README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:150
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
widget:
  - source_sentence: What services does Techchefz Digital offer for AI adoption?
    sentences:
      - >-
        We are a New breed of innovative digital transformation agency,
        redefining storytelling for an always-on world.

        With roots dating back to 2017, we started as a pocket size team of
        enthusiasts with a goal of helping traditional businesses transform and
        create dynamic, digital cultures through disruptive strategies and agile
        deployment of innovative solutions.
      - >-
        At Techchefz Digital, we specialize in guiding companies through the
        complexities of adopting and integrating Artificial Intelligence and
        Machine Learning technologies. Our consultancy services are designed to
        enhance your operational efficiency and decision-making capabilities
        across all sectors. With a global network of AI/ML experts and a
        commitment to excellence, we are your partners in transforming
        innovative possibilities into real-world
        achievements.                                                                                                                                            
         DATA INTELLIGENCE PLATFORMS we specialize in
        TensorFlow

        Databricks

        Tableau

        Pytorch

        OpenAI

        Pinecone"
      - >-
        How can we get started with your DevOps solutions?

        Getting started is easy. Contact us through our website. We'll schedule
        a consultation to discuss your needs, evaluate your current
        infrastructure, and propose a customized DevOps solution designed to
        achieve your goals.
  - source_sentence: Hav you made any services for schools and students?
    sentences:
      - >-
        How do we do Custom Development ?

        We follow below process to develop custom web or mobile Application on
        Agile Methodology, breaking requirements in pieces and developing and
        shipping them with considering utmost quality:

        Requirements Analysis

        We begin by understanding the client's needs and objectives for the
        website. Identify key features, functionality, and any specific design
        preferences.


        Project Planning

        Then create a detailed project plan outlining the scope, timeline, and
        milestones. Define the technology stack and development tools suitable
        for the project.


        User Experience Design

        Then comes the stage of Developing wireframes or prototypes to visualize
        the website's structure and layout. We create a custom design that
        aligns with the brand identity and user experience goals.


        Development

        After getting Sign-off on Design from Client, we break the requirements
        into Sprints on Agile Methodology, and start developing them.
      - >-
        This is our Portfolio

        Introducing the world of Housing Finance& Banking Firm.

        Corporate Website with 10 regional languages in India with analytics and
        user personalization and Dashboard for Regional Managers, Sales Agents,
        etc. to manage the Builder Requests, approve/deny Properties, manage
        visits and appointments, manage leads, etc.



        Introducing the world of Global Automotive Brand.We have implemented a
        Multi Locale Multilingual Omnichannel platform for Royal Enfield. The
        platform supports public websites, customer portals, internal portals,
        business applications for over 35+ different locations all over the
        world.


        Developed Digital Platform for Students, Guardians, Teachers, Tutors,
        with AI/ML in collaboration with Successive Technologies Inc, USA. 
        Cloud, Dev-Sec-Ops & Data Governance

        Managing cloud provisioning and modernization alongside automated
        infrastructure, event-driven microservices, containerization, DevOps,
        cybersecurity, and 24x7 monitoring support ensures efficient, secure,
        and responsive IT operations.
      - >-
        SERVICES WE PROVIDE

        Flexible engagement models tailored to your needs

        We specialize in comprehensive website audits that provide valuable
        insights and recommendations to enhance your online presence.

        Digital Strategy & Consulting

        Creating digital roadmap that transform your digital enterprise and
        produce a return on investment, basis our discovery framework,
        brainstorming sessions & current state analysis.


        Platform Selection

        Helping you select the optimal digital experience, commerce, cloud and
        marketing platform for your enterprise.


        Platform Builds

        Deploying next-gen scalable and agile enterprise digital platforms,
        along with multi-platform integrations.   

        Product Builds

        Help you ideate, strategize, and engineer your product with help of our
        enterprise frameworks

        Infrastructure

        Specialize in multi-cloud infrastructure helping you put forward the
        right cloud infrastructure and optimization strategy.


        Managed Services

        Operate and monitor your business-critical applications, data, and IT
        workloads, along with Application maintenance and operations.

        Team Augmentation

        Help you scale up and augment your existing team to solve your hiring
        challenges with our easy to deploy staff augmentation offerings."
  - source_sentence: How did TechChefz evolve from its early days?
    sentences:
      - >-
        Why do we need Microservices ?

