borgcollectivegmbh/jina-embeddings-v2-small-en_linkedin_profile_model_run1__modified_config

SentenceTransformer based on jinaai/jina-embeddings-v2-small-en

This is a sentence-transformers model finetuned from jinaai/jina-embeddings-v2-small-en. It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

https://wandb.ai/deklanw/sentence-transformers/runs/frjg0h13?nw=nwuserdeklanw

Model Description

• Model Type: Sentence Transformer
• Base model: jinaai/jina-embeddings-v2-small-en
• Maximum Sequence Length: 2048 tokens
• Output Dimensionality: 512 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': 2048, 'do_lower_case': False}) with Transformer model: JinaBertModel 
  (1): Pooling({'word_embedding_dimension': 512, '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("borgcollectivegmbh/jina-embeddings-v2-small-en_linkedin_profile_model_run1")
# Run inference
sentences = [
    'Experienced in SAP consultancy',
    '=== PERSON ===\nMärt Ehrenpreis\nN/A\nTallinn Metropolitan Area\n470\n\n=== ROLES ===\n>>> COMPANY ROLES <<<\n\nCompany Role #1:\n  Board Member CTO\n  2023-04 - N/A\n  N/A\n  Elron / Eesti Liinirongid AS \n  eestiliinirongid\n  Truck Transportation\n  Loome Sulle aega – viime Sind kohale kiiresti, turvaliselt ja mugavalt\n  414\n\nCompany Role #2:\n  Managing Director, Proxion Plan Estonia OÜ\n  2021-01 - 2023-04\n  N/A\n  Proxion\n  proxion-plan-oy\n  Civil Engineering\n  Proxion on osa WSP-yhtiöitä.\nOtathan seurantaan WSP in Finland -tilin!\n  2563\n\n>>> SCHOOL ROLES <<<\nNo school roles listed.',
    "=== PERSON ===\nHarvindar Singh Garcha\nHarvindar's passion for technology can be traced back right from his childhood, Getting into the field of computer science bought him to have more focus on his goal. He is a fast learner and easily adapts to new skills. He always has the hunger and curiosity to learn new skills. <br><br>He has expertise in the design &  development of RESTful APIs and back-end services utilizing Python ecosystem, Django, Flask, Docker, and SQL with an emphasis on scalability and security.<br><br>He is currently working as a full stack developer at AI Automotive company where he has worked on technologies Django, Flask, Python, RESTful APIs, React, Redux, Celery, and JavaScript, while keeping in mind all the secure code practices of OWASP top 10.<br><br>His specialties include quickly learning new skills, Programming languages, and Critical thinking in problem-solving.<br><br>In his free time, you will find him reading articles about the latest trending technologies on Internet,  Spending some time on Quora & hiking on the mountains.\nPune, Maharashtra, India\n1294\n\n=== ROLES ===\n>>> COMPANY ROLES <<<\n\nCompany Role #1:\n  Software Development Analyst\n  2020-04 - 2020-08\n  N/A\n  Metta Social\n  metta-social\n  IT Services and IT Consulting\n  Building world’s largest common good platform to enable sustainable impact at scale!\n  4002\n\nCompany Role #2:\n  Junior Backend Engineer\n  2020-09 - 2021-03\n  N/A\n  SRV Media\n  srv-media\n  Advertising Services\n  Insights | Ideas | Impact\n  49579\n\nCompany Role #3:\n  Full Stack Developer\n  2021-03 - 2022-01\n  N/A\n  SRV Media\n  srv-media\n  Advertising Services\n  Insights | Ideas | Impact\n  49579\n\nCompany Role #4:\n  Software Development Intern\n  2019-10 - 2020-03\n  Currently building a B2B social ecosystem platform where my daily work includes to develop and unit test REST API's using Flask and ORM using SQLAlchemy.<br><br>- Contributed 90% of the API's for mobile application which was build in just a month keeping in mind all the secure code practices of OWASP Top 10.<br><br>- Building REST API using Flask framework, for web app & checking the load balancing of concurrent users.<br>        <br>- Building database model using SQL-Alchemy, and connecting it to Heroku.<br><br>- Security Testing of the API's !\n  Metta Social\n  metta-social\n  IT Services and IT Consulting\n  Building world’s largest common good platform to enable sustainable impact at scale!\n  4002\n\nCompany Role #5:\n  Research And Development Engineer\n  2022-01 - N/A\n  N/A\n  Cerence Inc.\n  cerence\n  Software Development\n  Cerence is the global industry leader in creating unique, moving experiences for the mobility world.\n  44039\n\n>>> SCHOOL ROLES <<<\nNo school roles listed.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

