README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:2394
  - loss:MultipleNegativesRankingLoss
base_model: Qwen/Qwen3-Embedding-0.6B
widget:
  - source_sentence: >-
      Hendricks case: confidential incident details discussed with OR staff
      outside the formal investigation process
    sentences:
      - >-
        Subject: Concerns Regarding Recent Dietary Services Menu Change

        From: Laura A. Hughes

        To: Elizabeth M. Turner

        Date: 2026-01-16


        Hello Elizabeth,


        I am reaching out to bring to your attention several patient concerns
        that have arisen following the recent dietary services menu change
        implemented last week. Multiple patients and their families have noted a
        lack of clarity regarding allergen labeling and have expressed confusion
        about the new meal selections. In light of our patient safety protocols,
        I recommend we conduct a rapid review of current menu documentation and
        consider a focused staff in-service to address labeling accuracy and
        communication with patients. Please let me know if you require detailed
        feedback reports or would like to coordinate a joint review meeting to
        address these issues collectively.


        Best regards,

        Laura A. Hughes
      - >-
        Subject: Patient Safety Week Activities: Join Us in Fostering a Culture
        of Safety

        From: Diane L. Cooper

        To: All Hospital Staff

        Date: 2025-10-12


        Dear St. Catherine's Team,


        As we approach National Patient Safety Week, I am pleased to invite all
        staff to participate in a series of activities dedicated to reinforcing
        our shared commitment to patient safety and quality care. Throughout the
        week, we will host educational workshops, interactive safety
        simulations, and informative sessions led by our hospital's clinical
        risk management team. These events are designed not only to enhance our
        understanding of best practices but also to empower every one of us in
        proactively promoting a safe hospital environment.


        Patient safety remains at the heart of our mission, and your engagement
        is instrumental in upholding our standards. I encourage everyone to
        review the attached schedule and make time to participate in as many
        sessions as possible. Together, let’s continue to cultivate
        transparency, learning, and collaboration across all departments.


        Should you have any questions regarding the activities or wish to
        suggest additional topics, please do not hesitate to reach out to me
        directly.


        Thank you for your dedication to excellence and patient care.


        Best regards,

        Diane L. Cooper

        Director, Employee Relations

        St. Catherine's Regional Hospital
      - >-
        Subject: Required Meeting: Performance and Policy Compliance

        From: Patricia M. Vasquez

        To: Sarah J. Morrison

        Date: 2025-09-17


        Dear Sarah,


        Thank you for your prompt reply and for confirming your attendance at
        the meeting. To address your request for clarification, we have received
        reports that you have been discussing confidential incident details
        related to the Hendricks case with OR staff members outside the formal
        investigation process. Additionally, it has been noted that your
        characterization of events in those discussions has been inconsistent
        with your formal statements submitted to patient safety and risk
        management.


        Given the seriousness of these concerns, we will discuss them in detail
        during our meeting on Thursday. I urge you to consider carefully how you
        want to proceed with your employment here and to review any relevant
        documentation in advance. If you have further questions, please let me
        know.


        Regards,

        Patricia M. Vasquez

        Risk Management Director
  - source_sentence: >-
      Who is responsible for coordinating with Employee Health to establish
      overnight or mobile flu vaccination slots for Radiology and Ultrasound
      night-shift staff, and what is the timeline to implement it?
    sentences:
      - >-
        Subject: Issue with Patient Portal Enrollment Impacting Billing
        Documentation

        From: Sofia R. Ramirez

        To: George M. Harris

        Date: 2025-11-11


        Hi George,


        I'm reaching out because I've noticed several cases where new patients
        are unable to complete their portal enrollment, which has led to
        incomplete demographic and insurance information in our records. This is
        causing issues with proper billing code assignment and delays in claims
        processing. Do you have recommendations for improving the collection of
        required documentation at this stage or a workflow update that could
        help ensure all necessary data is captured before billing? Your
        expertise would be invaluable as we try to minimize claim denials due to
        missing information.


        Thanks for your help,

        Sofia
      - >-
        Subject: Concern Regarding Central Line Infection Rate and Equipment
        Protocols

        From: Daniel M. Evans

        To: Thomas R. Anderson

        Date: 2025-09-29


        Hi Thomas,


        I wanted to bring to your attention a recent uptick in the central line
        infection rates reported on Med-Surg units over the past two weeks. My
        initial review suggests possible inconsistencies in how central line
        carts are being sanitized and restocked during overnight shifts,
        especially with high patient turnover. I recommend we conduct a targeted
        refresher with night staff and consider updating signage on carts to
        reinforce proper protocol. Could you assist in coordinating this or
        suggest an alternate approach to address the issue promptly?