        Instead of building a monolithic application where all functionalities
        are tightly integrated, microservices break down the system into modular
        and loosely coupled services.


        Scalability

        Flexibility and Agility

        Resilience and Fault Isolation

        Technology Diversity

        Continuous Delivery
      - >-
        After a transformative scuba dive in the Maldives, Mayank Maggon made a
        pivotal decision to depart from the corporate ladder in December 2016.
        Fueled by a clear vision to revolutionize the digital landscape, Mayank
        set out to leverage the best technology ingredients, crafting custom
        applications and digital ecosystems tailored to clients' specific needs,
        limitations, and budgets.


        However, this solo journey was not without its challenges. Mayank had to
        initiate the revenue engine by offering corporate trainings and
        conducting online batches for tech training across the USA. He also
        undertook small projects and subcontracted modules of larger projects
        for clients in the US, UK, and India. It was only after this initial
        groundwork that Mayank was able to hire a group of interns, whom he
        meticulously trained and groomed to prepare them for handling Enterprise
        Level Applications. This journey reflects Mayank's resilience,
        determination, and entrepreneurial spirit in building TechChefz Digital
        from the ground up.


        With a passion for innovation and a relentless drive for excellence,
        Mayank has steered TechChefz Digital through strategic partnerships,
        groundbreaking projects, and exponential growth. His leadership has been
        instrumental in shaping TechChefz Digital into a leading force in the
        digital transformation arena, inspiring a culture of innovation and
        excellence that continues to propel the company forward.
      - >-
        In what ways can machine learning optimize our operations?

        Machine learning algorithms can analyze operational data to identify
        inefficiencies, predict maintenance needs, optimize supply chains, and
        automate repetitive tasks, significantly improving operational
        efficiency and reducing costs.
  - source_sentence: What kind of data do you leverage for AI solutions?
    sentences:
      - >-
        In the Introducing the world of Global Insurance Firm, we crafted
        Effective Solutions for Complex Problems and delieverd a comprehensive
        Website Development, Production Support & Managed Services, we optimized
        customer journeys, integrate analytics, CRM, ERP, and third-party
        applications, and implement cutting-edge technologies for enhanced
        performance and efficiency

        and achievied 200% Reduction in operational time & effort managing
        content & experience, 70% Reduction in Deployment Errors and Downtime,
        2.5X Customer Engagement, Conversion & Retention
      - >-
        Our Solutions

        Strategy & Digital Transformation

        Innovate via digital transformation, modernize tech, craft product
        strategies, enhance customer experiences, optimize data analytics,
        transition to cloud for growth and efficiency


        Product Engineering & Custom Development

        Providing product development, enterprise web and mobile development,
        microservices integrations, quality engineering, and application support
        services to drive innovation and enhance operational efficiency.
      - >-
        Our AI/ML services pave the way for transformative change across
        industries, embodying a client-focused approach that integrates
        seamlessly with human-centric innovation. Our collaborative teams are
        dedicated to fostering growth, leveraging data, and harnessing the
        predictive power of artificial intelligence to forge the next wave of
        software excellence. We don't just deliver AI; we deliver the future.
  - source_sentence: What managed services does TechChefz provide ?
    sentences:
      - >2
          What we do

        Digital Strategy

        Creating digital frameworks that transform your digital enterprise and
        produce a return on investment.


        Platform Selection

        Helping you select the optimal digital experience, commerce, cloud and
        marketing platform for your enterprise.


        Platform Builds

        Deploying next-gen scalable and agile enterprise digital platforms,
        along with multi-platform integrations.


        Product Builds

        Help you ideate, strategize, and engineer your product with help of our
        enterprise frameworks 


        Team Augmentation

        Help you scale up and augment your existing team to solve your hiring
        challenges with our easy to deploy staff augmentation offerings .

        Managed Services

        Operate and monitor your business-critical applications, data, and IT
        workloads, along with Application maintenance and operations
      - >-
        What makes your DevOps solutions stand out from the competition?

