README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:1520
  - loss:MultipleNegativesRankingLoss
base_model: Qwen/Qwen3-Embedding-0.6B
widget:
  - source_sentence: >-
      Internal communications tracking permit application delays or production
      impact
    sentences:
      - >-
        Subject: Re: Coordination for Upcoming Auditor Visit to Tequila Facility

        Date: 2026-01-07T13:35:00

        From: Roberto Garza

        Participants: Elena Fuentes


        Body:

        Hi Elena,


        Thanks for reaching out regarding the auditor visit. Can you share
        whether any of the visitors have dietary restrictions or accessibility
        needs we should consider for the site tour and lunch? Also, will
        translation services or special PPE be required for any attendees?
        Please confirm if there are specific topics or production areas they
        want to prioritize during the tour, so we can prepare accordingly.


        Looking forward to your response.


        Best regards,

        Roberto
      - >-
        Subject: Production Team Shift Schedules and Holiday Coverage

        Date: 2025-08-11T10:08:00

        From: Sofia Hernandez

        Participants: Agave Spirits International Production Team


        Body:

        Hi team,


        I wanted to follow up regarding our upcoming shift schedules and to
        ensure we have the necessary coverage for the next few weeks. As you
        know, we need the permit to maintain production levels, so it's
        important that we avoid any staffing gaps—especially with the team
        working overtime this week. Please review your assigned shifts on the
        attached schedule. If you need to request time off or swap a shift, let
        me know by Wednesday so we can coordinate approvals and avoid
        disruptions. For those available to cover during the holiday period,
        please confirm your availability as soon as possible. Your flexibility
        and commitment are highly appreciated as we work to keep production
        targets on track.


        Thank you,

        Sofia Hernandez

        Production Supervisor
      - >-
        Subject: Re: Tequila Production Yield Calculations and Permit Status
        Concerns

        Date: 2025-10-24T07:21:00

        From: Sofia Hernandez

        Participants: Roberto Garza


        Body:

        Hi Roberto,


        Thank you for sending over the yield data and highlighting the decrease
        due to fiber content. I'll review the numbers more closely before our
        Thursday meeting and will propose any adjustments to the shift schedule
        if necessary. Regarding the permit, I agree it’s critical—I'll check in
        with Rick this afternoon for a status update and notify you immediately
        if your involvement is needed or if there are any bottlenecks we need to
        address. Your proactive approach is appreciated.


        Let’s align on next steps Thursday.


        Best,

        Sofia
  - source_sentence: Internal communications planning around regulatory crisis or investigation
    sentences:
      - >-
        Subject: Re: Crisis Communication Preparation: Controlling the Narrative

        Date: 2025-10-20T10:32:00

        From: Thomas Tom Bradford

        Participants: Daniel Wright


        Body:

        Hi Daniel,


        Thank you for emphasizing the urgency of tight crisis communication
        planning. I completely agree with the need for pre-drafted statements
        and consistent internal messaging. Let’s schedule the all-hands call for
        Monday at 10:00 AM, which should allow us to address recent updates and
        finalize our unified approach. Please confirm if this timing works, and
        circulate your suggested draft statements/Q&A by end of day today.


        Looking forward to aligning on next steps.


        Best,

        Tom
      - >-
        Subject: Request for Final Approval: Press Release Draft on Tequila
        Facility Expansion

        Date: 2025-10-13T15:06:00

        From: Daniel Wright

        Participants: Thomas Tom Bradford; Sarah Mitchell


        Body:

        Hi Tom, Sarah,


        I'm attaching the latest draft of our press release regarding the
        Tequila facility expansion. As you review, please pay close attention to
        how we've addressed the partnership with local officials and the
        environmental safeguards—these areas are especially sensitive given
        current media attention. I believe the draft is balanced, but I'm
        concerned about how the narrative could shift if taken out of context in
        headlines. I recommend a careful review for any language that might
        inadvertently invite controversy or misrepresentation.


        Could you send your feedback or approval by end of day tomorrow? Once
        cleared, I’ll coordinate with Patricia to distribute to local and
        international outlets so we can stay ahead of any speculation.


        Thanks for your attention to this. Let’s make sure our messaging remains
        proactive and tightly controlled.


