| --- |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - dense |
| - generated_from_trainer |
| - dataset_size:1548 |
| - loss:DPOLoss |
| base_model: Qwen/Qwen3-Embedding-0.6B |
| widget: |
| - source_sentence: Requests for information on anonymous whistleblower or concern |
| reporting procedures |
| sentences: |
| - 'Subject: Re: Employee Morale and Recent Informal Concerns |
| |
| Date: 2026-01-20T16:53:00 |
| |
| From: Thomas Tom Bradford |
| |
| Participants: Carmen Ortiz |
| |
| |
| Body: |
| |
| Hi Carmen, |
| |
| |
| Thank you for proactively raising these important issues and for sharing the candid |
| feedback from our staff in Tequila. I completely agree that transparent communication |
| is essential, and I appreciate your suggestion to hold an all-hands meeting soon. |
| It’s clear that addressing concerns around perceived favoritism and keeping everyone |
| informed about our decision-making process is crucial for maintaining morale and |
| trust within the team. |
| |
| |
| Let’s coordinate on scheduling this meeting before the end of the month, and I’d |
| welcome your insights on the agenda and on the draft communication you mentioned. |
| Please go ahead and share your draft with the group. I’ll also connect with Sarah |
| and Patricia so we can align on messaging and logistics. |
| |
| |
| Thanks again for your initiative, and please keep us posted on any further feedback |
| you hear in the meantime. |
| |
| |
| Best regards, |
| |
| Tom' |
| - 'Subject: Urgent: Additional Documentation Required for Payment Processing |
| |
| Date: 2025-12-30T20:00:00 |
| |
| From: James Cooper |
| |
| Participants: Victoria Hayes |
| |
| |
| Body: |
| |
| Hi Victoria, |
| |
| |
| I hope this message finds you well. We are in the process of preparing our claim |
| submission to Chubb, but I''ve encountered a discrepancy with the beneficiary |
| details for the recent wire transfer. The beneficiary account listed in the payment |
| instructions does not match our internal records. To proceed, we will need additional |
| documentation clarifying the intended recipient and supporting the legitimacy |
| of the transaction. This is essential for both audit and compliance purposes. |
| |
| |
| Please let me know if you can provide the necessary documents or if there''s a |
| specific contact at Chubb who can assist with further verification. I want to |
| ensure there are no delays in our claim due to incomplete or mismatched payment |
| information. |
| |
| |
| Looking forward to your prompt response. |
| |
| |
| Best regards, |
| |
| James Cooper |
| |
| Treasury Manager |
| |
| |
| -- |
| |
| James Cooper |
| |
| Treasury Manager |
| |
| Agave Spirits International' |
| - 'Subject: Concern About Recent Events and Reporting Process |
| |
| Date: 2025-08-14T13:01:00 |
| |
| From: Arturo Sandoval |
| |
| Participants: Carmen Ortiz |
| |
| |
| Body: |
| |
| Hi Carmen, |
| |
| |
| I hope you don’t mind me reaching out. I wanted to share that lately, I’ve been |
| feeling uncomfortable with what’s happening around the plant. Rick asked me to |
| prepare the water samples last week, and while I was working late, I noticed some |
| unusual visitors in the admin area. I’ve also seen some things that worry me, |
| especially around the dinners with the mayor. People in town talk about the mayor’s |
| relationship with certain groups, and there are rumors about his connections. |
| I’m worried about the company’s reputation if any of this is true. Can you let |
| me know how I could report concerns anonymously? I want to do the right thing |
| but I’m not sure how to proceed. |
| |
| |
| Thank you for your guidance. |
| |
| |
| Best, |
| |
| Arturo |
| |
| |
| -- |
| |
| Arturo Sandoval |
| |
| Environmental Technician |
| |
| Destilería Agave Spirits' |
| - 'Subject: Coordinated Project Status Update and Next Steps |
| |
| Date: 2025-11-21T15:20:00 |
| |
| From: Patricia Reeves |
| |
| Participants: Sarah Mitchell; Luis Fernando Chavez; Hector Vargas |
| |
| |
| Body: |
| |
| Hello Team, |
| |
| |
| I wanted to share an update on the ongoing Agave Expansion Project and highlight |
| the need for closer coordination among our departments. We have made good progress |
| on permitting and environmental assessments, but upcoming deadlines require tighter |
| collaboration between Legal, Urban Development, and Environmental teams. Please |
| review the attached timeline and confirm your department’s primary contact for |
| weekly sync meetings. This coordination will ensure we address any regulatory, |
| compliance, and technical issues in a timely manner. |
| |
| |
| Let’s work together to keep momentum and avoid bottlenecks. If you have any concerns |
| or require additional support, don’t hesitate to reach out. |
| |
| |
| Best regards, |
| |
| Patricia Reeves |
| |
| Executive Assistant to CEO |
| |
| |
| -- |
| |
| Patricia Reeves |
| |
| Executive Assistant to the CEO |
| |
| Agave Spirits International' |
| - source_sentence: Which executives attended offsite dinners as part of audit review |
| preparations? |
| sentences: |
| - 'Subject: Follow-Up Required: Discrepancies in Beneficiary Account for Wire Transfer |
| |
| Date: 2025-08-11T15:13:00 |
| |
| From: James Cooper |
| |
| Participants: Maria Santos |
| |
| |
| Body: |
| |
| Hi Maria, |
| |
| |
| I''m following up regarding the recent wire transfer associated with the Tequila |
| project. Our treasury review flagged that the beneficiary account currently listed |
| does not match our records on file for this vendor. Before we can process the |
| payment, we need additional documentation to verify the account details and ensure |