        Our DevOps solutions stand out due to our personalized approach,
        extensive expertise, and commitment to innovation. We focus on
        delivering measurable results, such as reduced deployment times,
        improved system reliability, and enhanced security, ensuring you get the
        maximum benefit from our services.
      - >-
        Introducing the world of General Insurance Firm

        In this project, we implemented Digital Solution and Implementation with
        Headless Drupal as the CMS, and lightweight React JS (Next JS SSR on
        Node JS) with the following features:

        PWA & AMP based Web Pages

        Page Speed Optimization

        Reusable and scalable React JS / Next JS Templates and Components

        Headless Drupal CMS with Content & Experience management, approval
        workflows, etc for seamless collaboration between the business and
        marketing teams

        Minimalistic Buy and Renewal Journeys for various products, with API
        integrations and adherence to data compliances


        We achieved 250% Reduction in Operational Time and Effort in managing
        the Content & Experience for Buy & renew Journeys,220% Reduction in
        Customer Drops during buy and renewal journeys, 300% Reduction in bounce
        rate on policy landing and campaign pages
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: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.17333333333333334
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5466666666666666
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6933333333333334
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17333333333333334
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1822222222222222
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06933333333333333
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17333333333333334
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5466666666666666
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6933333333333334
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.43705488094312567
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3539576719576719
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3663753684578632
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.17333333333333334
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.5333333333333333
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.6266666666666667
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6933333333333334
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17333333333333334
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.17777777777777776
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.12533333333333332
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06933333333333333
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17333333333333334
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.5333333333333333
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.6266666666666667
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6933333333333334
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.43324477959330543
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.3495185185185184
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.359896266319179
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.22666666666666666
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.49333333333333335
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.56
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.68
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.22666666666666666
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.16444444444444445
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11199999999999997
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06799999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.22666666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.49333333333333335
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.56
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.68
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4383628839300849
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.36210582010582004
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.3731640827722892
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.24
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.48
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.56
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.6933333333333334
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.24
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.16
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.11199999999999997
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.06933333333333332
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.24
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.48
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.56
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.6933333333333334
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.4443870388298522
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.36651322751322746
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.37546675549059694
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.08
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.3466666666666667
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.49333333333333335
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.56
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11555555555555555
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.09866666666666667
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05599999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.3466666666666667
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.49333333333333335
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.56
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3120295466486537
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.23260846560846554
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.24731947636993173
            name: Cosine Map@100

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. It maps sentences & paragraphs to a 768-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: BAAI/bge-base-en-v1.5
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Language: en
• License: apache-2.0

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': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, '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': False, '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("Shashwat13333/bge-base-en-v1.5")
# Run inference
sentences = [
    'What managed services does TechChefz provide ?',
    '  What we do\n\nDigital Strategy\nCreating digital frameworks that transform your digital enterprise and produce a return on investment.\n\nPlatform Selection\nHelping you select the optimal digital experience, commerce, cloud and marketing platform for your enterprise.\n\nPlatform Builds\nDeploying next-gen scalable and agile enterprise digital platforms, along with multi-platform integrations.\n\nProduct Builds\nHelp you ideate, strategize, and engineer your product with help of our enterprise frameworks \n\nTeam Augmentation\nHelp you scale up and augment your existing team to solve your hiring challenges with our easy to deploy staff augmentation offerings .\nManaged Services\nOperate and monitor your business-critical applications, data, and IT workloads, along with Application maintenance and operations\n',
    'Introducing the world of General Insurance Firm\nIn this project, we implemented Digital Solution and Implementation with Headless Drupal as the CMS, and lightweight React JS (Next JS SSR on Node JS) with the following features:\nPWA & AMP based Web Pages\nPage Speed Optimization\nReusable and scalable React JS / Next JS Templates and Components\nHeadless Drupal CMS with Content & Experience management, approval workflows, etc for seamless collaboration between the business and marketing teams\nMinimalistic Buy and Renewal Journeys for various products, with API integrations and adherence to data compliances\n\nWe achieved 250% Reduction in Operational Time and Effort in managing the Content & Experience for Buy & renew Journeys,220% Reduction in Customer Drops during buy and renewal journeys, 300% Reduction in bounce rate on policy landing and campaign pages',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Evaluation

