README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:786
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-l
widget:
  - source_sentence: >-
      How much money was saved through systems automation and process
      improvement efforts?
    sentences:
      - >-
        Member","Thought Leadership","E-commerce","Entrepreneurship","Mobile
        Devices","Product Management","Start-ups","Strategic
        Partnerships","Strategy"]
      - >-
        - URL":"linkedin.com/company/channel-factory","Description":"• Helped
        scale the video advertising startup from 0 to 8-figure revenues and 5 to
        40+ employees in 2.5 years.\n• Managed the company's day-to-day
        operations. Saved $100,000+ through systems automation and process
        improvement efforts.\n• Led sales operations for a 7-person ad sales
        team and managed BD partnerships with one of the three largest online
        travel agencies, a major online ad management platform, and rep firms in
        the United Kingdom, India, Brazil, and Australia.\n• Spearheaded
        company recruitment efforts and improved HR budget efficiency to save
        $350,000+ annually.\n• Evaluated, implemented, and managed third party
        business systems, including Salesforce and
      - >-
        and start building trust and camaraderie at work - vital assets in
        providing psychological safety, enabling agility and unleashing
        growth.\n","Company Size":"11-50","Industries":["Administrative
        Services","Community and Lifestyle","Government and Military","HR and
        Recruiting","Health","Information
        Technology","Software"],"Title":"Co-Founder and Servant
        CEO","Departments":["Senior Leadership"],"Start Date":"2018-01-01","End
        Date":null,"Location":"Santa Monica, California, United States, United
        States","Is Current":true,"Job Order":18},{"Company
        Name":"CNCCEF","Specter - Company
        ID":"5e3b912d137e998b5ae832aa","Domain":"cnccef.org","LinkedIn -
  - source_sentence: What skills do you possess that relate to marketing and brand development?
    sentences:
      - >-
        I have been fortunate to have been a part of the creation and/or growth
        story for brands including ASYSTEM, Formula Fig, Aritzia, Mr Porter to
        name a few.