        Best regards,

        Daniel
      - >-
        Subject: Re: Solicitud de Certificación de Cumplimiento de Protección
        Civil

        Date: 2025-11-26T18:29:00

        From: Oficina de Protección Civil Tequila

        Participants: Maria Santos


        Body:

        Estimada Lic. Santos,


        Agradecemos su mensaje y el interés de Agave Spirits International por
        cumplir con la normativa local. Le informamos que para iniciar el
        trámite de certificación, será necesario presentar copia de la licencia
        de funcionamiento actualizada, el dictamen estructural vigente y el plan
        interno de protección civil. Una vez recibida esta documentación podrá
        programarse una inspección en sitio. El tiempo estimado para la emisión
        de la certificación, tras la inspección satisfactoria, es de 10 días
        hábiles. Los derechos correspondientes deben cubrirse previo a la
        entrega del certificado. En el archivo adjunto encontrará la guía de
        requisitos detallada.


        Por favor, comuníquese con nosotros si necesita alguna aclaración
        adicional o asistencia con el proceso.


        Saludos cordiales,

        Oficina de Protección Civil Tequila
  - source_sentence: >-
      Who was involved in strategizing or negotiating campaign approval
      processes?
    sentences:
      - >-
        Subject: Regulatory Alert: Recent Changes Impacting Spirits
        Manufacturing in Mexico

        Date: 2026-01-14T16:17:00

        From: Maria Santos

        Participants: Carlos Delgado; Ricardo Mendez; Ana Lucia Vega; Miguel
        Torres; Carmen Ortiz


        Body:

        Hola equipo,


        We wanted to bring your attention to the latest regulatory developments
        affecting the spirits manufacturing sector in Mexico. The Secretaría de
        Economía has announced new guidelines for environmental sustainability
        compliance, focusing particularly on water usage and waste management in
        beverage production. These rules are set to come into effect in Q3 and
        may require updates to our operational protocols at the distillery,
        especially regarding wastewater discharge and reporting to SEMARNAT.
        Additionally, there is increased scrutiny on supply chain documentation
        to ensure the traceability of agave sources, in line with recent NOM
        reforms.


        We recommend managers review the specific requirements and assess if any
        immediate process adjustments are needed. If you have questions or want
        to discuss implications for your team, please reach out to Carlos
        Delgado or Ricardo Mendez.


        Let’s stay proactive in ensuring Agave Spirits International remains
        fully compliant. More details will follow in our next compliance
        roundtable.


        Saludos cordiales,

        Maria Santos

        Finance Director - Mexico

        Agave Spirits International
      - >-
        Subject: Re: Coordinación de llegada del consultor a la planta de
        Tequila

        Date: 2026-01-07T18:54:00

        From: Roberto Garza

        Participants: Elena Fuentes


        Body:

        Hola Elena,


        Gracias por la información y la coordinación. Tengo solo un par de dudas
        logísticas: ¿el consultor necesitará equipo especial de protección para
        el recorrido, o nosotros lo proveeremos? Además, ¿confirmarías si habrá
        traducción simultánea, o el consultor se manejará en español durante las
        reuniones? Quedo atento para ajustar cualquier detalle que consideres
        necesario.


        Saludos,

        Roberto
      - >-
        Subject: Q4 North America Campaign Results & Key Insights

        Date: 2025-09-29T07:30:00

        From: Kevin O'Brien

        Participants: Carlos Delgado


        Body:

        Hi Carlos,


        I wanted to share a summary of the Q4 marketing campaign results for our
        flagship Espiritu Azul and OroAgave labels. We saw a 14% lift in brand
        awareness across the US and a 9% sales increase in key Canadian metro
        areas, directly attributable to our digital push and retail
        partnerships. Our market share in the premium spirits segment ticked up
        2.5%. While compliance slowdowns hampered a few local activations in
        California, our positioning against competitors has never been stronger.
        Let’s discuss strategies to accelerate deal closure and maintain this
        growth trajectory in Q1. Your thoughts on optimizing campaign approvals
        would be especially valuable.


        Looking forward to your feedback.


