--- language: - en license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:11518 - loss:MatryoshkaLoss - loss:MultipleNegativesRankingLoss base_model: nomic-ai/modernbert-embed-base widget: - source_sentence: "= little to no difference (low certainty)\n \t\n= little to no\ \ difference (moderate certainty)\n= benefit that meets threshold for clinically\ \ important difference (very low certainty) = benefit that meets threshold for\ \ clinically important difference (low certainty)\n\t\n= benefit that meets threshold\ \ for clinically important difference (moderate certainty).\n53\n4. Evidence and\ \ recommendations\nIntervention class B: Physical interventions •\t In the comparison\ \ of any structured \nexercise programme with usual care \n(6 trials), trivial\ \ benefits were observed for \npain and function. Since the certainty of the \n\ evidence was very low for other time-points and outcomes, it was uncertain whether\ \ \nany structured exercise programme: \n\t›\n\tdecreased pain in the immediate\ \ term \n(trivial effect);\n\t›\n\tmade little to no difference to pain in the\ \ short term or long term;\n\t›\n\timproved function in the immediate \nterm (trivial\ \ effect);\n\t›\n\tmade little to no difference to function \nin the short term;\ \ or\n\t› improved function in the long term. \nIn the two trials on older people,\ \ trivial \nbenefit was observed for function. Since the \ncertainty of the evidence\ \ was very low, it was uncertain whether any structured exercise \nprogramme:\n\ \t›\n\tmade little to no difference to pain in \nthe immediate term (2 trials)\ \ or short \nterm (1 trial);\n\t› improved function the immediate term \n(trivial\ \ effect, 2 trials); or\n\t›\n\tmade little to no difference to function \nin\ \ the short term (1 trial).\nIn the two trials that monitored harms," sentences: - voice functions assessment techniques and impairments - physiotherapy exercises for patients with casts - effectiveness of exercise on function in older adults - source_sentence: "Material resources \nOccupations \n(rehabilitation specialists)\ \ \nAssistive products\nEquipment \nConsumables \n Cardio­vascular and immunological\ \ functions\nTarget: Oedema control\nAssessment of oedema 10\n–\n•\tMeasuring\ \ tape\n–\n•\tNursing professional\n•\tOccupational therapist\n•\tPhysiotherapist\ \ \n•\tSpecialist medical practitioner/\nPRM physician\nRange of motion exercises\n\ 15 –\n•\tTreatment table\n–\n•\tOccupational therapist \n•\tPhysiotherapist \n\ Retrograde massage\n30\n–\n•\tTreatment table\n•\tPillows •\tFoam rollers/wedges\n\ •\tCompression bandages\n•\tMassage lotion\n•\tOccupational therapist\n•\tPhysiotherapist\n\ Positioning for oedema \ncontrol\n10\n– •\tPillows\n•\tFoam rollers/wedges\n–\n\ •\tNursing professional\n•\tOccupational therapist\n•\tPhysiotherapist\nProvision\ \ and training \nin the use of assistive products for compression \ntherapy\n\ 15\n•\tProducts for compression \ntherapy (garments, sockets, \nbandages)\n–\n\ –\n•\tNursing professional \n•\tOccupational therapist •\tPhysiotherapist \nMotor\ \ functions and mobility\nTarget: Mobility of joint functions\nAssessment of joint\ \ \nmobility\n10\n–\n•\tTreatment table\n•\tGoniometer\n•\tMeasuring tape\n–" sentences: - role of occupational therapists in oedema management - protective measures during plaster application plastic sheeting - materials needed for adult fracture immobilization with POP - source_sentence: "benefits offered.\n•\t There are potentially serious adverse events\ \ \nassociated with SNRI antidepressants \namong older people, including \nhyponatraemia,\ \ memory impairment, \ngastrointestinal events and falls, without evidence of\ \ benefit. \n127\n4. Evidence and recommendations\nIntervention class D: Medicines\n\ \t›\nIt was uncertain whether SNRI \nantidepressants made little to no \ndifference\ \ to work-related outcomes (low to very low certainty evidence).\nHarms were monitored\ \ across the trials and \nwere identified for nausea, constipation, \ndizziness\ \ and somnolence.\n\t›\n\tSNRI antidepressants were probably associated with a\ \ large increase in the \nlikelihood of discontinuation due to \nadverse events,\ \ nausea, constipation, \ndizziness and somnolence (moderate \ncertainty evidence).\ \ \n\t› It was uncertain whether SNRI \nantidepressants were associated with \n\ a small increased likelihood of serious \nadverse events (very low certainty \n\ evidence).