| compliance with our internal controls. Could you please coordinate with the vendor |
| to obtain a current bank confirmation letter and any supporting documents? |
| |
| |
| Delays in providing this information may impact our timeline for releasing funds, |
| so your prompt assistance would be appreciated. Please let me know if you require |
| a template or further guidance for the needed documents. |
| |
| |
| Best regards, |
| |
| James |
| |
| |
| -- |
| |
| James Cooper |
| |
| Treasury Manager |
| |
| Agave Spirits International' |
| - 'Subject: Revisión y aprobación de asientos contables – Solicitud de documentación |
| adicional |
| |
| Date: 2025-12-01T17:18:00 |
| |
| From: David Chen |
| |
| Participants: Maria Santos |
| |
| |
| Body: |
| |
| Hola equipo, |
| |
| |
| He revisado los asientos contables presentados para el cierre de este mes. Desde |
| una perspectiva financiera, observo que varias de las descripciones de gastos |
| carecen de detalles suficientes y no identifican claramente la naturaleza de los |
| servicios o productos facturados. Los datos muestran discrepancias en tres partidas |
| específicas que superan los límites habituales del presupuesto. Solicito que adjunten |
| la documentación de respaldo correspondiente (facturas, contratos y autorizaciones |
| internas) antes de proceder con la aprobación final. La transparencia es indispensable |
| para cumplir con los estándares de auditoría y asegurar la integridad de los estados |
| financieros. |
| |
| |
| Agradezco su pronta respuesta con los documentos solicitados. |
| |
| |
| Saludos, |
| |
| David Chen |
| |
| |
| -- |
| |
| David Chen |
| |
| Chief Financial Officer |
| |
| Agave Spirits International' |
| - 'Subject: Brand Positioning Adjustments for Q4 – Strategic Recommendations |
| |
| Date: 2025-10-28T12:13:00 |
| |
| From: Kevin O''Brien |
| |
| Participants: Thomas Tom Bradford; Sarah Mitchell; Patricia Reeves |
| |
| |
| Body: |
| |
| Hi Team, |
| |
| |
| After reviewing our preliminary Q4 numbers, I''m seeing clear signs that our recent |
| brand messaging updates are helping us claw back market share, especially in key |
| North American regions. However, competitor promos are accelerating, which underscores |
| the need to streamline our go-to-market approvals. Compliance is critical, but |
| continual delays risk momentum just as we''re gaining traction. Let’s sync on |
| how we can balance both speed and adherence. |
| |
| |
| Looking forward to discussing this further in our upcoming exec call. |
| |
| |
| Best, |
| |
| Kevin |
| |
| |
| -- |
| |
| Kevin O''Brien |
| |
| VP Sales, North America |
| |
| Agave Spirits International' |
| - 'Subject: Re: Travel Arrangements for Audit Preparation – Schedule and Recommendations |
| |
| Date: 2025-08-25T17:50:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Elena Fuentes |
| |
| |
| Body: |
| |
| Hi Elena, |
| |
| |
| Thank you for organizing the travel and hotel arrangements so efficiently. Please |
| book the 9:00 AM flight for me, as I prefer arriving earlier to allow some buffer |
| before the meetings. Hotel Demetria sounds perfect, and I appreciate your discretion |
| with the arrangements. For dinner at Hueso, please include Lic. Fernando Reyes |
| and Ricardo Orozco, as their insights will be helpful during our discussions. |
| The reserved audit review slots work well for my schedule. |
| |
| |
| Let me know if you need any additional information from my end. Thanks again for |
| taking care of the details. |
| |
| |
| Best, |
| |
| Carlos' |
| - source_sentence: How does the company document legitimate business purposes for |
| community sponsorships near government officials? |
| sentences: |
| - 'Subject: Inventory Discrepancy at Tequila Warehouse – Let''s Resolve Together |
| |
| Date: 2025-08-08T17:18:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Roberto Garza |
| |
| |
| Body: |
| |
| Estimado Roberto, |
| |
| |
| I wanted to bring to your attention a small discrepancy we detected during our |
| recent inventory review—nothing too alarming, just a difference of about 420 liters |
| between documented and actual agave syrup stock. In Mexico, relationships matter, |
| and our team always strives for full transparency. I’m confident these minor variances |
| arise from day-to-day realities—sometimes a late-night delivery or a missed signature, |
| ya sabes cómo es. Vamos resolviendo this as we always do, con confianza y buena |
| comunicación. I propose we review circulation logs together and have Miguel cross-check |
| supplier dispatch notes; perhaps even a cafecito with the warehouse crew to foster |
| understanding. This is how business is done here—working closely with people, |
| not just paperwork. |
| |
| |
| Let’s coordinate a time to meet and sort through this. My priority is ensuring |
| everything reflects well on the team, and making sure our processes stay robust |
| without unnecessary noise. |
| |
| |
| Saludos cordiales, |
| |
| Carlos |
| |
| |
| -- |
| |
| Carlos Delgado |
| |
| Country Manager, Mexico Operations |
| |
| Agave Spirits International |
| |
| Tequila, Jalisco' |
| - 'Subject: Consulta sobre cálculo de IVA para reporte trimestral |
| |
| Date: 2025-09-16T17:56:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Maria Santos |
| |
| |
| Body: |
| |
| Hola Maria, |
| |
| |
| Thank you so much for raising your thoughtful question about the VAT calculation |
| for our upcoming quarterly report. As you know, aquí en México las relaciones |
| y las costumbres locales son muy importantes — this is how business is done here. |