        Thanks for your leadership,

        Daniel


        Get Outlook for iOS
      - >-
        Subject: Flu Vaccination Campaign: Night Shift Coverage Concern

        From: Jasmine K. Patel

        To: Thomas R. Anderson

        Date: 2026-01-19


        Hi Thomas,


        I wanted to flag an issue regarding the ongoing flu vaccination
        campaign. We've noticed that several night shift staff in Radiology and
        Ultrasound have missed scheduled vaccine appointments due to limited
        after-hours availability. Would it be possible to coordinate with
        Employee Health to set up a dedicated time slot overnight or provide
        mobile vaccination rounds for these teams?


        Let me know how you'd like to proceed.


        Thanks,

        Jasmine
  - source_sentence: >-
      Confirm availability of Room 214 or an alternative near the kitchen for a
      dietary workshop scheduled 2-4 pm on the upcoming Thursday.
    sentences:
      - >-
        Subject: Incident Report: PACS System Downtime Impacting Surgical
        Workflow

        From: Chloe R. Anderson

        To: Ronald J. Mitchell

        Date: 2025-12-17


        Hi Ronald,


        Thank you for your prompt response regarding the PACS system downtime in
        OR 3. I appreciate your commitment to coordinating with IT and
        implementing interim manual image access protocols, as well as
        initiating a root cause analysis. I will continue to document any
        further disruptions, as requested, and look forward to your update on
        both interim procedures and the proposed action plan within the next 48
        hours. Please let me know if there are any specific details or examples
        you require for the analysis, as I am happy to provide additional
        documentation or feedback to support the resolution process.


        Best regards,

        Chloe
      - >-
        Subject: Medication Inventory Shortage Affecting CT Protocols

        From: Maya S. Patel

        To: Emily T. O'Brien

        Date: 2025-12-19


        Hi Emily,


        Thank you for bringing this urgent medication shortage to my attention.
        I appreciate you taking the initiative to check with pharmacy first, and
        I completely understand the impact limited Omnipaque has on critical CT
        procedures, particularly for stroke and trauma protocols. I will
        immediately reach out to Materials Management to find out the status of
        the incoming shipment and see if there are any options for expediting
        delivery. Additionally, I’ll consult with Radiology and Pharmacy
        leadership to review possible alternative contrast agents that could be
        safely substituted without compromising patient care or compliance. I’ll
        provide you with an update later today as soon as I have more
        information.


        Please let me know if there are any specific cases you’re concerned
        about in the interim so we can prioritize resources accordingly.


        Thank you again for your vigilance on this issue.


        Best regards,

        Maya
      - >-
        Subject: Request for Room Reservation for Upcoming Dietary Workshop

        From: Mary E. Carter

        To: Barbara J. Young

        Date: 2025-10-20


        Hi Barbara,


        I hope you’re doing well. I’d like to request a room reservation for our
        upcoming dietary workshop scheduled next Thursday from 2-4 pm. We'll be
        reviewing new meal service procedures and want to cover updates on
        handling specific dietary restrictions for patients. Ideally, we’ll need
        a space near the kitchen to facilitate the hands-on demonstration
        segment. Could you please confirm if Room 214 or another suitable room
        is available during that time? Timely confirmation would be greatly
        appreciated so I can coordinate our kitchen staff and prepare the
        necessary materials.


        Thank you for your help!


        Best regards,

        Mary
  - source_sentence: >-
      What are the exact policy violations alleged in relation to the Hendricks
      incident referenced in the incident report?
    sentences:
      - >-
        Subject: Required Meeting: Performance and Policy Compliance

        From: Sarah J. Morrison

        To: Patricia M. Vasquez

        Date: 2025-10-02


        Dear Patricia,


        Thank you for your message. I am quite concerned and honestly confused
        by the allegations you referenced. I want to clarify that I have only
        discussed the Hendricks incident with patient safety personnel and the
        individuals you specifically directed me to meet with as part of the
        internal review process. At no point have I shared confidential patient
        safety matters outside of these channels, and I have not violated any
        HIPAA rules to my knowledge.


        Could you please provide more details regarding the specific policy
        violations being alleged? Is this related to my recent incident report
        concerning the Hendricks case? I want to ensure I understand the nature
        of the concerns so I can respond appropriately and prepare for our
        meeting. Please let me know what information you need from me and when
        you would like to schedule this discussion.


        I appreciate your clarification and look forward to resolving this
        matter.