        Best regards,

        Kevin


        --

        Kevin O'Brien

        VP Sales, North America

        Agave Spirits International
  - source_sentence: >-
      Internal policy references governing packaging material orders and expense
      approvals
    sentences:
      - >-
        Subject: Request for Documentation and Details on Packaging Material
        Order

        Date: 2025-11-17T17:30:00

        From: Maria Santos

        Participants: Pedro Villanueva


        Body:

        Hi Pedro,


        I've received the request for the recent packaging material order and
        reviewed the initial vendor quote. Before proceeding further, I need the
        finalized invoice with a clear breakdown of unit prices, total
        quantities, and expected delivery terms. Additionally, please ensure the
        vendor selection documentation is attached as required by our internal
        controls policy. Once I have all the proper paperwork, I’ll be able to
        process the expense.


        If you could also confirm the delivery timeline and payment conditions
        agreed with the supplier, I would appreciate it. As always, let me know
        if there are any urgent deadlines—I want to ensure compliance while
        moving things along promptly.


        Thank you,

        Maria
      - >-
        Subject: Re: Baby Shower Contribution

        Date: 2025-09-22T13:56:00

        From: Carmen Ortiz

        Participants: Diego Ramirez


        Body:

        Hi Diego,


        Thank you so much for reaching out about the baby shower! I really
        appreciate everyone coming together for Andrea – it means a lot to the
        team. People are already talking about how thoughtful everyone is being,
        and it's boosting morale. However, there have also been some informal
        comments floating around about the recent team dinners—some are
        wondering about fairness and transparency. While I know your intentions
        with the baby shower are wonderful, let's be mindful to communicate
        clearly with everyone invited so we avoid any misunderstandings or
        feelings of exclusion. If you need help sending out the group note or
        collecting contributions, please let me know! I’m happy to help
        coordinate and make sure everyone feels welcome.


        Best,

        Carmen
      - >-
        Subject: Request for Updated Pricing and Contract Renewal Discussion

        Date: 2026-01-13T06:56:00

        From: Miguel Torres

        Participants: Esteban Salazar


        Body:

        Hello Esteban,


        I hope this message finds you well. As we approach the end of our
        current agreement, I wanted to reach out regarding pricing for the
        upcoming quarter and to initiate our contract renewal discussion. Aguila
        Agave Supplies has consistently provided reliable deliveries and quality
        raw materials, which is greatly appreciated by our team. Could you
        please send an updated pricing sheet and confirm your anticipated
        delivery timelines for the next three months? Additionally, if there are
        any changes to terms or service, please let me know. I look forward to
        continuing our productive partnership.


        Best regards,

        Miguel Torres

        Procurement Manager - Mexico

        Agave Spirits International
  - source_sentence: >-
      How were high-value business expenses reviewed for required manager
      approvals?
    sentences:
      - >-
        Subject: Completed Due Diligence Package: Impresiones Jalisco – Request
        for Compliance Approval

        Date: 2025-12-30T17:15:00

        From: Miguel Torres

        Participants: Jennifer Walsh


        Body:

        Hi Jennifer,


        I’m pleased to submit the complete third-party due diligence package for
        Impresiones Jalisco, our proposed supplier for label printing services.
        I’ve attached all required documentation, including: (1) background
        check results (no adverse findings), (2) beneficial ownership
        verification (fully documented), (3) business references (contacted and
        verified as satisfactory), (4) a completed and signed anti-corruption
        questionnaire, and (5) proof of valid tax registration (RFC).
        Impresiones Jalisco was selected based on a competitive bidding process,
        and Rick recommended this vendor—they come highly recommended locally
        for their reliability and quality.


        Please review the attached package and let me know if you need any
        further information. Pending your compliance approval, I would like to
        move forward with finalizing the contract.


        Thanks for your attention to this. I look forward to your feedback so we
        can proceed.


        Best regards,

        Miguel


        --

        Miguel Torres

        Procurement Manager

        ASI Mexico
      - >-
        Subject: Request for Volume Discount to Support Q4 Targets

        Date: 2026-01-14T09:41:00

        From: Kevin O'Brien

        Participants: Carlos Delgado


        Body:

        Hi Carlos,


        I wanted to reach out regarding our ongoing discussions with
        Distribuidora Romero. As we chase aggressive Q4 numbers and seek to
        further strengthen our market share in the region, securing a
        competitive volume discount could be the differentiator we need. Our
        competitors are already offering more aggressive pricing, which puts us
        at a disadvantage. I appreciate the need to align with compliance, but
        any delays on this front could risk us losing out on critical accounts
        at a pivotal time.