| I want to ensure that our approach is fully compliant with both SAT expectations |
| and the nuances that have always guided our accounting practices. I also know |
| you and your equipo have been handling these issues with exceptional care, and |
| I trust your judgment. However, given the recent changes in local tax policy, |
| perhaps we should convene—maybe just a small dinner with our usual advisors—to |
| review our criteria and confirm we’re aligned with both corporate and local standards. |
| It’s always best to be proactive, y sabes que estoy aquí para apoyar a mi equipo |
| en todo. |
| |
| |
| Let me know if you’d like me to make some calls to gather additional perspective |
| or if you want to move forward with a specific advisor you have in mind. Your |
| diligence benefits all of us. |
| |
| |
| Saludos cordiales, |
| |
| Carlos |
| |
| |
| -- |
| |
| Carlos Delgado |
| |
| Country Manager, Mexico Operations |
| |
| Agave Spirits International |
| |
| Tequila, Jalisco' |
| - 'Subject: Request for Guidance: Proposed Sponsorship of Local School Initiative |
| |
| Date: 2025-09-05T08:37:00 |
| |
| From: Amanda Foster |
| |
| Participants: Sarah Mitchell |
| |
| |
| Body: |
| |
| Hi Sarah, |
| |
| |
| I wanted to bring to your attention a request we received regarding sponsorship |
| of a local school initiative in Tequila. While supporting education aligns with |
| our corporate values and could offer positive community engagement, I am keenly |
| aware that any sponsorship in this context may pose FCPA and compliance considerations. |
| Have we fully documented the legitimate business purpose and assessed potential |
| perception risks? Before proceeding, I recommend we secure all required pre-approvals |
| and ensure our due diligence process is robust. |
| |
| |
| Please advise on next steps and any internal protocols we should follow to avoid |
| unintended compliance issues. |
| |
| |
| Best regards, |
| |
| Amanda' |
| - 'Subject: Inventory Discrepancy at Tequila Warehouse – Let''s Resolve Together |
| |
| Date: 2025-08-08T17:18:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Roberto Garza |
| |
| |
| Body: |
| |
| Estimado Roberto, |
| |
| |
| I wanted to bring to your attention a small discrepancy we detected during our |
| recent inventory review—nothing too alarming, just a difference of about 420 liters |
| between documented and actual agave syrup stock. In Mexico, relationships matter, |
| and our team always strives for full transparency. I’m confident these minor variances |
| arise from day-to-day realities—sometimes a late-night delivery or a missed signature, |
| ya sabes cómo es. Vamos resolviendo this as we always do, con confianza y buena |
| comunicación. I propose we review circulation logs together and have Miguel cross-check |
| supplier dispatch notes; perhaps even a cafecito with the warehouse crew to foster |
| understanding. This is how business is done here—working closely with people, |
| not just paperwork. |
| |
| |
| Let’s coordinate a time to meet and sort through this. My priority is ensuring |
| everything reflects well on the team, and making sure our processes stay robust |
| without unnecessary noise. |
| |
| |
| Saludos cordiales, |
| |
| Carlos |
| |
| |
| -- |
| |
| Carlos Delgado |
| |
| Country Manager, Mexico Operations |
| |
| Agave Spirits International |
| |
| Tequila, Jalisco' |
| - source_sentence: Private event planning involving leadership and potential beneficiaries |
| such as mayors or their family members |
| sentences: |
| - 'Subject: Re: Reserva de cena especial en La Tequila para 6 personas – viernes |
| de enero |
| |
| Date: 2025-10-29T21:56:00 |
| |
| From: Elena Fuentes |
| |
| Participants: Ricardo Mendez |
| |
| |
| Body: |
| |
| Hola Ricardo, |
| |
| |
| Por indicación de Carlos, he gestionado la reservación para seis personas el viernes |
| por la noche en La Tequila. El salón privado está confirmado y el menú seleccionado |
| incluye opciones gourmet y una amplia variedad de tequilas premium. El costo estimado |
| es de 3,500 MXN por persona. ¿Prefieres que cargue el pago a la tarjeta corporativa |
| o seguimos con el proveedor habitual para la facturación? Adicionalmente, tengo |
| presente que la Sra. Sofía Reyes tiene restricciones alimenticias; ya informé |
| al chef para que lo tomen en cuenta y todo esté a la altura de lo esperado. Te |
| confirmo los detalles finales apenas reciba la última actualización del restaurante. |
| |
| |
| Quedo atenta a tus indicaciones. |
| |
| |
| Saludos, |
| |
| Elena' |
| - 'Subject: Re: Consulta sobre Clasificación Arancelaria – Necesitamos Perspectivas |
| Claras |
| |
| Date: 2025-11-05T16:14:00 |
| |
| From: Maria Santos |
| |
| Participants: Carlos Delgado |
| |
| |
| Body: |
| |
| Hola Carlos, |
| |
| |
| Gracias por tu mensaje y por tu apoyo constante al equipo. Estoy de acuerdo en |
| que las relaciones locales son clave para avanzar en estos temas. Estoy preparando |
| un resumen detallado con los argumentos presentados y los puntos donde hemos encontrado |
| resistencia con los agentes aduanales. Por ahora, mi impresión es que podríamos |
| agotar primero la vía informal con una reunión o cena discreta, aunque sí sugiero |
| tener a nuestros asesores externos listos por si el tema escala o si surgen dudas |
| legales específicas. Te lo envío antes del jueves para que lo revises y podamos |
| decidir juntos el mejor camino a seguir. |
| |
| |
| Quedo pendiente y agradezco tus comentarios. |
| |
| |
| Saludos, |
| |
| Maria' |
| - 'Subject: Re: Re: Committee Participation in Tequila Industry Associations |
| |
| Date: 2025-08-19T16:26:00 |
