Daxtra's picture
Add new SentenceTransformer model
f434d64 verified
metadata
base_model: mixedbread-ai/mxbai-embed-large-v1
library_name: sentence-transformers
metrics:
  - cosine_accuracy@10
  - cosine_precision@10
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@10
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:149352
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      - Assoc Sample Coordinator position for entry-level candidates with a high
      school diploma or equivalent and related experience (0-1 years).

      - Responsibilities include inventory tracking, administrative support, and
      training on SOPs, regulatory guidelines, and storage requirements.

      - Support laboratory operations and respond to environmental unit alarms.

      - Requires proficiency in Microsoft Office, time management, and detailed
      documentation skills.

      - Must have good written and oral communication skills, team orientation,
      and HR collaboration experience.
    sentences:
      - >-
        - Experienced construction contractor with diverse skills in painting,
        plumbing, and foundation work.

        - Currently serving as a subcontractor, handling tasks like building
        foundations, framing, and tile work.

        - Excellent customer service and scheduling abilities; proficient in
        plasterboard, drywall, and flooring installation.

        - Proficient in historic restoration and home rehabilitation.

        - Skilled in money and time management, as well as operating forklifts
        and handling deliveries.

        - Educational background includes a High School Diploma, with experience
        in electrical work and field services.

        - Strong communication and organizational skills.
      - >-
        - Freelance media professional with extensive experience in production,
        directing, editing, and writing for various media projects.

        - Currently overseeing the full project lifecycle, ensuring cohesive
        visual storytelling, from pre-production to post-production.

        - Capable of negotiating budgets and managing crews for corporate and
        film productions, ensuring successful execution.

        - Expertise in creating content for websites, social media, and
        marketing initiatives.

        - Holds Masters Degree in Film and Bachelors Degree in Arts
        Communications.

        - Proficient with Adobe After Effects, Photoshop, Premier, and Avid
        Media Composer.
      - >-
        - Experienced accounting professional with a Bachelor of Commerce and
        strong financial management skills, currently working as a Parks Canada
        Accounting Assistant.

        - Skilled in financial record-keeping, accounting procedures, and using
        accounting software for report generation.

        - Assisted in budget preparation and monitoring, ensuring compliance
        with guidelines.

        - Hands-on experience in insurance underwriting, managing policy
        renewals, and streamlining operations.

        - Proficient in communication, interpersonal skills, and working under
        pressure.

        - Holds Bachelor of Commerce degree and has experience as a Credit Card
        Specialist and Service Representative.

        - Strong experience in customer service, arranging appointments, and
        brokerage.
  - source_sentence: >-
      - Construction Workers - Roofing Supply Loader, available for all levels
      and positions including framers, carpenters, laborers, insulation workers,
      and finish carpenters.

      - Key responsibilities include loading and unloading roofing supplies,
      following instructions, and performing tasks both indoors and outdoors.

      - Essential qualifications: Can read tape measure for most jobs, can lift
      up to 50 lbs, and is willing to work in various environments.

      - No specific years of experience required; open to all skill levels.
    sentences:
      - >-
        - Operational expert with over 12 years in leading manufacturing and
        operation facilities to meet goals, focused on quality, cost reduction,
        and team development.

        - Operations Manager at REYNOLDS, implementing continuous improvement
        and lean manufacturing for efficiency, reducing quality defects and
        injuries, and enhancing KPIs.

        - Production Manager at REYNOLDS, increasing production by 25% and
        reducing maintenance costs by 20% through process improvements and
        maintenance optimization.

        - Advanced degrees in Chemical Engineering and a Bachelor's in Chemical
        Engineering, with AIB and ISO certifications.

        - Proficient in SAP, SAP IS, and SAP-netweaver BUSINESS, with experience
        in cost reduction, quality control, and training programs.
      - >-
        - Media graduate with expertise in digital media design, content
        creation, and digital marketing.

        - Currently an Account Executive at a growing startup, enhancing
        audience engagement and contributing to KOL specialization.

        - Previously worked as a Content Creator at Lemon8, managing paid
        content and audience engagement.

        - Experience as Supervisor at Black Sheep Coffee, organizing tasks and
        writing reviews.

        - Started a creative agency and led brand activation projects, with
        strong skills in Microsoft Excel and HOSPITALITY EXPERIENCE.

        - Holds a Bachelor of Arts in Mass Communication and has worked in
        hospitality and start-up settings.

        - Proficient in Microsoft PowerPoint, Excel, Instagram, and event
        planning.
      - >-
        - Agricultural professional with experience in farm hand roles,
        including harvesting and equipment operation.