        Sincerely,

        Sarah J. Morrison
      - >-
        Subject: Hinweis zu Systemfunktion – Bitte prüfen

        From: Andrew J. Bennett

        To: Angela R. Scott

        Date: 2025-09-29


        Hallo Angela,


        ich wollte dich kurz auf ein mögliches Problem mit der
        Dokumentenarchivierungsfunktion im neuen EHR-Update aufmerksam machen.
        Einige Nutzer haben Rückmeldungen gegeben, dass freigegebene
        Laborbefunde nicht wie vorgesehen in den Patientenakten angezeigt
        werden. Das könnte Auswirkungen auf die klinische Entscheidungsfindung
        haben. Kannst du das bitte prüfen und mir eine Rückmeldung geben, ob wir
        mit einem Patch rechnen können? Ich danke dir im Voraus für deine
        Unterstützung.


        Viele Grüße,

        Andrew
      - >-
        Subject: Defibrillator Battery Checks – Immediate Attention Required

        From: Robert Kim

        To: Jennifer Rodriguez

        Date: 2025-12-03


        Hi Jennifer,

        I've noticed repeated inconsistencies with the battery checks on several
        OR defibrillators over the past two weeks—twice now, devices have shown
        low battery during pre-op review. This poses unnecessary risk and
        disrupts our workflow in critical cases. I propose we assign a single OR
        tech to conduct and document battery checks at the start of each shift,
        to ensure accountability and avoid gaps in readiness. Please advise if
        you support this approach or can suggest a more robust solution.

        Best,

        Robert
  - source_sentence: >-
      What is the proposed date/time for a meeting with Maintenance to review
      findings and strategize a remediation plan for OR wing HVAC fluctuations
      affecting post-op mobility protocols?
    sentences:
      - >-
        Subject: Request for Conference Call Number

        From: Carol A. Campbell

        To: Melissa K. King

        Date: 2025-10-27


        Hi Melissa,


        I hope you're doing well. I am reaching out to request the conference
        call number for our upcoming credentialing review meeting scheduled
        later this week. Having the dial-in details ahead of time will help me
        circulate the information to all committee members and ensure we are
        fully prepared to discuss the physician files on the agenda. Please let
        me know at your earliest convenience if there are any specific protocols
        or security codes required for access.


        Thank you very much for your assistance.


        Best regards,

        Carol
      - >-
        Subject: Payment Posting Discrepancy – Assistance Needed with Discharge
        Billing

        From: Isaiah T. Jackson

        To: Taylor A. Richardson

        Date: 2025-10-30


        Hi Taylor,


        Thanks for bringing this to my attention. I've pulled the discharge plan
        and placement records and will cross-reference them with the insurance
        authorization to verify alignment. Once I have more clarity, I’ll
        coordinate with you and finance as needed to resolve any
        discrepancies—please hold off on correction for now. If I require any
        additional documentation, I’ll let you know.


        Best,

        Isaiah
      - >-
        Subject: HVAC System Issues Impacting OR Wing: Request for Collaborative
        Solution

        From: Dr. Susan L. Chang

        To: Brian K. Lee

        Date: 2025-10-20


        Hi Brian,


        Thank you for raising this concern regarding the HVAC fluctuations in
        the OR wing. My team has indeed noticed some difficulties in maintaining
        prescribed post-operative mobility protocols due to variable
        temperatures, which can discourage early patient movement and affect our
        recovery benchmarks. I agree that partnering with Maintenance for timely
        remediation is essential; I can share specific observations from our
        unit that might help guide targeted improvements in the HVAC settings or
        scheduling.


        Let me know when would be best to meet with you and Maintenance so we
        can review findings and strategize a plan. Thanks again for the
        proactive outreach.


