README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:2392
  - loss:MultipleNegativesRankingLoss
base_model: Qwen/Qwen3-Embedding-0.6B
widget:
  - source_sentence: >-
      What are the exact start and end times for overnight on-site IT coverage
      during the maintenance window?
    sentences:
      - >-
        Subject: Issue Encountered with Insurance Verification Workflow

        From: Julian R. Torres

        To: Rachel K. Martinez

        Date: 2025-10-20


        Hi Rachel,


        I wanted to flag an ongoing issue with the insurance verification
        process that’s impacting our ED admissions, especially during peak
        hours. Sometimes, patient insurance details aren’t fully updated in the
        system, and it’s causing delays getting clearance from registration.
        Could we discuss ways to streamline the info handoff between the ED and
        registration, or is there a protocol update I might’ve missed? Any
        suggestions or insight from your end would be appreciated.


        Thanks,

        Julian
      - >-
        Subject: EHR Medication Documentation Concerns – Joint Commission Survey
        Preparation

        From: Katherine M. Walsh

        To: Angela R. Scott

        Date: 2025-10-20


        Hello Angela,


        As we continue our preparations for the upcoming Joint Commission
        survey, I have identified a recurring issue with the EHR medication
        documentation process. Specifically, the current workflow does not
        require entry of medication batch numbers or precise dose changes during
        intraoperative adjustments, which is inconsistent with recent Joint
        Commission medication safety protocols. This gap could potentially lead
        to survey citations and, more importantly, compromises our ability to
        track medication safety accurately. Could you assist in reviewing and,
        if possible, updating the EHR fields so that batch numbers and
        intraoperative dose modifications are mandatory entries? If you need
        additional clinical detail, I am happy to collaborate.


        Thank you for your attention to this patient safety concern.


        Best regards,

        Katherine
      - >-
        Subject: Re: Scheduled System Maintenance Downtime – Main Hospital &
        Outpatient Clinics

        From: Richard T. Howard

        To: David R. Park

        Date: 2025-10-16


        Hi David,


        Thank you for your prompt reply and for raising the question about tech
        support coverage during the maintenance window. I can confirm that our
        IT team will have on-site personnel available overnight to assist with
        any urgent issues that arise, particularly for clinical teams. Please
        feel free to direct your staff to extension 4471 if immediate support is
        required during downtime.


        Let me know if you need any additional details or have further concerns.


        Best,

        Richard
  - source_sentence: >-
      Wrong-site surgery incident: what are the immediate disclosure obligations
      and communications strategy to the patient and family, in compliance with
      regulatory requirements?
    sentences:
      - >-
        Subject: Einladung zum Physician Appreciation Luncheon – 26. Juni,
        Sicherheitshinweise bitte beachten

        From: David R. Park

        To: Kevin T. Murphy

        Date: 2026-01-12


        Sehr geehrter Herr Murphy,


        vielen Dank für die Einladung zum Physician Appreciation Luncheon und
        die klaren Hinweise zu den Sicherheitsvorkehrungen. Ich begrüße die
        erhöhte Aufmerksamkeit für den Datenschutz und werde darauf achten,
        keine dienstlichen Geräte unbeaufsichtigt zu lassen und sensible
        Gesprächsthemen zu vermeiden. Die Maßnahmen der IT vor Ort geben
        zusätzliche Sicherheit.


        Mit freundlichen Grüßen

        David R. Park
      - >-
        Subject: Medication Reconciliation EHR Issue: Immediate Attention
        Required

        From: Christopher P. Brown

        To: Isaiah T. Jackson

        Date: 2025-12-22


        Hi Isaiah,


        I wanted to bring to your attention a recurring issue we've identified
        with the medication reconciliation feature in our EHR system. During
        peak usage hours, there are noticeable delays in loading patient
        medication histories, which has resulted in several incomplete
        reconciliations and workflow disruptions for clinical staff. I suspect
        this may be linked to the last unplanned EHR downtime, but we're still
        analyzing the root cause. Could you coordinate with nursing and pharmacy
        teams to document specific impact cases from the last week? This data
        will help us escalate the issue with our EHR vendor and develop interim
        protocols to mitigate patient safety risks.


        Let me know a good time for a short call to discuss next steps.


        Best,

        Christopher
      - >-
        Subject: Re: Re: URGENT: Incident Report - OR3 Surgical Case

        From: Patricia M. Vasquez

        To: David R. Park

        Date: 2025-09-12


        Dear David,


        I am writing to advise you of a critical adverse event that occurred
        earlier today in OR3 involving patient Robert Hendricks. During a
        scheduled arthroscopy, the procedure was performed on the wrong site
        (right knee rather than the consented and marked left knee). The patient
        is increasingly agitated and has voiced significant distress over the
        error; his family members are now actively seeking information and have
        expressed concern about the care provided.