        - Seasonal ranch hand at C.R.I. Feeders, Guymon, Oklahoma, 2021,
        handling tasks like fencing, herding, haying, and equipment maintenance.

        - Skills in operating large machinery and maintaining agricultural
        equipment.

        - Holds a Bachelor of Science degree in English and a Diploma in Feed
        truck driving.

        - Volunteer experience as a Firefighter, demonstrating teamwork and
        emergency response capabilities.
  - source_sentence: >-
      - Full Stack React Developer (Remote, A-26867) for a new application using
      React, Node.js, and Python, with a focus on front-end and back-end
      development.

      - Requires 2+ years of experience; 4+ years preferred.

      - Essential skills: React, Typescript, Node.js, Python, DB management, and
      basic API flow.

      - Must work closely with a full-time designer and use an internal design
      system.

      - Experience with Jira and agile projects is a plus.

      - Agile team environment with daily collaboration.
    sentences:
      - >-
        - Experienced registered nurse with expertise in care coordination and
        relationship coaching.

        - Currently practicing as a staff RN with a Bachelor of Science in
        Nursing, specializing in care coordination.

        - Proficient in providing comprehensive care and support to patients in
        a clinical and coaching role.

        - Holds an Associates degree in Liberal Arts and has volunteer
        experience in healthcare.

        - Fluent in English and Tagalog.
      - >-
        - Recent University graduate with a Criminology degree, currently
        pursuing a Juris Doctor at the University of Southampton.

        - Previous roles include Floor Staff at JD Sports, ensuring high
        standards in retail and customer service.

        - Strong background in business, computing, and accounting from various
        educational and work experiences.

        - Proficient in customer service, issue resolution, and standardizing
        products.

        - Experience in diverse roles demonstrating balanced experience across
        multiple industries.

        - Skills include effective communication, teamwork, and problem-solving.
      - >-
        - Java Developer with over 10 years of experience in J2EE and SDLC
        methodologies, including Agile (SCRUM), TDD, and Waterfall.

        - Specialized in Java/J2EE technologies like Hibernate, Servlets, JSP,
        AJAX, and JavaBeans.

        - Proficient in front-end technologies such as HTML, CSS, JavaScript,
        jQuery, and Angular.js.

        - Experienced in cloud technologies like Azure, Docker, AWS Lambda, and
        Node.js.

        - Skilled in database technologies including MySQL, Oracle, MongoDB, and
        Cassandra.

        - Experience with Java 8 and 11 features such as Lambda expressions,
        Streams, and Optional Interfaces.

        - Proficient in Spring Framework and Spring Boot, and has worked with
        Golang, Node.js, and Angular.js.
  - source_sentence: >-
      - Warehouse Front Counter Associate with occasional order pulling and
      tagging, assisting in the warehouse, and handling phone communications.

      - Key responsibilities include loading and unloading trucks, maintaining
      the front desk, greeting and assisting visitors, and using Quickbooks and
      CAD.

      - Requires 10% warehouse assistance, willingness to learn, and comfort
      performing diverse tasks.

      - High attention to detail and previous clerical and customer service
      experience necessary.

      - Attendance is critical as part of a small team; training will be
      provided for forklift operation.
    sentences:
      - >-
        - Sales Engineer with experience as an Account Executive and Associate
        Sales Engineer in the Greater Seattle Area, specializing in sales and
        industry.

        - Holds a Bachelor of Science in Electrical Engineering and holds
        proficiency in English, Russian, Autocad, and C++.

        - Skilled in Matlab and with strong sales, industry-specific knowledge.

        - Experience includes managing accounts, developing sales strategies,
        and leading sales teams.
      - >-
        - Expert in Material Handling, Customer Service, and Document Control,
        with experience in forklift operation and inventory management.

        - Currently a Meterial Handler, responsible for staging, receiving, and
        relocating materials and shelves.

        - Previous role as a Document Control Specialist, managing document
        control and customer service for Pacific Building Services.

        - Skills include forklift operation, professional customer service
        certification, phone handling, order picking, and communication.

        - Strong time management, warehouse experience, and data entry
        capabilities.

        - Educated in Professional Customer Service and Enterprise Resource
        Planning.

        - Proficient in using Pallet Trucks, Pick and Pack techniques, and
        warehouse management systems.
      - >-
        - Engineering professional with a strong foundation in sustainability
        and manufacturing, known for problem-solving and STEM expertise.