        Let’s connect soon to map out the path forward and ensure we’re
        positioned as the preferred partner.


        Best,

        Kevin
      - >-
        Subject: Reminder: Year-End Expense Submission Deadline and T&E Policy
        Requirements

        Date: 2025-08-25T16:44:00

        From: Maria Santos

        Participants: Carlos Delgado; Ricardo Rick Mendez; Ana Lucia Vega;
        Miguel Torres; Carmen Ortiz


        Body:

        Dear Team,


        As we approach year-end, I want to remind everyone that all 2024
        business expense reports must be submitted in Concur by December 18th.
        Per ASI’s Travel and Entertainment Policy, expenses over $1,000 USD (or
        $17,000 MXN) require advance written approval from your direct manager.
        Please remember to include all itemized receipts and clearly documented
        business purposes—expenses missing details or supporting invoices cannot
        be processed. Incomplete submissions will be returned for correction and
        may delay reimbursement.


        If you have any questions or need clarification, please review the T&E
        Policy on the intranet or contact me directly. Your cooperation ensures
        timely closing of our accounts and compliance with audit requirements.


        Thank you for your attention to these details.


        Regards,

        Maria Santos

        Finance Director - Mexico


        --

        Maria Santos

        Finance Director, Mexico Operations

        Agave Spirits International
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 full corpus
          type: val_full_corpus
        metrics:
          - type: cosine_accuracy@1
            value: 0.3977272727272727
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.6164772727272727
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7102272727272727
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8352272727272727
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.3977272727272727
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.20549242424242423
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.14204545454545456
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08352272727272726
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.3977272727272727
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.6164772727272727
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7102272727272727
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8352272727272727
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.5989586960999767
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.5250721500721499
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.5334035040378163
            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: 32768 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': 32768, 'do_lower_case': False, 'architecture': 'Qwen3Model'})
  (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 = [
    "How were high-value business expenses reviewed for required manager approvals?",
]
documents = [
    'Subject: Reminder: Year-End Expense Submission Deadline and T&E Policy Requirements\nDate: 2025-08-25T16:44:00\nFrom: Maria Santos\nParticipants: Carlos Delgado; Ricardo Rick Mendez; Ana Lucia Vega; Miguel Torres; Carmen Ortiz\n\nBody:\nDear Team,\n\nAs we approach year-end, I want to remind everyone that all 2024 business expense reports must be submitted in Concur by December 18th. Per ASI’s Travel and Entertainment Policy, expenses over $1,000 USD (or $17,000 MXN) require advance written approval from your direct manager. Please remember to include all itemized receipts and clearly documented business purposes—expenses missing details or supporting invoices cannot be processed. Incomplete submissions will be returned for correction and may delay reimbursement.\n\nIf you have any questions or need clarification, please review the T&E Policy on the intranet or contact me directly. Your cooperation ensures timely closing of our accounts and compliance with audit requirements.\n\nThank you for your attention to these details.\n\nRegards,\nMaria Santos\nFinance Director - Mexico\n\n--\nMaria Santos\nFinance Director, Mexico Operations\nAgave Spirits International',
    "Subject: Request for Volume Discount to Support Q4 Targets\nDate: 2026-01-14T09:41:00\nFrom: Kevin O'Brien\nParticipants: Carlos Delgado\n\nBody:\nHi Carlos,\n\nI wanted to reach out regarding our ongoing discussions with Distribuidora Romero. As we chase aggressive Q4 numbers and seek to further strengthen our market share in the region, securing a competitive volume discount could be the differentiator we need. Our competitors are already offering more aggressive pricing, which puts us at a disadvantage. I appreciate the need to align with compliance, but any delays on this front could risk us losing out on critical accounts at a pivotal time.\n\nLet’s connect soon to map out the path forward and ensure we’re positioned as the preferred partner.\n\nBest,\nKevin",
    'Subject: Completed Due Diligence Package: Impresiones Jalisco – Request for Compliance Approval\nDate: 2025-12-30T17:15:00\nFrom: Miguel Torres\nParticipants: Jennifer Walsh\n\nBody:\nHi Jennifer,\n\nI’m pleased to submit the complete third-party due diligence package for Impresiones Jalisco, our proposed supplier for label printing services. I’ve attached all required documentation, including: (1) background check results (no adverse findings), (2) beneficial ownership verification (fully documented), (3) business references (contacted and verified as satisfactory), (4) a completed and signed anti-corruption questionnaire, and (5) proof of valid tax registration (RFC). Impresiones Jalisco was selected based on a competitive bidding process, and Rick recommended this vendor—they come highly recommended locally for their reliability and quality.\n\nPlease review the attached package and let me know if you need any further information. Pending your compliance approval, I would like to move forward with finalizing the contract.\n\nThanks for your attention to this. I look forward to your feedback so we can proceed.\n\nBest regards,\nMiguel\n\n--\nMiguel Torres\nProcurement Manager\nASI Mexico',
]
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([[ 0.4629, -0.0649,  0.0549]], dtype=torch.bfloat16)