        Given the gravity of this situation, I am requesting immediate legal
        guidance regarding our incident management strategy, disclosure
        obligations to the patient and family, and best practices for
        documentation and information retention. I have instructed all involved
        staff to hold documentation pending our discussion and to refrain from
        further written communication until protocols are clarified. Please
        advise on next steps, including any immediate actions we should take to
        ensure compliance with regulatory requirements and to protect both the
        patient’s rights and the hospital’s interests.


        Your prompt attention to this matter is greatly appreciated. Please let
        me know if you require any additional information or wish to convene a
        call tonight to discuss further.


        Regards,

        Patricia M. Vasquez, RN, MBA, CPHRM

        Director of Risk Management & Patient Safety
  - source_sentence: >-
      What are the specific gaps between the current patient-facing grievance
      script and the formal grievance procedure documentation in our department,
      and which points are not being conveyed?
    sentences:
      - >-
        Subject: Request for Support: Employee Wellness Initiative Documentation

        From: Chloe R. Anderson

        To: Linda R. Taylor

        Date: 2026-01-13


        Hi Linda,


        I am reaching out regarding an issue we've encountered with tracking
        participation in the new employee wellness initiative. Several staff
        members have reported that their completed activity forms are not
        reflected in our records, possibly due to delays in processing or a
        system error. Would you be able to help review recent submissions and
        confirm that all entries from the past two weeks have been logged
        appropriately? If you notice any discrepancies, please let me know so we
        can address them promptly.


        Thank you for your assistance.


        Best,

        Chloe
      - >-
        Subject: Re: Sending this your way

        From: Angela R. Scott

        To: Zoe M. Campbell

        Date: 2025-12-09


        Hi Zoe,


        Thank you for passing along the documents and providing the details
        regarding the EHR issues. I’ve started reviewing the attached error logs
        and, based on some initial patterns, I suspect the API middleware might
        be bottlenecking when processing simultaneous attachment uploads. I plan
        to investigate further by running diagnostics during peak usage hours
        and testing middleware latency. I’ll circle back with more detailed
        findings and some preliminary recommendations by the end of the week. If
        you have any additional instances or timestamps where the failures were
        most severe, that information would be especially helpful for my
        analysis.


        Thanks for reaching out, and I’ll keep you posted as I dig deeper.


        Best regards,

        Angela
      - >-
        Subject: Clarification Needed on Grievance Procedure Communication

        From: Elizabeth M. Turner

        To: Jasmine K. Patel

        Date: 2025-10-29


        Hello Jasmine,


        During a recent audit of staff communications, I observed some
        inconsistencies in how the grievance procedure is being explained to
        patients within our department. It appears several steps specified in
        the formal documentation are not being fully outlined in verbal
        explanations, which could lead to misunderstandings. Could you assist by
        reviewing the current script with me, so we can ensure all required
        points are conveyed accurately going forward? Please let me know a
        convenient time for us to meet and update our process accordingly.


        Thank you for your attention to this matter.


        Best regards,

        Elizabeth M. Turner
  - source_sentence: >-
      ¿Cuál es el estado actual y la fecha estimada de entrega de los registros
      médicos y la documentación solicitada para la revisión inicial del caso?
    sentences:
      - >-
        Subject: Re: Solicitud de Documentación Adicional para la Investigación

        From: Inspector Helen R. Jacobs

        To: David R. Park

        Date: 2026-01-01


        Estimado Sr. Park,


        Agradezco su pronta respuesta y la confirmación del envío de los
        registros médicos y demás documentación solicitada. Por el momento, los
        documentos que menciona serán suficientes para continuar con la revisión
        inicial del caso; si surgiera la necesidad de información adicional, me
        pondré en contacto de inmediato. Quedamos atentos a la recepción de los
        archivos a finales de semana.


        Cordialmente,

        Helen R. Jacobs
      - >-
        Subject: Need your input

        From: George M. Harris

        To: Zoe M. Campbell

        Date: 2026-01-22


        Hi Zoe,


        Thanks for looping me in. Before I can provide a full response, could
        you clarify which specific billing codes are in question and whether the
        supporting clinical documentation has already been uploaded to the
        compliance system? I want to ensure that any input I provide aligns with
        the latest guidelines and audit standards. Please provide the relevant
        details when you have a moment.


        Thanks,

        George
      - >-
        Subject: Update

        From: David R. Park

        To: Katherine E. Morrison

        Date: 2026-01-26


        Hello,


        As requested, I am sending the update we discussed. Please find attached
        a summary of the current situation, along with all pertinent details
        that have come to light since our last conversation. If you have any
        further questions or need clarification on specific points, do not
        hesitate to reach out. Your input will be valuable as we move forward.