        - Currently a Chef de Rang in high-end hospitality, excelling in
        communication, teamwork, and problem-solving.

        - Managed multiple tasks with exceptional organizational and time
        management skills, ensuring accurate and precise food and beverage
        delivery.

        - Collaborated effectively to optimize service efficiency, handling
        events and daily operations.

        - Troubleshooted and maintained machinery using engineering knowledge,
        contributing to team dynamics.

        - Holds a Post-Graduate Diploma in Environment and Sustainable Energy,
        with a Bachelor of Science in Mechanical Engineering.

        - Skills: Teamwork, Client Services, Communication, Problem-solving,
        Time Management, Customer Satisfaction, Eye for Detail, Service
        Delivery, Adaptability.

        - Experience in various roles, including agency work, with a
        results-driven approach to problem-solving and innovation.
  - source_sentence: >-
      - Content Writer position for crafting engaging long-form content across
      various topics, requiring a 2:1 Degree in English History or a similar
      field.

      - Create captivating articles, features, and content that is informative
      and resonates with the target audience, utilizing research skills to
      ensure accuracy.

      - Manage multiple projects with strong organizational and time-management
      skills, ensuring clarity and accuracy in writing.

      - Excellent proofreading and editing skills to produce flawless content,
      with a diplomatic approach to client relationships and communication.

      - Collaborate with clients to transform visions into engaging content and
      conduct interviews to uncover compelling stories.

      - Must have a keen eye for detail and a passion for long-form storytelling
      and content orchestration.
    sentences:
      - >-
        - Instructional Designer and Senior Project Manager with expertise in
        developing eLearning experiences and conducting needs analysis for
        global clients.

        - Expertise in writing storyboards and scripts, creating engaging
        instructional graphics and animations, and developing scenario-based
        eLearning content.

        - Proficient in utilizing trends and best practices in learning
        technologies, liaising between stakeholders, and managing eLearning
        projects to completion.

        - Holds a Master of Arts in Applied Linguistics and Bachelor of Arts in
        History, with a Certificate in Digital Media.

        - Skilled in Adobe Captivate, Figma, Microsoft Excel, PowerPoint, and
        Word.

        - Experience includes roles as a Teacher, Instructional Designer, and
        eLearning Developer.
      - >-
        - Award-nominated journalist with over 12 years of experience in
        journalism, content writing, and SEO.

        - Currently a freelance journalist, specializing in various sectors
        including health, finance, and technology.

        - Freelance for publications like The Independent, CNN, and SELF, with
        notable success in SEO and content creation.

        - Strong skills in SEO, content writing, and copywriting, with a track
        record of high engagement and click-through rates.

        - Holds a Masters of Arts in Dramaturgy and Writing, and a BA in Media
        Journalism and Communications.

        - Proficient in WordPress, Umbraco, and Shopify; experienced in social
        media, content strategy, and email marketing.
      - >-
        - Junior Systems Administrator with a Bachelor of Science in Computer
        Science and Information Systems.

        - Conducted risk assessments, resolved vulnerabilities, and maintained
        IT systems using tools like Entra ID, Intune, and Azure AD.

        - Evaluated and maintained enterprise applications in PowerShell,
        Python, and C++, utilizing Azure DevOps for management.

        - Developed applications for business workflow and maintained
        documentation of IT processes and applications.

        - Proficient in cybersecurity frameworks and practices, including risk
        assessment and Azure DevOps project management.
model-index:
  - name: SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: vac res matcher
          type: vac-res-matcher
        metrics:
          - type: cosine_accuracy@10
            value: 0.3938953488372093
            name: Cosine Accuracy@10
          - type: cosine_precision@10
            value: 0.07994186046511628
            name: Cosine Precision@10
          - type: cosine_recall@10
            value: 0.12904738156953352
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.13193212924546854
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2091500553709855
            name: Cosine Mrr@10
          - type: cosine_map@10
            value: 0.08077975021655233
            name: Cosine Map@10

SentenceTransformer based on mixedbread-ai/mxbai-embed-large-v1

This is a sentence-transformers model finetuned from mixedbread-ai/mxbai-embed-large-v1. 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: mixedbread-ai/mxbai-embed-large-v1
  • Maximum Sequence Length: 128 tokens
  • Output Dimensionality: 1024 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