| |
| From: Thomas Bradford |
| |
| Participants: Alejandro Reyes Gutierrez |
| |
| |
| Body: |
| |
| Dear Alejandro, |
| |
| |
| I hope this message finds you well. I am reaching out to discuss Agave Spirits |
| International’s continued participation in the various committees associated with |
| the tequila industry, particularly those focused on sustainable production and |
| environmental impact. We believe strong collaboration between the municipality |
| and industry is critical for addressing pressing issues and ensuring compliance |
| with evolving regulations. I am interested in hearing your views on how we can |
| further contribute to these committees and strengthen our coordination with local |
| authorities and stakeholders. Please let me know your availability for a meeting |
| to discuss these initiatives in detail. |
| |
| |
| Thank you for your attention, and I look forward to your response. |
| |
| |
| Best regards, |
| |
| Tom' |
| - 'Subject: Upcoming Trade Group Meeting: Tequila Industry Associations |
| |
| Date: 2025-10-27T06:42:00 |
| |
| From: Thomas Tom Bradford |
| |
| Participants: Sarah Mitchell; Patricia Reeves; Alejandro Reyes Gutierrez; Luis |
| Fernando Chavez; Hector Vargas |
| |
| |
| Body: |
| |
| Dear Colleagues, |
| |
| |
| I wanted to inform you that the next meeting of the main tequila industry trade |
| group is scheduled for next Thursday at 10:00 AM at the Consejo Regulador del |
| Tequila headquarters. The agenda will focus on upcoming regulatory proposals, |
| sustainability initiatives, and recent market trends, including discussion of |
| changes proposed by local and international stakeholders. Your participation is |
| strongly encouraged, as we will be developing industry-wide positions on several |
| key issues. Please confirm your availability, and feel free to propose any additional |
| topics for the agenda in advance. |
| |
| |
| Best regards, |
| |
| Thomas "Tom" Bradford |
| |
| CEO, Agave Spirits International |
| |
| |
| -- |
| |
| Thomas Bradford |
| |
| Chief Executive Officer |
| |
| Agave Spirits International |
| |
| Dallas, TX' |
| - source_sentence: Which employees discussed circumventing compliance protocols to |
| secure government approvals? |
| sentences: |
| - 'Subject: PRIVILEGED AND CONFIDENTIAL - ATTORNEY-CLIENT COMMUNICATION - Mexico |
| Operations Concern |
| |
| Date: 2025-09-17T08:05:00 |
| |
| From: Jennifer Walsh |
| |
| Participants: Sarah Mitchell |
| |
| |
| Body: |
| |
| Hi Sarah, |
| |
| |
| For the record, I am forwarding a summary of a serious anonymous complaint received |
| via our ethics hotline regarding our Mexico operations. The report alleges that |
| the EHS Manager (Ricardo Mendez) hosted multiple dinners with a local government |
| official, provided gifts, and facilitated payments through fake invoices. There |
| are further red flags: the Country Manager (Carlos Delgado) is alleged to have |
| been aware, and there are mentions of organized crime involvement. These allegations, |
| if substantiated, raise significant FCPA exposure. |
| |
| |
| I strongly recommend we immediately engage outside counsel with FCPA expertise |
| to lead an independent investigation. We must document everything, preserve all |
| potentially relevant documents and communications, and strictly limit knowledge |
| of this matter to essential personnel only. Please confirm next steps and advise |
| on initial outreach to external counsel. Are there any additional protocols you |
| want implemented at this stage? |
| |
| |
| Best regards, |
| |
| Jennifer |
| |
| |
| -- |
| |
| Jennifer Walsh |
| |
| Vice President, Global Compliance & Ethics |
| |
| Agave Spirits International |
| |
| CONFIDENTIAL - Attorney Work Product' |
| - 'Subject: Re: Request for Special Pricing Exception – Key Distributor Opportunity |
| (Q4 Impact) |
| |
| Date: 2025-09-15T16:23:00 |
| |
| From: Thomas Bradford |
| |
| Participants: Kevin O''Brien |
| |
| |
| Body: |
| |
| Hi Kevin, |
| |
| |
| Thank you for flagging this opportunity and providing context regarding the potential |
| impact on our Q4 numbers. I agree that winning this distributor could be a game-changer, |
| but we need to ensure any pricing exception aligns with our compliance framework |
| and avoids unintended precedents. Sarah, could you please review the specifics |
| from a legal/compliance standpoint and advise on any restrictions or additional |
| documentation required? Assuming there are no major obstacles, I''m supportive |
| of proceeding with a tailored discount to secure the account. |
| |
| |
| Let’s coordinate a quick call Monday to finalize. |
| |
| |
| Best, |
| |
| Tom' |
| - 'Subject: Road Access Update – Impact on Distillery Operations |
| |
| Date: 2025-08-27T12:31:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Thomas Bradford; Patricia Reeves; Roberto Garza |
| |
| |
| Body: |
| |
| Estimados colegas, |
| |
| |
| I hope this message finds you well. I want to bring to your attention the current |
| conditions of the main access road to our Tequila distillery. We''ve recently |
| experienced increased delays due to potholes and minor landslides, particularly |
| after last week''s storms. Nuestro equipo de logística is doing their best, but |
| these challenges are beginning to affect deliveries and staff commutes. |
| |
| |
| As you know, in Mexico, relationships matter, and we have maintained ongoing conversations |
| with Municipio officials. This is how business is done here – through dialogue |
| and understanding. Mi equipo and I will continue nurturing these connections, |