Metrics

Information Retrieval

• Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.1733	0.1733	0.2267	0.24	0.08
cosine_accuracy@3	0.5467	0.5333	0.4933	0.48	0.3467
cosine_accuracy@5	0.6	0.6267	0.56	0.56	0.4933
cosine_accuracy@10	0.6933	0.6933	0.68	0.6933	0.56
cosine_precision@1	0.1733	0.1733	0.2267	0.24	0.08
cosine_precision@3	0.1822	0.1778	0.1644	0.16	0.1156
cosine_precision@5	0.12	0.1253	0.112	0.112	0.0987
cosine_precision@10	0.0693	0.0693	0.068	0.0693	0.056
cosine_recall@1	0.1733	0.1733	0.2267	0.24	0.08
cosine_recall@3	0.5467	0.5333	0.4933	0.48	0.3467
cosine_recall@5	0.6	0.6267	0.56	0.56	0.4933
cosine_recall@10	0.6933	0.6933	0.68	0.6933	0.56
cosine_ndcg@10	0.4371	0.4332	0.4384	0.4444	0.312
cosine_mrr@10	0.354	0.3495	0.3621	0.3665	0.2326
cosine_map@100	0.3664	0.3599	0.3732	0.3755	0.2473

Training Details

Training Dataset

Unnamed Dataset

• Size: 150 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 150 samples:

  	anchor	positive
  type	string	string
  details	min: 7 tokens mean: 12.4 tokens max: 20 tokens	min: 20 tokens mean: 126.17 tokens max: 378 tokens

• Samples:

  anchor	positive
  Is it hard to move old systems to the cloud?	We offer custom software development, digital marketing strategies, and tailored solutions to drive tangible results for your business. Our expert team combines technical prowess with industry insights to propel your business forward in the digital landscape. "Engage, analyze & target your customers Digital transformation enables you to interact with customers across multiple channels, providing personalized experiences. This could include social media engagement, interactive websites, and mobile apps." "Empower your employees & partners The push for digital transformation has led many companies to embrace cloud solutions. However, the migration and integration of legacy systems into the cloud often present challenges." "Optimize & automate your operations The push for digital transformation has led many companies to embrace cloud solutions. However, the migration and integration of legacy systems into the cloud often present challenges." "Transform your products The push for digi...
  What benefits does marketing automation offer for time management?	Our MarTech capabilities Personalization Involves tailoring marketing messages and experiences to individual customers. It enhances customer engagement, loyalty, and ultimately, conversion rates. Marketing Automation Marketing automation streamlines repetitive tasks such as email marketing, lead nurturing, and social media posting. It improves efficiency, saves time, and ensures timely communication with customers. Customer Relationship Management CRM systems help manage interactions with current and potential customers. They store customer data, track interactions, and facilitate communication, improving customer retention.
  How can your recommendation engines improve our business?	How can your recommendation engines improve our business? Our recommendation engines are designed to analyze customer behavior and preferences to deliver personalized suggestions, enhancing user experience, increasing sales, and boosting customer retention.

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• gradient_accumulation_steps: 4
• learning_rate: 1e-05
• weight_decay: 0.01
• num_train_epochs: 4
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• optim: adamw_torch_fused
• push_to_hub: True
• hub_model_id: Shashwat13333/bge-base-en-v1.5
• push_to_hub_model_id: bge-base-en-v1.5
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 4
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 1e-05
• weight_decay: 0.01
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 4
• max_steps: -1
• lr_scheduler_type: cosine
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: True
• 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: True
• 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_fused
• 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: True
• resume_from_checkpoint: None
• hub_model_id: Shashwat13333/bge-base-en-v1.5
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: bge-base-en-v1.5
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
0.2105	1	4.4608	-	-	-	-	-
0.8421	4	-	0.3891	0.3727	0.4175	0.3876	0.2956
1.2105	5	4.2215	-	-	-	-	-
1.8421	8	-	0.4088	0.4351	0.4034	0.4052	0.3167
2.4211	10	3.397	-	-	-	-	-
2.8421	12	-	0.4440	0.4252	0.4133	0.4284	0.3024
3.6316	15	2.87	-	-	-	-	-
3.8421	16	-	0.4371	0.4332	0.4384	0.4444	0.312

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.3.1
• Transformers: 4.47.1
• PyTorch: 2.5.1+cu124
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.21.0

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

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}
}