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("Daxtra/sbert-summaries-mxbai-24-batch")
# Run inference
sentences = [
    '- Content Writer position for crafting engaging long-form content across various topics, requiring a 2:1 Degree in English History or a similar field.\n- Create captivating articles, features, and content that is informative and resonates with the target audience, utilizing research skills to ensure accuracy.\n- Manage multiple projects with strong organizational and time-management skills, ensuring clarity and accuracy in writing.\n- Excellent proofreading and editing skills to produce flawless content, with a diplomatic approach to client relationships and communication.\n- Collaborate with clients to transform visions into engaging content and conduct interviews to uncover compelling stories.\n- Must have a keen eye for detail and a passion for long-form storytelling and content orchestration.',
    '- Award-nominated journalist with over 12 years of experience in journalism, content writing, and SEO.\n- Currently a freelance journalist, specializing in various sectors including health, finance, and technology.\n- Freelance for publications like The Independent, CNN, and SELF, with notable success in SEO and content creation.\n- Strong skills in SEO, content writing, and copywriting, with a track record of high engagement and click-through rates.\n- Holds a Masters of Arts in Dramaturgy and Writing, and a BA in Media Journalism and Communications.\n- Proficient in WordPress, Umbraco, and Shopify; experienced in social media, content strategy, and email marketing.',
    '- Instructional Designer and Senior Project Manager with expertise in developing eLearning experiences and conducting needs analysis for global clients.\n- Expertise in writing storyboards and scripts, creating engaging instructional graphics and animations, and developing scenario-based eLearning content.\n- Proficient in utilizing trends and best practices in learning technologies, liaising between stakeholders, and managing eLearning projects to completion.\n- Holds a Master of Arts in Applied Linguistics and Bachelor of Arts in History, with a Certificate in Digital Media.\n- Skilled in Adobe Captivate, Figma, Microsoft Excel, PowerPoint, and Word.\n- Experience includes roles as a Teacher, Instructional Designer, and eLearning Developer.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Metric Value
cosine_accuracy@10 0.3939
cosine_precision@10 0.0799
cosine_recall@10 0.129
cosine_ndcg@10 0.1319
cosine_mrr@10 0.2092
cosine_map@10 0.0808