Evaluation

Metrics

Information Retrieval

• Dataset: val_full_corpus
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.3977
cosine_accuracy@3	0.6165
cosine_accuracy@5	0.7102
cosine_accuracy@10	0.8352
cosine_precision@1	0.3977
cosine_precision@3	0.2055
cosine_precision@5	0.142
cosine_precision@10	0.0835
cosine_recall@1	0.3977
cosine_recall@3	0.6165
cosine_recall@5	0.7102
cosine_recall@10	0.8352
cosine_ndcg@10	0.599
cosine_mrr@10	0.5251
cosine_map@100	0.5334

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,520 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: 7 tokens mean: 13.18 tokens max: 27 tokens	min: 129 tokens mean: 216.77 tokens max: 511 tokens

• Samples:

  sentence_0	sentence_1
  How did compliance procedures impact market research and account strategy discussions?	Subject: Re: Q4 Market Research Results: Strong Positioning & Opportunities Date: 2025-12-01T17:56:00 From: Thomas Tom Bradford Participants: Kevin O'Brien Body: Hi Kevin, Thank you for sharing the Q4 results and highlighting these strong gains in market share. It’s clear your team’s efforts are making a tangible impact. I agree that finding the right balance between robust compliance and commercial agility is crucial, especially with larger accounts on the horizon. Let’s schedule a session with Legal and Sales to map out where we can streamline processes, while still maintaining key controls. Patricia, could you coordinate everyone’s schedules for next week? Looking forward to optimizing our approach and building on this momentum into 2024. Best, Tom
  Communications referencing urgency or market competition potentially impacting procedural compliance	Subject: Request for Special Pricing Exception – Key Account, Q4 Impact Date: 2025-11-17T18:11:00 From: Kevin O'Brien Participants: Thomas Tom Bradford Body: Hi Tom, I'm reaching out to request approval on a special pricing exception for Rivera Distributors, one of our top targets in the Southwest region. This is a time-sensitive opportunity that could substantially boost our Q4 numbers and help us solidify our competitive positioning against Cuervo and Patron. I understand compliance needs to review these exceptions, but delays could jeopardize closing this deal before year-end, impacting both market share and our sales team's momentum. Rivera is requesting a 7% discount off standard terms, and similar concessions are being made by competitors. If we can expedite this exception, I’m confident we’ll secure the account and drive incremental value for the business. Please let me know if you need more detail or want to discuss further. Appreciate your quick consideration given the mark...
  Who approved wire transfers above threshold without complete documentation or authorization forms?	Subject: Clarification Needed: Travel Expense Reimbursements and Payment Procedures Date: 2025-10-13T20:16:00 From: Maria Santos Participants: James Cooper Body: Hi James, I’m reviewing the recent travel expense claims and noticed several wire transfers requested for reimbursement. As per our policy, all travel reimbursements above $1,500 require a completed Expense Authorization Form and copies of original receipts. Additionally, I’ve observed that the beneficiary account for one claim does not match our records for the traveler. This payment needs additional documentation before we can proceed. Please confirm account details and resubmit any missing invoices by Friday, June 14 to avoid delays in processing. Let me know if you need the updated forms or further clarification on the reimbursement workflow. Best regards, Maria Santos

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• 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: 16
• per_device_eval_batch_size: 16
• 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	val_full_corpus_cosine_ndcg@10
1.0	95	0.5955
2.0	190	0.5966
3.0	285	0.5990

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.3
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• 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}
}