metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:408
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en-v1.5
widget:
  - source_sentence: What sets TechChefz apart?
    sentences:
      - >-
        Sharing Stories from Our Team


        Discover firsthand experiences, growth journeys, and the vibrant culture
        that fuels our success.


        I have been a part of Techchefz for 3 years, and I can confidently say
        it's been a remarkable journey. From day one, I was welcomed into a
        vibrant community that values collaboration, creativity, and personal
        growth. The company culture here isn't just a buzzword, it's tangible in
        every interaction and initiative.

        profileImg


        Aashish Massand


        Sr. Manager Delivery


        TechChefz has been a transformative journey, equipping me with
        invaluable skills and fostering a supportive community. From coding
        fundamentals to advanced techniques, I've gained confidence and
        expertise. Grateful for this experience and opportunity.

        profileImg


        Pankaj Datt


        Associate Technology
      - >-
        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.
      - >-
        TechChefz Digital has established its presence in two countries,
        showcasing its global reach and influence. The company’s headquarters is
        strategically located in Noida, India, serving as the central hub for
        its operations and leadership. In addition to the headquarters,
        TechChefz Digital has expanded its footprint with offices in Delaware,
        United States, allowing the company to cater to the North American
        market with ease and efficiency.
  - source_sentence: How does this solution comply with data regulations?
    sentences:
      - >-
        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
      - >
        We assist businesses by transforming their goals, teams, and cultures
        with digital technology to make them colinear with the digital age.
        Through digitalization, organizations can facilitate advanced
        decision-making and management.
      - >-
        Microservices Transformation Process

        Requirements Analysis

        We begin by understanding the client&#39;s needs and objectives for the
        website. Identify key features, functionality, and any specific design
        preferences.


        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.


        Testing

        After each sprint we conduct thorough testing of the website to identify
        and fix any bugs or issues. Perform usability testing to ensure a
        positive user experience.

        Deployment

        After testing we deploy the website sprint by sprint, to a hosting
        environment, ensuring proper configuration for security and performance.
        Our expert DevOps team sets up any necessary domain and server
        configurations and ensure smooth running of website.
  - source_sentence: What tasks can we automate using machine learning?
    sentences:
      - >-
        Check out our latest news, announcements, and featured insights.


        Explore our latest insights and stay informed with our thought-provoking
        content. Dive in now for valuable perspectives.

        Our Featured Insights


        How UX and UI Work Together in Web Design


        Navigating the Post-Cookie Era: Strategies for Effective Targeting and
        Personalization


        Data-Driven Decision Making in Digital Advertising: Leveraging Analytics
        for Success


        SEO Unleashed: Navigating the Digital Landscape with Advanced Search
        Engine Optimization Tools


        Is manual testing replaced by automation Testing?
      - >-
        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.
      - Mayank Maggon is CEO of Techchefz Digital
  - source_sentence: How can you help us grow our partnerships?
    sentences:
      - |-
        Partner Experience (PX)
         From optimized collaboration tools to data-driven insights, our solutions are designed to drive efficiency, transparency, and growth in partner relationships. With a keen understanding of complexities of partner ecosystems, we help enterprise brands unlock new opportunities, strengthen alliances, and achieve shared success in today’s dynamic business environment.
      - >-
        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.
      - >-
        COMMERCE PLATFORMS

        Discover the strength of our partnership.

        Adobe Commerce Cloud

        A comprehensive e-commerce platform that allows businesses to create,
        manage, and optimize their online stores. Formerly known as Magento
        Commerce, Adobe Commerce Cloud provides a range of features and
        capabilities to help businesses create engaging online shopping
        experiences, manage their products and catalogs, process orders, and
        drive online sales.

        Magento

        An open-source e-commerce platform that allows businesses to create
        online stores and manage their digital operations. It was first released
        in 2008 and has since become one of the most popular e-commerce
        platforms in the world.

        Shopify

        Salesforce Commerce Cloud (SFCC)
  - source_sentence: How is an Enterprise CMS different from a headless CMS?
    sentences:
      - >-
        How do I figure out how much your services will cost?

        Determining the cost of our services is best achieved through a 15-30
        minute discovery call, where we can understand your unique requirements.
        Following that, we will provide a transparent and detailed price within
        24-48 hours tailored specifically to you
      - >-
        Discover the right CMS for your Business Requirements

        Headless CMS

        They separate the backend content repository from the frontend
        presentation layer, allowing content to be delivered to any device or
        platform via APIs offering flexibility and scalability.