Training Details

Training Dataset

Unnamed Dataset

  • Size: 149,352 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: 57 tokens
    • mean: 116.11 tokens
    • max: 128 tokens
    • min: 52 tokens
    • mean: 118.95 tokens
    • max: 128 tokens
  • Samples:
    sentence_0 sentence_1
    - Staff Accountant position seeking individuals with 2-3 years of experience in AR and AP areas, ideally with a Bachelor's degree in accounting, finance, or related field, or equivalent work experience.
    - Responsibilities include processing e-commerce payments, handling payables and receivables, preparing financial statements, supporting tax reports, and managing close processes.
    - Requires knowledge of basic accounting principles, experience with general ledger functions, and proficiency in Microsoft Office, particularly Excel.
    - Strong communication, problem-solving, and organizational skills are essential.
    - Attributes include a high level of integrity, ability to multitask, and strong time management.
    - Regular attendance and adherence to health, safety, and environmental policies are required.
    - Experienced Account Payable Specialist with 5 years in vendor management, invoice processing, and reconciliation.
    - Processed 120-150 invoices daily, handling 3 V-way matching, and reconciling over 100,000 accounts.
    - Skilled in using Oracle, Excel VLOOKUP, and SAP Concur for reconciliation and disbursements.
    - Master’s in Accountancy; proficient in Microsoft Excel, SharePoint, and SAP applications.
    - Excellent interpersonal, analytical, and organizational skills.
    - Detailed work in expense invoicing, payments, and communication with vendors.
    - Controls Assistant Project Manager position requires 3+ years of experience, stable work history, and a bachelor's degree in mechanical or electrical engineering.
    - Candidates must be familiar with AutoCAD and Visio, and have experience with BACnet and DDC controls.
    - Knowledge of Siemens, Johnson Controls, and similar control systems is essential.
    - EIT or PE license is preferred but not required.
    - Systems Integrator with 3 years of experience in Greater Seattle Area, specialized in project integration and sales.
    - Currently a Systems Integrator at GE Cimplicity, responsible for sales and project integration.
    - Former Systems Integrator at Siemens Tia Portal; proficient in Siemens Hardware.
    - Experience in GE Proficy and Albireo Energy roles, focusing on mechanical engineering.
    - Skills: Project Integrator, Bachelor's degree in Mechanical Engineering, bilingual in English and Spanish.
    - Strong background in customer engagement and system sales.
    - Senior HVAC Service Technician, requiring 5+ years of experience in commercial HVAC service and repair.
    - Key responsibilities include diagnosing, repairing, and maintaining large commercial HVAC systems, interpreting blueprints and data, and providing customer education.
    - Must possess an EPA Universal Certification and extensive knowledge of commercial HVAC systems.
    - Requires proficiency in interpreting technical data and blueprints, and a local work history.
    - Strong communication and customer service skills essential.
    - Ideal for professionals in San Diego, CA; must be passionate about HVAC craft and committed to service excellence.
    - Mechanical Technician with extensive experience in startup, commissioning, and mechanical trades.
    - Currently employed at Countywide Mechanical Systems, Inc. in San Diego County, California.
    - Skilled in mechanical systems commissioning and troubleshooting.
    - Strong problem-solving and attention to detail in complex mechanical environments.
    - Proficient in system design, installation, and maintenance of mechanical systems.
    - Holds certifications in mechanical technology and engineering.
    - Experienced in project management and collaborative teamwork.
    - Educated in mechanical engineering or a related field.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 24
  • per_device_eval_batch_size: 24
  • num_train_epochs: 1
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 24
  • per_device_eval_batch_size: 24
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • 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: 1
  • max_steps: -1
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: {}
  • warmup_ratio: 0.0
  • warmup_steps: 0
  • log_level: passive
  • log_level_replica: warning
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • save_safetensors: True
  • save_on_each_node: False
  • save_only_model: False
  • restore_callback_states_from_checkpoint: False
  • no_cuda: False
  • use_cpu: False
  • use_mps_device: False
  • seed: 42
  • data_seed: None
  • jit_mode_eval: False
  • use_ipex: False
  • bf16: False
  • fp16: False
  • fp16_opt_level: O1
  • half_precision_backend: auto
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • local_rank: 0
  • ddp_backend: None
  • tpu_num_cores: None
  • tpu_metrics_debug: False
  • debug: []
  • dataloader_drop_last: False
  • dataloader_num_workers: 0
  • dataloader_prefetch_factor: None
  • past_index: -1
  • disable_tqdm: False
  • remove_unused_columns: True
  • label_names: None
  • load_best_model_at_end: False
  • ignore_data_skip: False
  • fsdp: []
  • fsdp_min_num_params: 0
  • fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
  • deepspeed: None
  • label_smoothing_factor: 0.0
  • optim: adamw_torch
  • optim_args: None
  • adafactor: False
  • group_by_length: False
  • length_column_name: length
  • ddp_find_unused_parameters: None
  • ddp_bucket_cap_mb: None
  • ddp_broadcast_buffers: False
  • dataloader_pin_memory: True
  • dataloader_persistent_workers: False
  • skip_memory_metrics: True
  • use_legacy_prediction_loop: False
  • push_to_hub: False
  • resume_from_checkpoint: None
  • hub_model_id: None
  • hub_strategy: every_save
  • hub_private_repo: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • eval_do_concat_batches: True
  • fp16_backend: auto
  • push_to_hub_model_id: None
  • push_to_hub_organization: None
  • mp_parameters:
  • auto_find_batch_size: False
  • full_determinism: False
  • torchdynamo: None
  • ray_scope: last
  • ddp_timeout: 1800
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • dispatch_batches: None
  • split_batches: None
  • include_tokens_per_second: False
  • include_num_input_tokens_seen: False
  • neftune_noise_alpha: None
  • optim_target_modules: None
  • batch_eval_metrics: False
  • eval_on_start: False
  • eval_use_gather_object: False
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step Training Loss vac-res-matcher_cosine_map@10
0.0803 500 1.2875 -
0.1000 622 - 0.0833
0.1607 1000 1.1274 -
0.1999 1244 - 0.0822
0.2410 1500 1.0646 -
0.2999 1866 - 0.0793
0.3214 2000 0.9926 -
0.3998 2488 - 0.0773
0.4017 2500 0.9651 -
0.4821 3000 0.9499 -
0.4998 3110 - 0.0798
0.5624 3500 0.9098 -
0.5997 3732 - 0.0793
0.6428 4000 0.8948 -
0.6997 4354 - 0.0831
0.7231 4500 0.8962 -
0.7996 4976 - 0.0809
0.8035 5000 0.8677 -
0.8838 5500 0.8696 -
0.8996 5598 - 0.0816
0.9642 6000 0.8718 -
0.9995 6220 - 0.0808
1.0 6223 - 0.0808

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.2.1
  • Transformers: 4.44.2
  • PyTorch: 2.4.1+cu121
  • Accelerate: 0.34.2
  • Datasets: 3.0.1
  • Tokenizers: 0.19.1

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}
}