\n•\t In the comparison of SNRI antidepressants (treatment duration\ \ < 12 weeks) with \nplacebo (5 trials, 263 participants), the \ncertainty of\ \ evidence was very low. It was \nuncertain whether SNRI antidepressants made\ \ little to no difference to pain or \npsychological well-being at < 1 month or\ \ at \n1–3 months; or to function or quality of life \nat 1–3 months. Harms were\ \ monitored in the included \ntrials, however, the certainty of evidence \nwas\ \ very low. It was therefore uncertain \nwhether SNRI antidepressants:\n\t›\n\ increased the likelihood of treatment" sentences: - does organic milk have more n-3 PUFA than non-organic - evidence-based recommendations for chronic low back pain management - SNRI antidepressants and work-related outcomes evidence - source_sentence: "Assessment of mobilityb\nMobility training (incl. wheelchair skills\ \ \ntraining)b\nFunctional positioningb\nProvision and training in the use of\ \ assistive \nproducts for mobilityb\nAssessment of hand and arm usec Functional\ \ training for hand and arm usec\nExercise and \nfitness\nAssessment of exercise\ \ capacityb\nFitness trainingb\nActivity of daily \nliving\nAssessment of activities\ \ of daily living \n(ADL)b ADL trainingb\nProvision and training in the use of\ \ assistive \nproducts for self-careb\nModification of the home environmentb\n\ [cont.]\n82\nAssessmentsa\nInterventionsa\nInterpersonal interactions and \nrelationships\n\ Assessment of interpersonal interactions \nand relationshipsb\nPsychological support/counsellingb\n\ Education and \nvocation\nEducational assessmentk\nEducational counselling, training,\ \ and supportk Modification of the school environmentk Vocational assessmentj\n\ Vocational counselling, training, and supportd\nProvision and training in the\ \ use of assistive \nproducts for workd\nModification of the workplace environmentd\n\ Community \nand social life Assessment of participation in \ncommunity and social\ \ lifeb\nParticipation focused interventionsb\nPeer supportb\nLifestyle \nmodification\n\ Assessment of lifestyle risk factorsb\nEducation and advice on healthy lifestyleb\n\ Self-\nmanagement Education, advice and support for self-\nmanagement of the health\ \ conditionb\nEducation and advice on self-directed \nexercisesb\nCarer and \n\ family support\nAssessment of carer and family needsl" sentences: - adverse events in dietary and exercise interventions - ACSM-CPT certification details - assistive products for daily living activities - source_sentence: "facilitate publication;\n• \aMobilise academic expertise for \n\ developing training programmes and \nmobilising trainers.\n\t Weigh in on the\ \ debate around issues \nrelated to rehabilitation promotion and funding, promote\ \ best practices to \ninfluence policies that favour access \nto rehabilitation\ \ services and thereby \nmove toward advocacy actions.\n48\nUsers,\nDisabled people’s\n\ organisations\nService\nproviders\nDecision-makers User \ngroups\nLocal\nauthorities\n\ Ministry of \nHealth, Ministry \nof Social Action,\netc.\nUnited Nations \n(WHO,\ \ etc.)\nHospitals, \nReference\nrehabilitation centre\nProfessional \nassociations\n\ Service provider groups\nTraining institutes\nCommunity- \nbased Services\nFederation\n\ and national\n associations\nHospital, \nHealth \ncare centres Network: actors\ \ that can be mobilised for physical \nand functional rehabilitation\nInternational\n\ National\nLocal\nInstitutional donors\nFacilitation organisations* * \aOrganisations\ \ (IOs, NGOs, etc.), agencies, universities and research centres that facilitate\ \ the existence of physical \nand functional rehabilitation via national or international\ \ projects.\nInternational \n consortia (IDDC, etc.)\n International\n\ \ networks \n (CBR, WCPT, \n WFOT, ISPO,\nFATO,\ \ etc.)\nLevels of intervention © Handicap International, 2013\n \n \n49\n Intervention.\n\  modalities .\nThe Unit has technical resources specifically \npositioned to be\ \ able to reach the maximum" sentences: - risks of yo-yo dieting and heart disease - training programmes for rehabilitation professionals - long-term effects of mobility assistive products on chronic low back pain pipeline_tag: sentence-similarity 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 model-index: - name: ModernBERT Embed base fitness health Matryoshka results: - task: type: information-retrieval name: Information Retrieval dataset: name: dim 768 type: dim_768 metrics: - type: cosine_accuracy@1 value: 0.47890625 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.47890625 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.47890625 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.521875 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.47890625 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.47890625 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.47890625 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.439453125 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.060052083333333325 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.18015625000000002 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.3002604166666667 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5134114583333333 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.49903613322071383 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.4860677083333333 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5680816897290807 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 512 type: dim_512 metrics: - type: cosine_accuracy@1 