        Enterprise CMS

        ECMSs are more comprehensive systems designed to manage all types of
        content within an organization, including documents, images, videos, and
        other digital assets.
      - >-
        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.
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
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.0784313725490196
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4019607843137255
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5196078431372549
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.0261437908496732
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08039215686274509
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05196078431372548
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.0784313725490196
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.4019607843137255
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5196078431372549
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.20681828171013134
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.11193977591036408
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12704742492729623
            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
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.0784313725490196
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.4019607843137255
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5196078431372549
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.0261437908496732
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08039215686274509
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05196078431372548
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.0784313725490196
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.4019607843137255
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5196078431372549
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.20587690425273067
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.11086601307189538
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12502250584870636
            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
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.06862745098039216
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.39215686274509803
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5098039215686274
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.02287581699346405
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.0784313725490196
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05098039215686274
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.06862745098039216
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.39215686274509803
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5098039215686274
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.20200410483390918
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.10891690009337061
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.12124652633795324
            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
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.058823529411764705
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3137254901960784
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.49019607843137253
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.0196078431372549
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.06274509803921569
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04901960784313725
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.058823529411764705
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3137254901960784
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.49019607843137253
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.18661585783989612
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.09673202614379077
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.11007694082793783
            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
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.029411764705882353
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.28431372549019607
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.4117647058823529
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.00980392156862745
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.05686274509803922
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04117647058823529
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.029411764705882353
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.28431372549019607
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.4117647058823529
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.15696823886592676
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.08097572362278241
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.09297982754610348
            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("akashmaggon/bge-base-financial-matryoshka-finetuning-tcz-1")
# Run inference
sentences = [
    'How is an Enterprise CMS different from a headless CMS?',
    'Discover the right CMS for your Business Requirements\nHeadless CMS\nThey separate the backend content repository from the frontend presentation layer, allowing content to be delivered to any device or platform via APIs offering flexibility and scalability.\n\n\nEnterprise CMS\nECMSs are more comprehensive systems designed to manage all types of content within an organization, including documents, images, videos, and other digital assets.',
    'How do I figure out how much your services will cost?\nDetermining the cost of our services is best achieved through a 15-30 minute discovery call, where we can understand your unique requirements. Following that, we will provide a transparent and detailed price within 24-48 hours tailored specifically to you',
]
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	0.0	0.0	0.0	0.0	0.0
cosine_accuracy@3	0.0784	0.0784	0.0686	0.0588	0.0294
cosine_accuracy@5	0.402	0.402	0.3922	0.3137	0.2843
cosine_accuracy@10	0.5196	0.5196	0.5098	0.4902	0.4118
cosine_precision@1	0.0	0.0	0.0	0.0	0.0
cosine_precision@3	0.0261	0.0261	0.0229	0.0196	0.0098
cosine_precision@5	0.0804	0.0804	0.0784	0.0627	0.0569
cosine_precision@10	0.052	0.052	0.051	0.049	0.0412
cosine_recall@1	0.0	0.0	0.0	0.0	0.0
cosine_recall@3	0.0784	0.0784	0.0686	0.0588	0.0294
cosine_recall@5	0.402	0.402	0.3922	0.3137	0.2843
cosine_recall@10	0.5196	0.5196	0.5098	0.4902	0.4118
cosine_ndcg@10	0.2068	0.2059	0.202	0.1866	0.157
cosine_mrr@10	0.1119	0.1109	0.1089	0.0967	0.081
cosine_map@100	0.127	0.125	0.1212	0.1101	0.093

Training Details

Training Dataset

Unnamed Dataset

Size: 408 training samples
Columns: anchor and positive
Approximate statistics based on the first 408 samples:
anchor positive
type string string
details
min: 8 tokens
mean: 12.63 tokens
max: 21 tokens

min: 14 tokens
mean: 94.18 tokens
max: 270 tokens

	anchor	positive
type	string	string
details	min: 8 tokens mean: 12.63 tokens max: 21 tokens	min: 14 tokens mean: 94.18 tokens max: 270 tokens

Samples:

anchor	positive
`What's it like working at Techchefz?`	`Join one of the most resourceful tech teams Discover your future with us. Explore opportunities, values, and culture. Join a dynamic and innovative team at Techchefz. LIFE AT TECHCHEFZ Make an Impact from Day One. We believe in the power of collaboration to create, innovate, and develop groundbreaking solutions. Our teams work closely with clients and partners to co-create solutions that drive innovation and business growth. Your new journey awaits!`
`How can I contact TechChefz if I'm in the US?`	`TechChefz Digital has established its presence in two countries, showcasing its global reach and influence. The company’s headquarters is strategically located in Noida, India, serving as the central hub for its operations and leadership. In addition to the headquarters, TechChefz Digital has expanded its footprint with offices in Delaware, United States, allowing the company to cater to the North American market with ease and efficiency.`
`What results can I expect from your services?`	`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.`

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
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: True
optim: adamw_torch_fused
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: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
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: False
resume_from_checkpoint: None
hub_model_id: None
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: 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
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	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
0.6154	1	0.2038	0.1993	0.1953	0.1764	0.1595
1.6154	2	0.2038	0.1993	0.1953	0.1764	0.1595
2.6154	3	0.2068	0.2059	0.202	0.1866	0.157
3.6154	4	0.2068	0.2059	0.2020	0.1866	0.1570

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+cu121
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}
}