| perhaps with just a small cena to discuss solutions informally, as is our local |
| custom. Please rest assured, I am advocating strongly for our people and operations. |
| |
| |
| If you have any questions or would like to discuss further actions, let me know. |
| I appreciate your trust in managing these local matters the ''right way''. |
| |
| |
| Un abrazo, |
| |
| Carlos |
| |
| |
| -- |
| |
| Carlos Delgado |
| |
| Country Manager, Mexico Operations |
| |
| Agave Spirits International |
| |
| Tequila, Jalisco' |
| - 'Subject: Re: Urgent: Water Permit Renewal Delay Threatening Production Levels |
| |
| Date: 2025-08-25T15:02:00 |
| |
| From: Carlos Delgado |
| |
| Participants: Roberto Garza |
| |
| |
| Body: |
| |
| Hola Roberto, |
| |
| |
| Thank you for raising your concerns. I completely understand the pressure this |
| delay puts on the plant, but I want to reassure you that Rick has the situation |
| well in hand. We’ve been investing a lot in our relationship with the local authorities—In |
| Mexico, relationships matter, ya sabes. The mayor has been very receptive to our |
| efforts, and we’ve had several productive meetings (and just a small dinner or |
| two) with municipal leadership. This is how business is done here; these things |
| take relationship building, and I’m confident we’ll have good news soon. Por favor, |
| don’t worry—déjalo en nuestras manos. I’ll keep you posted as soon as I hear anything |
| definitive. |
| |
| |
| Un abrazo, |
| |
| Carlos' |
| 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: 0.27076923076923076 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.5046153846153846 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.5815384615384616 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.676923076923077 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.27076923076923076 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.16820512820512823 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.11630769230769229 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.06769230769230769 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.27076923076923076 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.5046153846153846 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.5815384615384616 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.676923076923077 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.4684036352190012 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.4022136752136752 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.4138601344933103 |
| name: Cosine Map@100 |
| --- |
| |
| # SentenceTransformer based on Qwen/Qwen3-Embedding-0.6B |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/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](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision c54f2e6e80b2d7b7de06f51cec4959f6b3e03418 --> |
| - **Maximum Sequence Length:** 32768 tokens |
| - **Output Dimensionality:** 1024 dimensions |
| - **Similarity Function:** Cosine Similarity |
| <!-- - **Training Dataset:** Unknown --> |
| <!-- - **Language:** Unknown --> |
| <!-- - **License:** Unknown --> |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'max_seq_length': 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: |
|
|
| ```bash |
| pip install -U sentence-transformers |
| ``` |
|
|
| Then you can load this model and run inference. |
| ```python |
| from sentence_transformers import SentenceTransformer |
| |
| # Download from the 🤗 Hub |
| model = SentenceTransformer("sentence_transformers_model_id") |
| # Run inference |
| queries = [ |
| "Which employees discussed circumventing compliance protocols to secure government approvals?", |
| ] |
| documents = [ |
| 'Subject: PRIVILEGED AND CONFIDENTIAL - ATTORNEY-CLIENT COMMUNICATION - Mexico Operations Concern\nDate: 2025-09-17T08:05:00\nFrom: Jennifer Walsh\nParticipants: Sarah Mitchell\n\nBody:\nHi Sarah,\n\nFor the record, I am forwarding a summary of a serious anonymous complaint received via our ethics hotline regarding our Mexico operations. The report alleges that the EHS Manager (Ricardo Mendez) hosted multiple dinners with a local government official, provided gifts, and facilitated payments through fake invoices. There are further red flags: the Country Manager (Carlos Delgado) is alleged to have been aware, and there are mentions of organized crime involvement. These allegations, if substantiated, raise significant FCPA exposure.\n\nI strongly recommend we immediately engage outside counsel with FCPA expertise to lead an independent investigation. We must document everything, preserve all potentially relevant documents and communications, and strictly limit knowledge of this matter to essential personnel only. Please confirm next steps and advise on initial outreach to external counsel. Are there any additional protocols you want implemented at this stage?\n\nBest regards,\nJennifer\n\n--\nJennifer Walsh\nVice President, Global Compliance & Ethics\nAgave Spirits International\nCONFIDENTIAL - Attorney Work Product', |
| "Subject: Re: Request for Special Pricing Exception – Key Distributor Opportunity (Q4 Impact)\nDate: 2025-09-15T16:23:00\nFrom: Thomas Bradford\nParticipants: Kevin O'Brien\n\nBody:\nHi Kevin,\n\nThank you for flagging this opportunity and providing context regarding the potential impact on our Q4 numbers. I agree that winning this distributor could be a game-changer, but we need to ensure any pricing exception aligns with our compliance framework and avoids unintended precedents. Sarah, could you please review the specifics from a legal/compliance standpoint and advise on any restrictions or additional documentation required? Assuming there are no major obstacles, I'm supportive of proceeding with a tailored discount to secure the account.\n\nLet’s coordinate a quick call Monday to finalize.\n\nBest,\nTom", |