        Looking forward to your response.


        Best regards,

        David R. Park
  - source_sentence: >-
      What bottlenecks in the updated post-operative workflow are contributing
      to delays in surgical site infection specimen transfer and tracking?
    sentences:
      - >-
        Subject: Inquiry Regarding Post-Operativ Care Documentation

        From: David R. Park

        To: Inspector Helen R. Jacobs

        Date: 2026-01-26


        Hello Inspector Jacobs,


        I am reaching out regarding the ongoing investigation tied to Mr.
        Hendricks’ recent case. We have been reviewing the patient records and
        noticed that the documentation for the post-operativ care period
        contains several ambiguities. We would appreciate your guidance on
        whether additional clarification or supplementary notes are required for
        compliance purposes. Please let me know how you would like us to
        proceed, or if you need copies of the relevant chart sections.


        Best regards,

        David R. Park
      - >-
        Subject: Concern Regarding Allergy Documentation Accuracy and Glucose
        Meter Integration

        From: Daniel M. Evans

        To: Gabriella I. Santos

        Date: 2026-01-26


        Hi Gabriella,


        I wanted to bring to your attention a recurring issue we’ve noticed with
        our glucose meters not consistently syncing updated allergy information
        from the patient chart. During routine maintenance, I found
        discrepancies between recorded allergies on the device and what is
        documented in the EMR, which could lead to potential risks for patients
        with sensitivities, especially regarding test strip ingredients. I
        propose we review the current integration workflow and possibly schedule
        a troubleshooting session with IT to ensure seamless allergy data
        transfer. Please let me know if you’ve experienced similar concerns and
        if you’d be available to discuss this further.


        Thanks,

        Daniel
      - >-
        Subject: Concerns Regarding Timeliness of Surgical Site Infection
        Tracking

        From: Xavier D. Brooks

        To: David S. Wilson

        Date: 2025-11-10


        Hi David,


        Thank you for raising these concerns about the delays in surgical site
        infection tracking. We have indeed adjusted some aspects of our post-op
        patient flow in an attempt to enhance discharge efficiency, including
        new documentation checkpoints that might inadvertently be slowing the
        specimen transfer process. I’ll coordinate with our nursing and records
        teams to closely review recent workflow changes and identify any
        bottlenecks that could be contributing to extended turnaround times.
        I’ll share our findings and propose potential improvements by the end of
        this week, and I welcome any further details you notice from the lab
        side as well.


        Best regards,

        Xavier
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: SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: val real corpus thread ir
          type: val_real_corpus_thread_ir
        metrics:
          - type: cosine_accuracy@1
            value: 0.7612687813021702
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8297161936560935
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8614357262103506
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8948247078464107
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7612687813021702
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.5275459098497496
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.33489148580968287
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.17896494156928214
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.3664997217584864
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.701307735114079
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7390651085141903
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.7844462993878687
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7519775439563073
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8039410922966848
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7154125325663795
            name: Cosine Map@100

SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B

This is a sentence-transformers model finetuned from Qwen/Qwen3-Embedding-0.6B. It maps sentences & paragraphs to a 1024-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: Qwen/Qwen3-Embedding-0.6B
• Maximum Sequence Length: 768 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 768, 'do_lower_case': False, 'architecture': 'PeftModelForFeatureExtraction'})
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, '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': True, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
queries = [
    "What bottlenecks in the updated post-operative workflow are contributing to delays in surgical site infection specimen transfer and tracking?",
]
documents = [
    'Subject: Concerns Regarding Timeliness of Surgical Site Infection Tracking\nFrom: Xavier D. Brooks\nTo: David S. Wilson\nDate: 2025-11-10\n\nHi David,\n\nThank you for raising these concerns about the delays in surgical site infection tracking. We have indeed adjusted some aspects of our post-op patient flow in an attempt to enhance discharge efficiency, including new documentation checkpoints that might inadvertently be slowing the specimen transfer process. I’ll coordinate with our nursing and records teams to closely review recent workflow changes and identify any bottlenecks that could be contributing to extended turnaround times. I’ll share our findings and propose potential improvements by the end of this week, and I welcome any further details you notice from the lab side as well.\n\nBest regards,\nXavier',
    'Subject: Concern Regarding Allergy Documentation Accuracy and Glucose Meter Integration\nFrom: Daniel M. Evans\nTo: Gabriella I. Santos\nDate: 2026-01-26\n\nHi Gabriella,\n\nI wanted to bring to your attention a recurring issue we’ve noticed with our glucose meters not consistently syncing updated allergy information from the patient chart. During routine maintenance, I found discrepancies between recorded allergies on the device and what is documented in the EMR, which could lead to potential risks for patients with sensitivities, especially regarding test strip ingredients. I propose we review the current integration workflow and possibly schedule a troubleshooting session with IT to ensure seamless allergy data transfer. Please let me know if you’ve experienced similar concerns and if you’d be available to discuss this further.\n\nThanks,\nDaniel',
    'Subject: Inquiry Regarding Post-Operativ Care Documentation\nFrom: David R. Park\nTo: Inspector Helen R. Jacobs\nDate: 2026-01-26\n\nHello Inspector Jacobs,\n\nI am reaching out regarding the ongoing investigation tied to Mr. Hendricks’ recent case. We have been reviewing the patient records and noticed that the documentation for the post-operativ care period contains several ambiguities. We would appreciate your guidance on whether additional clarification or supplementary notes are required for compliance purposes. Please let me know how you would like us to proceed, or if you need copies of the relevant chart sections.\n\nBest regards,\nDavid R. Park',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.7188, 0.1221, 0.0596]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