value: 0.47421875 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.47421875 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.47421875 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.5140625 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.47421875 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.47421875 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.47421875 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.436171875 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.058958333333333335 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.17687499999999998 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2947916666666667 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.5077864583333334 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4934297397023317 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.4808268229166666 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5631677376472394 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 256 type: dim_256 metrics: - type: cosine_accuracy@1 value: 0.45546875 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.45546875 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.45546875 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.496875 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.45546875 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.45546875 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.45546875 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.41875 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.05701822916666667 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.1710546875 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2850911458333333 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.4881510416666666 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.47460494952644156 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.4623697916666667 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5446289971505553 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 128 type: dim_128 metrics: - type: cosine_accuracy@1 value: 0.43515625 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.43515625 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.43515625 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.47265625 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.43515625 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.43515625 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.43515625 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.398828125 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.05451822916666667 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.1635546875 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2725911458333333 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.4639322916666666 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4521791896913678 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.44140625000000017 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.5207625038942943 name: Cosine Map@100 - task: type: information-retrieval name: Information Retrieval dataset: name: dim 64 type: dim_64 metrics: - type: cosine_accuracy@1 value: 0.39453125 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.39453125 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.39453125 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.4296875 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.39453125 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.39453125 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.39453125 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.359765625 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.049895833333333334 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.1496875 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.2494791666666667 name: Cosine Recall@5 - type: cosine_recall@10 value: 0.4223958333333333 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.4108797528312945 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.40039062500000033 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.4763475810083717 name: Cosine Map@100 --- # ModernBERT Embed base fitness health Matryoshka This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [nomic-ai/modernbert-embed-base](https://huggingface.co/nomic-ai/modernbert-embed-base) - **Maximum Sequence Length:** 8192 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - json - **Language:** en - **License:** apache-2.0 ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("kokojake/modernbert-embed-base-fitness-health-matryoshka") # Run inference sentences = [ 'facilitate publication;\n•\u2009\x07Mobilise academic expertise for \ndeveloping training programmes and \nmobilising trainers.\n\t Weigh in on the debate around issues \nrelated to rehabilitation promotion and funding, promote best practices to \ninfluence policies that favour access \nto rehabilitation services and thereby \nmove toward advocacy actions.