        Skills: ["E-commerce","Advertising","Social
        Media","Strategy","Marketing","Online Advertising","Fashion","Brand
        Development","Marketing Strategy","Digital Strategy","Media
        Relations","Retail","Business Development","Digital Marketing","Mobile
        Devices","Digital Media","Marketing Communications","Strategic
        Communications","Branding & Identity","Business Strategy","Product
        Development","Social media","eCommerce","Art Direction","Brand
        Management","Brand Strategy","Consumer Behavior","Creative
        Strategy","E-Commerce","Media"]
      - >-
        is able to do so in near real time.","Company
        Size":null,"Industries":null,"Title":"ceo","Departments":["Senior
        Leadership"],"Start Date":"2005-03-01","End
        Date":"2007-12-01","Location":null,"Is Current":false,"Job
        Order":8},{"Company Name":"SnapNames","Specter - Company
        ID":"5e3bc17800c8f4c966a8bad6","Domain":"snapnames.com","LinkedIn -
        URL":"linkedin.com/company/snapnames-com","Description":"I served as a
        strategic advisor to the CEO in the capacity of a Board Director, and
        briefly as Chairman of the Board, prior to its acquisition by
        Oversee","Company Size":"11-50","Industries":["Commerce and
        Shopping","Internet Services"],"Title":"Director Board Of
        Directors","Departments":["Senior Leadership"],"Start
        Date":"2002-04-01","End
      - "Technology\",\"Software\",\"Transportation\"],\"Title\":\"Co-Founder & CTO\",\"Departments\":[\"Senior Leadership\",\"Engineering\"],\"Start Date\":\"2021-08-01\",\"End Date\":null,\"Location\":\"Los Altos, California, United States, United States\",\"Is Current\":true,\"Job Order\":6},{\"Company Name\":\"XDLINX Space Labs\",\"Specter - Company ID\":\"6712477ab8cbb513aaee920e\",\"Domain\":\"xdlinx.space\",\"LinkedIn - URL\":\"linkedin.com/company/xdlinx-labs\",\"Description\":null,\"Company Size\":\"51-200\",\"Industries\":[\"Hardware\",\"Transportation\"],\"Title\":\"Co-Founder\",\"Departments\":[\"Senior Leadership\"],\"Start Date\":\"2022-07-01\",\"End Date\":null,\"Location\":\"HyderÄ\x81bÄ\x81d, Telangana, India, Asia\",\"Is Current\":true,\"Job Order\":5},{\"Company Name\":\"Diamanti\",\"Specter - Company"
  - source_sentence: In what ways does SignalFire support companies at the seed stage?
    sentences:
      - >-
        -
        URL":"linkedin.com/school/%D0%BC%D0%BE%D1%81%D0%BA%D0%BE%D0%B2%D1%81%D0%BA%D0%B0%D1%8F-%D0%BC%D0%B5%D0%B6%D0%B4%D1%83%D0%BD%D0%B0%D1%80%D0%BE%D0%B4%D0%BD%D0%B0%D1%8F-%D0%B2%D1%8B%D1%81%D1%88%D0%B0%D1%8F-%D1%88%D0%BA%D0%BE%D0%BB%D0%B0-%D0%B1%D0%B8%D0%B7%D0%BD%D0%B5%D1%81%D0%B0-%C2%AB%D0%BC%D0%B8%D1%80%D0%B1%D0%B8%D1%81%C2%BB-%D0%B8%D0%BD%D1%81%D1%82%D0%B8%D1%82%D1%83%D1%82-","Field
        of Study":"","Degree Title":"Integrated year
        abroad","Description":null,"Start Date":"2006-01-01","End
        Date":"2006-01-01","Location":"Moscow, Moscow, Russian Federation,
        Russia"},{"Name":"Hochschule Furtwangen University","LinkedIn -
        URL":"linkedin.com/school/hochschule-furtwangen-university","Field of
        Study":"International Management","Degree Title":"Bachelor
      - >-
        I specialize in driving the data algorithms that can predict venture
        outcomes and target the top 5% of funding rounds at each stage. I have a
        product mentality and a people-first, technology second, point of view.
        I also have an honorary doctorate from the University of Kent, where I
        studied British Constitution and Sociology. I have lived in Palo Alto,
        California since 1997, and I am passionate about anticipating and
        creating change in the tech industry.
      - >-
        firepower at the seed stage to solve the biggest entrepreneur pain
        points.  Our distributed network approach provides expert advice from
        some of the world's best entrepreneurs, product & engineering leaders in
        virtually every key discipline and industry.  We have developed a first
        of its kind centralized infrastructure to help with recruiting
        exceptional talent, business development, customer acquisition as well
        as educational & community events.  We don’t follow the crowd, and
        almost always lead our investment rounds as the first institutional
        investors in exceptional companies.  You can read more about SignalFire
        at: https://medium.com/signalfire-fund","Company
        Size":"51-200","Industries":["Data and Analytics","Finance","Lending and
  - source_sentence: What role did the individual hold at the company from 1998 to 2002?
    sentences:
      - >-
        Current":true,"Job Order":25},{"Company Name":"BigSpring","Specter -
        Company ID":"653554dfd1653b1e73051e7c","Domain":"bigspring.ai","LinkedIn
        - URL":"linkedin.com/company/bigspringai","Description":null,"Company
        Size":"11-50","Industries":["Community and Lifestyle","Data and
        Analytics","DeepTech","Education","HR and Recruiting","Professional
        Services","Software"],"Title":"Advisor","Departments":["Other"],"Start
        Date":"2019-01-01","End Date":null,"Location":"San Francisco,
        California, United States, United States","Is Current":true,"Job
        Order":24},{"Company Name":"Clockwise","Specter - Company
        ID":"5e3a8f1e040ca7b0c6f0bd98","Domain":"getclockwise.com","LinkedIn -
        URL":"linkedin.com/company/clockwise-inc.","Description":null,"Company
      - >-
        a relationship to VeriSIgn to sell Internet Keywords through its
        channels.\n\nAn IPO filing.\n\nOver 350 employees.","Company
        Size":"1-10","Industries":["Internet
        Services","Software","Transportation"],"Title":"CEO, President,
        Chairman","Departments":["Senior Leadership"],"Start
        Date":"1998-01-01","End Date":"2002-06-01","Location":"San Carlos,
        California, United States, United States","Is Current":false,"Job
        Order":4},{"Company Name":"NetNames","Specter - Company
        ID":"5e3bbde400c8f4c9669d8d4b","Domain":"netnames.com","LinkedIn -
        URL":"linkedin.com/company/netnames","Description":"I seed funded
        NetNames. We sold it to NetBenefit in 2000. I was a board member of the
        merged entity through 2001. NetNames was the world's first domain name
      - >-
        - Company
        ID":"64f802e6538115f141f4063a","Domain":"trynectar.io","LinkedIn -
        URL":"linkedin.com/company/nectar-ai","Description":null,"Company
        Size":"11-50","Industries":["Advertising","Commerce and Shopping","Data
        and Analytics","DeepTech","Sales and
        Marketing","Software"],"Title":"Investor","Departments":["Senior
        Leadership"],"Start Date":"2023-10-01","End
        Date":null,"Location":"Seattle, Washington, United States, United
        States","Is Current":true,"Job Order":32},{"Company
        Name":"BinStar","Specter - Company
        ID":"6411d185abe7c1e313b62b4a","Domain":"bin-star.com","LinkedIn -
        URL":"linkedin.com/company/binstar","Description":null,"Company
        Size":"1-10","Industries":["Commerce and
        Shopping"],"Title":"Investor","Departments":["Senior
  - source_sentence: >-
      What is the primary focus of Fluence as a continuing education
      organization?
    sentences:
      - >-
        Name":"Fluence","Specter - Company
        ID":"621f973f972ef7e5d69c8085","Domain":"fluencetraining.com","LinkedIn
        - URL":"linkedin.com/company/fluencetraining","Description":"Fluence is
        a leading continuing education organization in psychedelic
        therapy.","Company Size":"11-50","Industries":["Education","HR and
        Recruiting","Health","Software"],"Title":"Advisor","Departments":["Other"],"Start
        Date":"2023-07-01","End Date":null,"Location":"New York City, New York,
        United States, United States","Is Current":true,"Job
        Order":17},{"Company Name":"VentureKit","Specter - Company
        ID":null,"Domain":"venturekit.com","LinkedIn -
        URL":"linkedin.com/company/venturekit","Description":"VentureKit
        publishes free guides to help entrepreneurs get things
      - >-
        Order":7},{"Company Name":"Jelastic","Specter - Company
        ID":"5e3bbee700c8f4c966a06981","Domain":"jelastic.com","LinkedIn -
        URL":"linkedin.com/company/jelastic","Description":"Jelastic is a cloud
        platform that provides multi-cloud Platform as a Service (PaaS) based on
        container technology. It supports a wide range of programming languages
        and frameworks, and is easy to scale up or down to meet your changing
        needs. Acquired by Virtoozo in 2021.\n\nRole and results:\n- Managed an
        engineering team\n- Managed R&D projects\n- Jelastic won several
        international startup awards \n- Acquired by Virtozzo","Company
        Size":"11-50","Industries":["Information Technology","Internet
        Services","Software"],"Title":"Co-Founder","Departments":["Senior
      - >-
        Education Level: Bachelor's Degree