| 'Subject: Re: Urgent: Water Permit Renewal Delay Threatening Production Levels\nDate: 2025-08-25T15:02:00\nFrom: Carlos Delgado\nParticipants: Roberto Garza\n\nBody:\nHola Roberto,\n\nThank you for raising your concerns. I completely understand the pressure this delay puts on the plant, but I want to reassure you that Rick has the situation well in hand. We’ve been investing a lot in our relationship with the local authorities—In Mexico, relationships matter, ya sabes. The mayor has been very receptive to our efforts, and we’ve had several productive meetings (and just a small dinner or two) with municipal leadership. This is how business is done here; these things take relationship building, and I’m confident we’ll have good news soon. Por favor, don’t worry—déjalo en nuestras manos. I’ll keep you posted as soon as I hear anything definitive.\n\nUn abrazo,\nCarlos', |
| ] |
| 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([[ 0.3281, -0.1060, 0.0874]], dtype=torch.bfloat16) |
| ``` |
|
|
| <!-- |
| ### Direct Usage (Transformers) |
|
|
| <details><summary>Click to see the direct usage in Transformers</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Downstream Usage (Sentence Transformers) |
|
|
| You can finetune this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Out-of-Scope Use |
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| --> |
|
|
| ## Evaluation |
|
|
| ### Metrics |
|
|
| #### Information Retrieval |
|
|
| * Dataset: `val_full_corpus` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------|:-----------| |
| | cosine_accuracy@1 | 0.2708 | |
| | cosine_accuracy@3 | 0.5046 | |
| | cosine_accuracy@5 | 0.5815 | |
| | cosine_accuracy@10 | 0.6769 | |
| | cosine_precision@1 | 0.2708 | |
| | cosine_precision@3 | 0.1682 | |
| | cosine_precision@5 | 0.1163 | |
| | cosine_precision@10 | 0.0677 | |
| | cosine_recall@1 | 0.2708 | |
| | cosine_recall@3 | 0.5046 | |
| | cosine_recall@5 | 0.5815 | |
| | cosine_recall@10 | 0.6769 | |
| | **cosine_ndcg@10** | **0.4684** | |
| | cosine_mrr@10 | 0.4022 | |
| | cosine_map@100 | 0.4139 | |
| |
| <!-- |
| ## Bias, Risks and Limitations |
| |
| *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
| --> |
| |
| <!-- |
| ### Recommendations |
| |
| *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
| --> |
| |
| ## Training Details |
| |
| ### Training Dataset |
| |
| #### Unnamed Dataset |
| |
| * Size: 1,548 training samples |
| * Columns: <code>sentence_0</code>, <code>sentence_1</code>, <code>sentence_2</code>, <code>sentence_3</code>, and <code>sentence_4</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | |
| |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------| |
| | type | string | string | string | string | string | |
| | details | <ul><li>min: 7 tokens</li><li>mean: 13.67 tokens</li><li>max: 27 tokens</li></ul> | <ul><li>min: 129 tokens</li><li>mean: 226.59 tokens</li><li>max: 511 tokens</li></ul> | <ul><li>min: 129 tokens</li><li>mean: 218.17 tokens</li><li>max: 511 tokens</li></ul> | <ul><li>min: 129 tokens</li><li>mean: 216.09 tokens</li><li>max: 511 tokens</li></ul> | <ul><li>min: 129 tokens</li><li>mean: 218.05 tokens</li><li>max: 511 tokens</li></ul> | |
| * Samples: |
| | sentence_0 | sentence_1 | sentence_2 | sentence_3 | sentence_4 | |
| |:-----------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| | <code>Internal communications regarding upcoming tequila industry regulations</code> | <code>Subject: Upcoming Regulatory Comment Period: Tequila Industry Associations<br>Date: 2025-12-08T07:41:00<br>From: Sarah Mitchell<br>Participants: Thomas Bradford; Patricia Reeves<br><br>Body:<br>Dear Colleagues,<br><br>I wanted to bring to your attention the forthcoming public comment period for the draft regulations being proposed for tequila industry associations. This is a critical opportunity for industry stakeholders to present their perspectives and ensure that the final framework reflects operational realities and best practices. I encourage all relevant departments to review the proposal closely and prepare any formal comments or suggestions to submit before the deadline. Please coordinate internally to consolidate feedback and let me know if you require any support or clarification regarding the submission process.<br><br>Thank you and best regards,<br><br>Sarah Mitchell<br>General Counsel</code> | <code>Subject: Request for Approval: Maintenance Budget Variance – Q2<br>Date: 2026-01-26T10:51:00<br>From: David Chen<br>Participants: Maria Santos<br><br>Body:<br>Hi Maria,<br><br>Following a detailed review of our Q2 maintenance expenditures, the data shows that actual costs exceeded the initial budget by 18%. The variance stems primarily from unanticipated repairs to the distillation equipment and supply chain delays that increased third-party maintenance fees. From a financial perspective, I require a full breakdown of each line item, accompanying invoices, and a variance analysis compared to the original budget. Vague descriptors such as 'misc. repairs' are not sufficient for approval—please provide supporting documentation and justifications for each overage. Once I have this detail, I will evaluate the request accordingly.