\n48\nUsers,\nDisabled people’s\norganisations\nService\nproviders\nDecision-makers User \ngroups\nLocal\nauthorities\nMinistry of \nHealth, Ministry \nof Social Action,\netc.\nUnited Nations \n(WHO, etc.)\nHospitals, \nReference\nrehabilitation centre\nProfessional \nassociations\nService provider groups\nTraining institutes\nCommunity- \nbased Services\nFederation\nand national\n associations\nHospital, \nHealth \ncare centres Network: actors that can be mobilised for physical \nand functional rehabilitation\nInternational\nNational\nLocal\nInstitutional donors\nFacilitation organisations* * \x07Organisations (IOs, NGOs, etc.), agencies, universities and research centres that facilitate the existence of physical \nand functional rehabilitation via national or international projects.\nInternational \n consortia (IDDC, etc.)\n International\n networks \n (CBR, WCPT, \n WFOT, ISPO,\nFATO, etc.)\nLevels of intervention © Handicap International, 2013\n \n \n49\n\xa0Intervention.\n\xa0modalities\u200a.\nThe Unit has technical resources specifically \npositioned to be able to reach the maximum', 'training programmes for rehabilitation professionals', 'risks of yo-yo dieting and heart disease', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `dim_768` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 768 } ``` | Metric | Value | |:--------------------|:----------| | cosine_accuracy@1 | 0.4789 | | cosine_accuracy@3 | 0.4789 | | cosine_accuracy@5 | 0.4789 | | cosine_accuracy@10 | 0.5219 | | cosine_precision@1 | 0.4789 | | cosine_precision@3 | 0.4789 | | cosine_precision@5 | 0.4789 | | cosine_precision@10 | 0.4395 | | cosine_recall@1 | 0.0601 | | cosine_recall@3 | 0.1802 | | cosine_recall@5 | 0.3003 | | cosine_recall@10 | 0.5134 | | **cosine_ndcg@10** | **0.499** | | cosine_mrr@10 | 0.4861 | | cosine_map@100 | 0.5681 | #### Information Retrieval * Dataset: `dim_512` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 512 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.4742 | | cosine_accuracy@3 | 0.4742 | | cosine_accuracy@5 | 0.4742 | | cosine_accuracy@10 | 0.5141 | | cosine_precision@1 | 0.4742 | | cosine_precision@3 | 0.4742 | | cosine_precision@5 | 0.4742 | | cosine_precision@10 | 0.4362 | | cosine_recall@1 | 0.059 | | cosine_recall@3 | 0.1769 | | cosine_recall@5 | 0.2948 | | cosine_recall@10 | 0.5078 | | **cosine_ndcg@10** | **0.4934** | | cosine_mrr@10 | 0.4808 | | cosine_map@100 | 0.5632 | #### Information Retrieval * Dataset: `dim_256` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 256 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.4555 | | cosine_accuracy@3 | 0.4555 | | cosine_accuracy@5 | 0.4555 | | cosine_accuracy@10 | 0.4969 | | cosine_precision@1 | 0.4555 | | cosine_precision@3 | 0.4555 | | cosine_precision@5 | 0.4555 | | cosine_precision@10 | 0.4188 | | cosine_recall@1 | 0.057 | | cosine_recall@3 | 0.1711 | | cosine_recall@5 | 0.2851 | | cosine_recall@10 | 0.4882 | | **cosine_ndcg@10** | **0.4746** | | cosine_mrr@10 | 0.4624 | | cosine_map@100 | 0.5446 | #### Information Retrieval * Dataset: `dim_128` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 128 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.4352 | | cosine_accuracy@3 | 0.4352 | | cosine_accuracy@5 | 0.4352 | | cosine_accuracy@10 | 0.4727 | | cosine_precision@1 | 0.4352 | | cosine_precision@3 | 0.4352 | | cosine_precision@5 | 0.4352 | | cosine_precision@10 | 0.3988 | | cosine_recall@1 | 0.0545 | | cosine_recall@3 | 0.1636 | | cosine_recall@5 | 0.2726 | | cosine_recall@10 | 0.4639 | | **cosine_ndcg@10** | **0.4522** | | cosine_mrr@10 | 0.4414 | | cosine_map@100 | 0.5208 | #### Information Retrieval * Dataset: `dim_64` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: ```json { "truncate_dim": 64 } ``` | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.3945 | | cosine_accuracy@3 | 0.3945 | | cosine_accuracy@5 | 0.3945 | | cosine_accuracy@10 | 0.4297 | | cosine_precision@1 | 0.3945 | | cosine_precision@3 | 0.3945 | | cosine_precision@5 | 0.3945 | | cosine_precision@10 | 0.3598 | | cosine_recall@1 | 0.0499 | | cosine_recall@3 | 0.1497 | | cosine_recall@5 | 0.2495 | | cosine_recall@10 | 0.4224 | | **cosine_ndcg@10** | **0.4109** | | cosine_mrr@10 | 0.4004 | | cosine_map@100 | 0.4763 | ## Training Details ### Training Dataset #### json * Dataset: json * Size: 11,518 training samples * Columns: positive and anchor * Approximate statistics based on the first 1000 samples: | | positive | anchor | |:--------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | positive | anchor | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------| | values and preferences among older people
in relation to exercise, noting that older
people valued the outcomes of exercise
for maintaining health. They judged that
the evidence for older people was likely to be relevant to all adults and agreed
there was likely to be some uncertainty or
variability with respect to people’s values and
preferences for exercise and its outcomes.