        Current Position Title: CTO, Head of Research

        Current Position Company Name: Mursion

        Current Position Company Website: mursion.com

        Past Position Title: CEO and Co-founder

        Past Position Company Name: DNABLOCK

        Past Position Company Website: dnablock.com

        Current Tenure: 85.0

        Average Tenure: 34.0

        Languages: [{"Name":"Spanish","Proficiency Level":"Limited Working
        Proficiency"},{"Name":"Arabic","Proficiency Level":"Limited Working
        Proficiency"}]

        LinkedIn - Followers: 5022.0

        LinkedIn - Connections: 2997.0
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-l
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.7916666666666666
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9666666666666667
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.975
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9833333333333333
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7916666666666666
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.32222222222222213
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19500000000000003
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09833333333333334
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7916666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9666666666666667
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.975
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9833333333333333
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.901899634958155
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.874107142857143
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8748790726817042
            name: Cosine Map@100

SentenceTransformer based on Snowflake/snowflake-arctic-embed-l

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. 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: Snowflake/snowflake-arctic-embed-l
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("ngiometti/legal-ft-3")
# Run inference
sentences = [
    'What is the primary focus of Fluence as a continuing education organization?',
    'Name":"Fluence","Specter - Company ID":"621f973f972ef7e5d69c8085","Domain":"fluencetraining.com","LinkedIn - URL":"linkedin.com/company/fluencetraining","Description":"Fluence is a leading continuing education organization in psychedelic therapy.","Company Size":"11-50","Industries":["Education","HR and Recruiting","Health","Software"],"Title":"Advisor","Departments":["Other"],"Start Date":"2023-07-01","End Date":null,"Location":"New York City, New York, United States, United States","Is Current":true,"Job Order":17},{"Company Name":"VentureKit","Specter - Company ID":null,"Domain":"venturekit.com","LinkedIn - URL":"linkedin.com/company/venturekit","Description":"VentureKit publishes free guides to help entrepreneurs get things',
    'Education Level: Bachelor\'s Degree\nCurrent Position Title: CTO, Head of Research\nCurrent Position Company Name: Mursion\nCurrent Position Company Website: mursion.com\nPast Position Title: CEO and Co-founder\nPast Position Company Name: DNABLOCK\nPast Position Company Website: dnablock.com\nCurrent Tenure: 85.0\nAverage Tenure: 34.0\nLanguages: [{"Name":"Spanish","Proficiency Level":"Limited Working Proficiency"},{"Name":"Arabic","Proficiency Level":"Limited Working Proficiency"}]\nLinkedIn - Followers: 5022.0\nLinkedIn - Connections: 2997.0',
]
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

• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7917
cosine_accuracy@3	0.9667
cosine_accuracy@5	0.975
cosine_accuracy@10	0.9833
cosine_precision@1	0.7917
cosine_precision@3	0.3222
cosine_precision@5	0.195
cosine_precision@10	0.0983
cosine_recall@1	0.7917
cosine_recall@3	0.9667
cosine_recall@5	0.975
cosine_recall@10	0.9833
cosine_ndcg@10	0.9019
cosine_mrr@10	0.8741
cosine_map@100	0.8749

Training Details

Training Dataset

Unnamed Dataset

• Size: 786 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 786 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 9 tokens mean: 17.2 tokens max: 33 tokens	min: 11 tokens mean: 218.92 tokens max: 464 tokens

• Samples:

  sentence_0	sentence_1
  What types of products has the individual built experience in, according to the context?	experience in building world class hardware and software products for consumer electronics, aerospace and enterprise software solutions. Proven track record of building big-data cloud computing software and analytic software platform with AI, Computer Vision and Machine Learning. Progressive, innovative and highly valued for aligning corporate strategies with market opportunities, translating goals into actionable plans, and providing leadership to multi-discipline, cross cultural teams.
  How does the individual align corporate strategies with market opportunities?	experience in building world class hardware and software products for consumer electronics, aerospace and enterprise software solutions. Proven track record of building big-data cloud computing software and analytic software platform with AI, Computer Vision and Machine Learning. Progressive, innovative and highly valued for aligning corporate strategies with market opportunities, translating goals into actionable plans, and providing leadership to multi-discipline, cross cultural teams.
  What is the company size of Diamanti?	- Company ID":"5e3a8f19040ca7b0c6f031bf","Domain":"diamanti.com","LinkedIn - URL":"linkedin.com/company/diamanti","Description":null,"Company Size":"51-200","Industries":["Consumer Products","Hardware","Information Technology","Internet Services","Software"],"Title":"Chief Operating Officer","Departments":["Senior Leadership","Operations"],"Start Date":"2018-11-01","End Date":"2021-07-01","Location":"San Jose, California, United States, United States","Is Current":false,"Job Order":4},{"Company Name":"Planet","Specter - Company ID":"5e3bc13c00c8f4c966a7da4c","Domain":"planet.com","LinkedIn - URL":"linkedin.com/company/planet-labs","Description":"Planet operates the world's largest fleet of Earth imaging satellites to daily image the entire

• 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: steps
• per_device_train_batch_size: 10
• per_device_eval_batch_size: 10
• num_train_epochs: 10
• 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: 10
• per_device_eval_batch_size: 10
• 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: 10
• 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: 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: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	cosine_ndcg@10
0.6329	50	-	0.8917
1.0	79	-	0.9080
1.2658	100	-	0.9265
1.8987	150	-	0.9091
2.0	158	-	0.9100
2.5316	200	-	0.9214
3.0	237	-	0.9110
3.1646	250	-	0.9161
3.7975	300	-	0.9108
4.0	316	-	0.9145
4.4304	350	-	0.8955
5.0	395	-	0.9019
5.0633	400	-	0.9008
5.6962	450	-	0.8980
6.0	474	-	0.9036
6.3291	500	0.7603	0.9021
6.9620	550	-	0.8977
7.0	553	-	0.8976
7.5949	600	-	0.9059
8.0	632	-	0.9005
8.2278	650	-	0.9039
8.8608	700	-	0.9050
9.0	711	-	0.9052
9.4937	750	-	0.9021
10.0	790	-	0.9019

Framework Versions

• Python: 3.13.1
• Sentence Transformers: 3.4.1
• Transformers: 4.49.0
• PyTorch: 2.6.0+cu124
• Accelerate: 1.4.0
• Datasets: 3.3.2
• 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}
}