<br><br>Thanks,<br>David</code> | <code>Subject: Request for Travel Budget Exception: Supplier Audit in Guadalajara<br>Date: 2025-10-13T18:03:00<br>From: Miguel Torres<br>Participants: Maria Santos<br><br>Body:<br>Hi Maria,<br><br>I am writing to request a travel budget exception for our upcoming supplier audit in Guadalajara. The current accounts do not cover the additional airfare and lodging costs, which are $1,830 MXN and $3,200 MXN respectively, as vendor rates have increased by 15% since last quarter. The data shows this audit is required to maintain ISO compliance and mitigate supply chain risks. Please advise what documentation you require to process this exception. I have attached initial quotes and the audit schedule for your review.<br><br>Thank you for your prompt attention to this matter.<br><br>Best regards,<br>Miguel<br><br>--<br>Miguel Torres<br>Procurement Manager<br>ASI Mexico</code> | <code>Subject: Campaña en redes sociales: control del mensaje y estrategia proactiva<br>Date: 2025-11-10T08:50:00<br>From: Daniel Wright<br>Participants: Tom Bradford; Patricia Reeves<br><br>Body:<br>Estimados,<br><br>Quisiera poner sobre la mesa la importancia de definir una narrativa clara y cohesiva antes de lanzar cualquier contenido de nuestra próxima campaña en redes sociales. Me preocupa cómo pueden interpretarse ciertos mensajes externos, especialmente en el actual clima mediático. Debemos asegurarnos de que cada publicación refuerce la reputación ética y la transparencia de Agave Spirits International. Sugiero que revisemos juntos el calendario de publicaciones y los mensajes clave antes de su difusión para anticipar posibles titulares en la prensa y evitar interpretaciones adversas.<br><br>Quedo atento a sus comentarios para coordinar una reunión esta semana.<br><br>Saludos cordiales,<br>Daniel Wright<br><br>--<br>Daniel Wright<br>Director, Corporate Communications<br>Agave Spirits International</code> | |
| | <code>How did managers justify onboarding shell or lightly documented consulting firms?</code> | <code>Subject: Re: New Vendor Setup - Consultoria Verde de Jalisco (Urgent)<br>Date: 2025-12-22T09:26:00<br>From: Carlos Delgado<br>Participants: Michelle Santos; Ricardo Mendez<br><br>Body:<br>Hola Michelle,<br><br>Rick is right—this is a top priority for our Mexico operations and we need Consultoria Verde de Jalisco operational immediately. I’ve personally reviewed the engagement: it’s just straightforward EHS consulting, nothing more. Please process their setup under the standard track and we’ll deliver any remaining documentation early next week. En México, las relaciones importan y así se mueve el negocio—if we wait, we risk operational disruption. I appreciate your attention to compliance, but sometimes local realities require us to act with agility. Let me know if you need anything else from my side, but for now, I ask you to move forward as requested. Gracias por tu apoyo y comprensión.<br><br>Saludos,<br>Carlos</code> | <code>Subject: PRIVILEGED AND CONFIDENTIAL - ATTORNEY-CLIENT COMMUNICATION - Mexico Operations Concern<br>Date: 2025-09-17T08:05:00<br>From: Jennifer Walsh<br>Participants: Sarah Mitchell<br><br>Body:<br>Hi Sarah,<br><br>For the record, I am forwarding a summary of a serious anonymous complaint received via our ethics hotline regarding our Mexico operations. The report alleges that the EHS Manager (Ricardo Mendez) hosted multiple dinners with a local government official, provided gifts, and facilitated payments through fake invoices. There are further red flags: the Country Manager (Carlos Delgado) is alleged to have been aware, and there are mentions of organized crime involvement. These allegations, if substantiated, raise significant FCPA exposure.<br><br>I strongly recommend we immediately engage outside counsel with FCPA expertise to lead an independent investigation. We must document everything, preserve all potentially relevant documents and communications, and strictly limit knowledge of this matter to essential ...</code> | <code>Subject: Campaña en redes sociales: control del mensaje y estrategia proactiva<br>Date: 2025-11-10T08:50:00<br>From: Daniel Wright<br>Participants: Tom Bradford; Patricia Reeves<br><br>Body:<br>Estimados,<br><br>Quisiera poner sobre la mesa la importancia de definir una narrativa clara y cohesiva antes de lanzar cualquier contenido de nuestra próxima campaña en redes sociales. Me preocupa cómo pueden interpretarse ciertos mensajes externos, especialmente en el actual clima mediático. Debemos asegurarnos de que cada publicación refuerce la reputación ética y la transparencia de Agave Spirits International. Sugiero que revisemos juntos el calendario de publicaciones y los mensajes clave antes de su difusión para anticipar posibles titulares en la prensa y evitar interpretaciones adversas.<br><br>Quedo atento a sus comentarios para coordinar una reunión esta semana.<br><br>Saludos cordiales,<br>Daniel Wright<br><br>--<br>Daniel Wright<br>Director, Corporate Communications<br>Agave Spirits International</code> | <code>Subject: Upcoming Regulatory Comment Period: Tequila Industry Associations<br>Date: 2025-12-08T07:41:00<br>From: Sarah Mitchell<br>Participants: Thomas Bradford; Patricia Reeves<br><br>Body:<br>Dear Colleagues,<br><br>I wanted to bring to your attention the forthcoming public comment period for the draft regulations being proposed for tequila industry associations. This is a critical opportunity for industry stakeholders to present their perspectives and ensure that the final framework reflects operational realities and best practices. I encourage all relevant departments to review the proposal closely and prepare any formal comments or suggestions to submit before the deadline. Please coordinate internally to consolidate feedback and let me know if you require any support or clarification regarding the submission process.<br><br>Thank you and best regards,<br><br>Sarah Mitchell<br>General Counsel</code> | |