Some GDG members suggested that given reasonably consistent benefit and very
little harms, there would be no important
uncertainty or variability regarding people’s
values on the outcomes of exercise. In the
absence of direct qualitative evidence, the GDG judged from their own experience
that resource requirements for structured
exercise programmes would vary by country
and setting, but in some settings might
be associated with moderate costs (for
structured exercise programmes, compared with self-managed physical activity). The GDG
noted that costs could also vary according to
the modality of ... | exercise preferences and outcomes variability among adults | | ICRC, ICRC Hospital Design and Rehabilitation Guidelines, Vol. 1: Models Of Care, ICRC, Geneva, 2022: https://shop. icrc.org/icrc-hospital-design-and-rehabilitation-guidelines-volume-1-models-of-care-print-en.html | ICRC rehabilitation guidelines 2022 | | fitness training is guided by a health worker or (if feasible) performed self-directed by
the patient following education and advice.
Metacognitive
training
Metacognitive training aims to improve social functioning through reducing cognitive biases/psychotic symptoms (e.g. delusion, impaired self-awareness or insight).
Metacognitive training is usually provided as a structured group intervention during which participants perform exercises to reflect their own thinking and receive training in
strategies to cope with cognitive biases during daily routines. Metacognitive training is
guided by a health worker.
Mindfulness-
based approaches Mindfulness-based interventions aim to achieve a state of mindfulness in which a
person becomes more aware of their physical, mental, and emotional condition in the
present moment, without becoming judgemental. Mindfulness-based interventions (e.g. mindfulness-based cognitive therapy, acceptance and commitment therapy)
help people to pay attentio... | structured group interventions for metacognitive training | * Loss: [MatryoshkaLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: ```json { "loss": "MultipleNegativesRankingLoss", "matryoshka_dims": [ 768, 512, 256, 128, 64 ], "matryoshka_weights": [ 1, 1, 1, 1, 1 ], "n_dims_per_step": -1 } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 16 - `gradient_accumulation_steps`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 4 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `bf16`: True - `tf32`: True - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 16 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 16 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 2e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 4 - `max_steps`: -1 - `lr_scheduler_type`: cosine - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: True - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: True - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: True - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `tp_size`: 0 - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch_fused - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| | 0.4444 | 10 | 64.4729 | - | - | - | - | - | | 0.8889 | 20 | 32.1029 | - | - | - | - | - | | 1.0 | 23 | - | 0.4734 | 0.4741 | 0.4590 | 0.4271 | 0.3722 | | 1.3111 | 30 | 23.9454 | - | - | - | - | - | | 1.7556 | 40 | 19.7319 | - | - | - | - | - | | 2.0 | 46 | - | 0.4934 | 0.4926 | 0.4723 | 0.4471 | 0.4021 | | 2.1778 | 50 | 17.6381 | - | - | - | - | - | | 2.6222 | 60 | 16.9329 | - | - | - | - | - | | **3.0** | **69** | **-** | **0.498** | **0.4954** | **0.4746** | **0.4528** | **0.4089** | | 3.0444 | 70 | 15.4096 | - | - | - | - | - | | 3.4889 | 80 | 15.4012 | - | - | - | - | - | | 3.8444 | 88 | - | 0.4990 | 0.4934 | 0.4746 | 0.4522 | 0.4109 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 4.0.2 - Transformers: 4.51.1 - PyTorch: 2.6.0+cu124 - Accelerate: 1.5.2 - Datasets: 3.5.0 - 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", } ``` #### MatryoshkaLoss ```bibtex @misc{kusupati2024matryoshka, title={Matryoshka Representation Learning}, author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, year={2024}, eprint={2205.13147}, archivePrefix={arXiv}, primaryClass={cs.LG} } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```