• Dataset: val_real_corpus_thread_ir
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7613
cosine_accuracy@3	0.8297
cosine_accuracy@5	0.8614
cosine_accuracy@10	0.8948
cosine_precision@1	0.7613
cosine_precision@3	0.5275
cosine_precision@5	0.3349
cosine_precision@10	0.179
cosine_recall@1	0.3665
cosine_recall@3	0.7013
cosine_recall@5	0.7391
cosine_recall@10	0.7844
cosine_ndcg@10	0.752
cosine_mrr@10	0.8039
cosine_map@100	0.7154

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,392 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 11 tokens mean: 26.85 tokens max: 62 tokens	min: 99 tokens mean: 159.15 tokens max: 364 tokens

• Samples:

  sentence_0	sentence_1
  What specific documents and timeline details are being requested for the medication administration incident involving the late husband (e.g., notes and observed discrepancy times)?	Subject: Clarification Needed Regarding Recent Medciation Administration Incident From: David R. Park To: Margaret L. Hendricks Date: 2025-10-16 Hello Mrs. Hendricks, Thank you for your prompt reply and for clarifying your experience regarding the medication administration incident involving your late husband. I acknowledge your willingness to provide further details and want to ensure that our review is thorough and respectful of your family's concerns. A call on Wednesday afternoon works for me, and I appreciate your flexibility in offering to share information by email. If you have any documentation, such as notes or times you observed discrepancies, that would be very helpful for our review. Please let me know your preferred time for the call, or if you wish to send information in writing, I am happy to review it carefully. Thank you again for your cooperation as we work to address these important concerns. I look forward to speaking with you and assisting however I can. Best r...
  What specific additional materials or documentation should my team prepare ahead of the meeting?	Subject: Re: Meeting Confirmation and Case Materials From: David R. Park To: Katherine E. Morrison Date: 2025-12-01 Hi Katherine, Thank you for confirming the meeting time and sharing the agenda. I appreciate your prompt coordination on this. Please let me know if there are any additional materials or documentation you would like from my team ahead of our discussion. I look forward to collaborating and ensuring all questions are addressed at our meeting. Best regards, David
  Who is assigned to coordinate the review of PACS-EHR interface error logs with radiology IT to address radiology report delays?	Subject: Radiology Report Turnaround Delays in EHR From: Angela R. Scott To: Laura A. Hughes Date: 2025-11-17 Hi Laura, I've noticed a consistent delay in radiology report turnaround times stemming from integration issues between the PACS interface and our EHR system. Reports are not always populating promptly in patient records, which is affecting timely communication with both care teams and patients. I suggest we collaborate with the radiology IT staff to review interface error logs and streamline the auto-notification features. If you have additional insight from recent patient feedback or workflow observations, please let me know so we can address this comprehensively. Thanks, Angela --- This email and any attachments are confidential and intended solely for the use of the individual or entity to whom they are addressed.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 3
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_ratio: None
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• enable_jit_checkpoint: False
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• use_cpu: False
• seed: 42
• data_seed: None
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: -1
• ddp_backend: None
• debug: []
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: False
• ignore_data_skip: False
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• 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_fused
• optim_args: None
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• 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
• 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_for_metrics: []
• eval_do_concat_batches: True
• auto_find_batch_size: False
• full_determinism: False
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• use_cache: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	val_real_corpus_thread_ir_cosine_ndcg@10
1.0	299	-	0.7464
1.6722	500	0.0176	-
2.0	598	-	0.7507
3.0	897	-	0.7520

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.2
• Transformers: 5.0.0
• PyTorch: 2.9.0+cu128
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

@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",
}

MultipleNegativesRankingLoss

@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}
}