| | <code>What internal controls are in place for reviewing beneficiary account changes before processing payments?</code> | <code>Subject: Re: Urgent: Discrepancy in Beneficiary Account Information for Broker Payment<br>Date: 2025-10-22T20:38:00<br>From: Maria Santos<br>Participants: James Cooper<br><br>Body:<br>Hi James,<br><br>Thank you for catching this and bringing it to my attention. I've already reached out to the broker requesting the latest official documentation confirming their beneficiary account details. As soon as I receive the required paperwork, I will forward it to you for review. If you have a preferred template or checklist you'd like the broker to use, please send it along, and I'll make sure it's followed to the letter. My priority is to ensure compliance and avoid any delays in the payment process.<br><br>Appreciate your vigilance on this,<br>Maria</code> | <code>Subject: Trade Association Political Activity Disclosure and Government Engagement Compliance<br>Date: 2025-10-13T08:19:00<br>From: Amanda Foster<br>Participants: Sarah Mitchell<br><br>Body:<br>Hi Sarah,<br><br>I wanted to touch base regarding our upcoming trade association political activity disclosures and ensure we remain fully compliant with both US (e.g., LDA, FARA) and Mexican (Transparencia y Acceso a la Información Pública) regulations. As you know, all ASI government interactions are run through our pre-clearance process, including detailed documentation of business purposes and regulatory filings. Routine reporting—such as our semi-annual LDA filings in the US and quarterly submissions to Mexican authorities—reflects only legitimate, transparent engagement, all pre-approved in writing and logged for audit purposes. This diligence is especially critical given recent events involving unofficial channels.<br><br>Let me know if you need any further documentation from Government Relations for the upcoming comp...</code> | <code>Subject: RE: Request for Departmental Budget Inputs – FY2025 Planning<br>Date: 2025-08-12T15:38:00<br>From: Carlos Delgado<br>Participants: Maria Santos<br><br>Body:<br>Dear Maria,<br><br>Thank you for your detailed instructions on the budget process. Attached you will find our department’s completed budget template for FY2025, with all supporting documentation as requested. We have taken special care to ensure that each line item is accompanied by clear justifications. As siempre, I want to highlight that in Mexico, relationships matter—a veces eso means a small dinner with community leaders or a modest contribution to local fiestas (you'll see these reflected under 'Community & Stakeholder Engagement'). This is how business is done here; these are key to maintaining our strong ties and smooth operational flow.<br><br>Please note, we have pending invoices for environmental consulting that will be forwarded next week. If there are any doubts or further documentation needed, let me know and our team will resolve the...</code> | <code>Subject: Revisión de posicionamiento de marca y objetivos de Q4<br>Date: 2025-10-13T15:16:00<br>From: Kevin O'Brien<br>Participants: Thomas Tom Bradford; Sarah Mitchell; Patricia Reeves<br><br>Body:<br>Estimado equipo ejecutivo,<br><br>Quisiera destacar que, mientras nos acercamos al cierre de Q4, hemos observado cambios importantes en el posicionamiento de nuestra marca dentro del mercado norteamericano. Nuestros números preliminares de ventas indican una mejora notable en la cuota de mercado, especialmente en canales premium y distribución independiente. Sin embargo, la competencia está reaccionando agresivamente, lo que implica un ajuste ágil de nuestras estrategias de precio y visibilidad en el punto de venta. Si bien entiendo la importancia de los procesos de compliance, me preocupa que algunas revisiones internas estén ralentizando cierres claves justo en temporada alta. Sugiero que exploremos vías para agilizar la aprobación de nuevos contratos sin perder el control ni la transparencia requerida.<br><br>Agra...</code> | |
| * Loss: <code>__main__.DPOLoss</code> |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `per_device_train_batch_size`: 6 |
| - `per_device_eval_batch_size`: 6 |
| - `multi_dataset_batch_sampler`: round_robin |
| |
| #### All Hyperparameters |
| <details><summary>Click to expand</summary> |
| |
| - `do_predict`: False |
| - `eval_strategy`: no |
| - `prediction_loss_only`: True |
| - `per_device_train_batch_size`: 6 |
| - `per_device_eval_batch_size`: 6 |
| - `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`: {} |
| |
| </details> |
| |
| ### Training Logs |
| | Epoch | Step | val_full_corpus_cosine_ndcg@10 | |
| |:-----:|:----:|:------------------------------:| |
| | 1.0 | 258 | 0.4684 | |
| |
| |
| ### 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 |
| ```bibtex |
| @inproceedings{reimers-2019-sentence-bert, |
| title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
| author = "Reimers, Nils and Gurevych, Iryna", |
| booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
| month = "11", |
| year = "2019", |
| publisher = "Association for Computational Linguistics", |
| url = "https://arxiv.org/abs/1908.10084", |
| } |
| ``` |
| |
| <!-- |
| ## Glossary |
| |
| *Clearly define terms in order to be accessible across audiences.* |
| --> |
| |
| <!-- |
| ## Model Card Authors |
| |
| *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
| --> |
| |
| <!-- |
| ## Model Card Contact |
| |
| *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
| --> |