        Best,

        Susan
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 evaluation
          type: val_evaluation
        metrics:
          - type: cosine_accuracy@1
            value: 0.8948247078464107
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9582637729549248
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9799666110183639
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.8948247078464107
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3194212576516416
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19599332220367274
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09999999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.8948247078464107
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9582637729549248
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9799666110183639
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.947164718374032
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9301560802395528
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9301560802395525
            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 is the proposed date/time for a meeting with Maintenance to review findings and strategize a remediation plan for OR wing HVAC fluctuations affecting post-op mobility protocols?",
]
documents = [
    'Subject: HVAC System Issues Impacting OR Wing: Request for Collaborative Solution\nFrom: Dr. Susan L. Chang\nTo: Brian K. Lee\nDate: 2025-10-20\n\nHi Brian,\n\nThank you for raising this concern regarding the HVAC fluctuations in the OR wing. My team has indeed noticed some difficulties in maintaining prescribed post-operative mobility protocols due to variable temperatures, which can discourage early patient movement and affect our recovery benchmarks. I agree that partnering with Maintenance for timely remediation is essential; I can share specific observations from our unit that might help guide targeted improvements in the HVAC settings or scheduling.\n\nLet me know when would be best to meet with you and Maintenance so we can review findings and strategize a plan. Thanks again for the proactive outreach.\n\nBest,\nSusan',
    "Subject: Payment Posting Discrepancy – Assistance Needed with Discharge Billing\nFrom: Isaiah T. Jackson\nTo: Taylor A. Richardson\nDate: 2025-10-30\n\nHi Taylor,\n\nThanks for bringing this to my attention. I've pulled the discharge plan and placement records and will cross-reference them with the insurance authorization to verify alignment. Once I have more clarity, I’ll coordinate with you and finance as needed to resolve any discrepancies—please hold off on correction for now. If I require any additional documentation, I’ll let you know.\n\nBest,\nIsaiah",
    "Subject: Request for Conference Call Number\nFrom: Carol A. Campbell\nTo: Melissa K. King\nDate: 2025-10-27\n\nHi Melissa,\n\nI hope you're doing well. I am reaching out to request the conference call number for our upcoming credentialing review meeting scheduled later this week. Having the dial-in details ahead of time will help me circulate the information to all committee members and ensure we are fully prepared to discuss the physician files on the agenda. Please let me know at your earliest convenience if there are any specific protocols or security codes required for access.\n\nThank you very much for your assistance.\n\nBest regards,\nCarol",
]
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([[0.7461, 0.0432, 0.0610]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

• Dataset: val_evaluation
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.8948
cosine_accuracy@3	0.9583
cosine_accuracy@5	0.98
cosine_accuracy@10	1.0
cosine_precision@1	0.8948
cosine_precision@3	0.3194
cosine_precision@5	0.196
cosine_precision@10	0.1
cosine_recall@1	0.8948
cosine_recall@3	0.9583
cosine_recall@5	0.98
cosine_recall@10	1.0
cosine_ndcg@10	0.9472
cosine_mrr@10	0.9302
cosine_map@100	0.9302

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,394 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: 8 tokens mean: 26.77 tokens max: 63 tokens	min: 99 tokens mean: 160.64 tokens max: 399 tokens

• Samples:

  sentence_0	sentence_1
  What are the routine badge access needs for the phlebotomy team under the updated infection control protocol to prevent access-related delays in the patient observation wing?	Subject: Request for Assistance: Infection Control Protocol Update Impacting Phlebotomy Access From: Paul R. Nelson To: Carlos J. Rodriguez Date: 2025-12-15 Hi Carlos, I wanted to reach out regarding recent changes to our infection control protocols, which now require stricter badge access in certain areas, including the patient observation wing. We've had a few incidents where phlebotomy staff were delayed due to these new access restrictions. To ensure patient care isn't impacted, could you assist by identifying routine access needs for your team so we can adjust permissions accordingly? Please let me know if you or your team have experienced any specific challenges, and I’ll work to resolve these promptly. Thanks for your cooperation, Paul
  Are there any specific legal/compliance issues to be addressed during the Emergency Preparedness Drill?	Subject: Re: Upcoming Hospital-wide Emergency Preparedness Drill – Participation Required From: David R. Park To: Richard T. Howard Date: 2025-12-02 Hello Richard, Thank you for the detailed announcement and for outlining the objectives of the upcoming Emergency Preparedness Drill. I appreciate the proactive approach to ensuring all staff are familiar with emergency protocols, especially with the simulation of both power and network outages. My team and I will review our current department safety procedures and ensure we are prepared to both participate in the drill and report any issues we discover. Please let me know if there are any specific compliance issues from the legal perspective you would like addressed during the exercise. Best regards, David R. Park
  Quem é o responsável por fornecer o relatório de ultrassom de Miguel Silva para desbloquear a baixa de dívida incobrável?	Subject: Solicitação de apoio: aprovação de baixa de dívidas incobráveis From: Rachel K. Martinez To: Jasmine K. Patel Date: 2025-10-27 Olá Jasmine, Estou enfrentando dificuldades com a aprovação de uma baixa de dívida incobrável referente ao paciente do Pronto-Socorro. O sistema está bloqueando o processo devido à ausência de alguns documentos do setor de imagem. Você poderia, por favor, me ajudar a localizar ou encaminhar o relatório do ultrassom do paciente Miguel Silva? Precisamos desse documento para dar andamento à solicitação. Agradeço pela agilidade! Atenciosamente, Rachel K. Martinez

• 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_evaluation_cosine_ndcg@10
1.0	300	-	0.9461
1.6667	500	0.0168	-
2.0	600	-	0.9459
3.0	900	-	0.9472

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}
}