
| |:--------------------|:----------| |
| | MaxSim_accuracy@1 | 0.6089 | |
| | MaxSim_accuracy@3 | 0.7692 | |
| | MaxSim_accuracy@5 | 0.8061 | |
| | MaxSim_accuracy@10 | 0.8769 | |
| | MaxSim_precision@1 | 0.6089 | |
| | MaxSim_precision@3 | 0.3683 | |
| | MaxSim_precision@5 | 0.277 | |
| | MaxSim_precision@10 | 0.1934 | |
| | MaxSim_recall@1 | 0.3594 | |
| | MaxSim_recall@3 | 0.5171 | |
| | MaxSim_recall@5 | 0.5644 | |
| | MaxSim_recall@10 | 0.6491 | |
| | **MaxSim_ndcg@10** | **0.627** | |
| | MaxSim_mrr@10 | 0.6982 | |
| | MaxSim_map@100 | 0.5437 | |
| |
| <!-- |
| ## Bias, Risks and Limitations |
| |
| *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
| --> |
| |
| <!-- |
| ### Recommendations |
| |
| *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
| --> |
| |
| ## Training Details |
| |
| ### Training Dataset |
| |
| #### msmarco-10m-triplets |
| |
| * Dataset: [msmarco-10m-triplets](https://huggingface.co/datasets/bclavie/msmarco-10m-triplets) at [8c5139a](https://huggingface.co/datasets/bclavie/msmarco-10m-triplets/tree/8c5139a245a5997992605792faa49ec12a6eb5f2) |
| * Size: 10,000,000 training samples |
| * Columns: <code>query</code>, <code>positive</code>, and <code>negative</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | query | positive | negative | |
| |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| |
| | type | string | string | string | |
| | details | <ul><li>min: 4 tokens</li><li>mean: 9.31 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 31.95 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 18 tokens</li><li>mean: 31.91 tokens</li><li>max: 32 tokens</li></ul> | |
| * Samples: |
| | query | positive | negative | |
| |:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| | <code>the most important factor that influences k+ secretion is __________.</code> | <code>The regulation of K+ distribution between the intracellular and extracellular space is referred to as internal K+ balance. The most important factors regulating this movement under normal conditions are insulin and catecholamines (1).</code> | <code>They are both also important for secretion and flow of bile: 1 Cholecystokinin: The name of this hormone describes its effect on the biliary system-cholecysto = gallbladder and kinin = movement. 2 Secretin: This hormone is secreted in response to acid in the duodenum.</code> | |
| | <code>how much did the mackinac bridge cost to build</code> | <code>The cost to design the project was $3,500,000 (Steinman Company). The cost to construct the bridge was $70, 268,500. Two primary contractors were hired to build the bridge: American Bridge for superstructure - $44,532,900; and Merritt-Chapman and Scott of New York for the foundations - $25,735,600.</code> | <code>When your child needs a dental tooth bridge, you need to know the average cost so you can factor the price into your budget. Several factors affect the price of a bridge, which can run between $700 to $1,500 per tooth. If you have insurance or your child is covered by Medicaid, part of the cost may be covered.</code> | |
| | <code>when do concussion symptoms appear</code> | <code>Then you can get advice on what to do next. For milder symptoms, the doctor may recommend rest and ask you to watch your child closely for changes, such as a headache that gets worse. Symptoms of a concussion don't always show up right away, and can develop within 24 to 72 hours after an injury.</code> | <code>Concussion: A traumatic injury to soft tissue, usually the brain, as a result of a violent blow, shaking, or spinning. A brain concussion can cause immediate but temporary impairment of brain functions, such as thinking, vision, equilibrium, and consciousness. After a person has had a concussion, he or she is at increased risk for recurrence. Moreover, after a person has several concussions, less of a blow can cause injury, and the person can require more time to recover.</code> | |
| * Loss: <code>pylate.losses.contrastive.Contrastive</code> |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `eval_strategy`: steps |
| - `per_device_train_batch_size`: 64 |
| - `learning_rate`: 3e-05 |
| - `max_steps`: 50000 |
| - `fp16`: True |
| - `dataloader_drop_last`: True |
| - `dataloader_num_workers`: 8 |
| - `ddp_find_unused_parameters`: False |
| - `torch_compile`: True |
| - `torch_compile_backend`: inductor |
| - `eval_on_start`: True |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `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`: 8 |
| - `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`: 3e-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`: 3.0 |
| - `max_steps`: 50000 |
| - `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`: False |
| - `fp16`: True |
| - `fp16_opt_level`: O1 |
| - `half_precision_backend`: auto |
| - `bf16_full_eval`: False |
| - `fp16_full_eval`: False |
| - `tf32`: None |
| - `local_rank`: 0 |
| - `ddp_backend`: None |
| - `tpu_num_cores`: None |
| - `tpu_metrics_debug`: False |
| - `debug`: [] |
| - `dataloader_drop_last`: True |
| - `dataloader_num_workers`: 8 |
| - `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} |
| - `parallelism_config`: 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`: False |
| - `ddp_bucket_cap_mb`: None |
| - `ddp_broadcast_buffers`: False |
| - `dataloader_pin_memory`: True |
| - `dataloader_persistent_workers`: False |
| - `skip_memory_metrics`: True |
| - `use_legacy_prediction_loop`: False |
| - `push_to_hub`: False |
| - `resume_from_checkpoint`: None |
| - `hub_model_id`: None |
| - `hub_strategy`: every_save |
| - `hub_private_repo`: None |
| - `hub_always_push`: False |
| - `hub_revision`: None |
| - `gradient_checkpointing`: False |
| - `gradient_checkpointing_kwargs`: None |
| - `include_inputs_for_metrics`: False |
| - `include_for_metrics`: [] |
| - `eval_do_concat_batches`: True |
| - `fp16_backend`: auto |
| - `push_to_hub_model_id`: None |
| - `push_to_hub_organization`: None |
| - `mp_parameters`: |
| - `auto_find_batch_size`: False |
| - `full_determinism`: False |
| - `torchdynamo`: None |
| - `ray_scope`: last |
| - `ddp_timeout`: 1800 |
| - `torch_compile`: True |
| - `torch_compile_backend`: inductor |
| - `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`: True |
| - `use_liger_kernel`: False |
| - `liger_kernel_config`: None |
| - `eval_use_gather_object`: False |
| - `average_tokens_across_devices`: False |
| - `prompts`: None |
| - `batch_sampler`: batch_sampler |
| - `multi_dataset_batch_sampler`: proportional |
| - `router_mapping`: {} |
| - `learning_rate_mapping`: {} |
| |
| </details> |
| |
| |