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

Evaluation

Metrics

Binary Classification

• Datasets: ``, rec_test_evaluator and query_test_evaluator
• Evaluated with custom_evaluator.BinaryClassificationEvaluator

Metric		rec_test_evaluator	query_test_evaluator
cosine_accuracy	0.9527	0.9369	0.9622
cosine_accuracy_threshold	0.2778	0.3141	0.263
cosine_f1	0.8559	0.7995	0.885
cosine_f1_threshold	0.2539	0.2846	0.2541
cosine_precision	0.8474	0.8165	0.8894
cosine_recall	0.8646	0.7832	0.8805
cosine_ap	0.9214	0.87	0.9475
dot_accuracy	0.9287	0.9174	0.9483
dot_accuracy_threshold	7.1923	4.7818	8.4253
dot_f1	0.7795	0.7457	0.8433
dot_f1_threshold	6.0999	4.3656	7.5479
dot_precision	0.7621	0.7486	0.8372
dot_recall	0.7976	0.7428	0.8495
dot_ap	0.8651	0.7954	0.9205
manhattan_accuracy	0.8422	0.8619	0.8801
manhattan_accuracy_threshold	69.5022	69.5686	116.771
manhattan_f1	0.3987	0.507	0.56
manhattan_f1_threshold	133.9353	82.6656	128.6138
manhattan_precision	0.2726	0.4506	0.5831
manhattan_recall	0.742	0.5796	0.5387
manhattan_ap	0.3697	0.5479	0.6344
euclidean_accuracy	0.8425	0.8626	0.8804
euclidean_accuracy_threshold	3.8574	3.8601	6.4738
euclidean_f1	0.3999	0.5062	0.5614
euclidean_f1_threshold	7.4916	4.6146	7.1657
euclidean_precision	0.2716	0.4435	0.5753
euclidean_recall	0.7579	0.5894	0.5481
euclidean_ap	0.37	0.5487	0.6369
max_accuracy	0.9527	0.9369	0.9622
max_accuracy_threshold	69.5022	69.5686	116.771
max_f1	0.8559	0.7995	0.885
max_f1_threshold	133.9353	82.6656	128.6138
max_precision	0.8474	0.8165	0.8894
max_recall	0.8646	0.7832	0.8805
max_ap	0.9214	0.87	0.9475

Training Details

Training Dataset

Unnamed Dataset

• Size: 155,651 training samples
• Columns: text1 and text2
• Approximate statistics based on the first 1000 samples:

  	text1	text2
  type	string	string
  details	min: 5 tokens mean: 231.14 tokens max: 2048 tokens	min: 51 tokens mean: 618.32 tokens max: 2048 tokens

• Samples:

  text1	text2
  === PERSON === Dr. Amol Charegaonkar Alumnus of IIM Indore (FDP-Executive Education) Specialties: Data Analysis, Finance Pune, Maharashtra, India 4511 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Principal Consultant 2015-04 - 2021-06 N/A Maruma Consultancy maruma-consultancy Human Resources Services People Development Simplified 218 Company Role #2: Assistant Manager – Credit (Policy - Unsecured loans) 2008-06 - 2009-01 Job Responsibilities: As a Team Member of the Credit Policy & Risk function 1.Analysis of Delinquent cases in Personal loans and Business Loans 2.Online analysis of cases booked under Personal and Business Loans 3.Auditing Pan India cases for credit underwriting w. r. t. Policy 4.Analyzing and publishing a Monthly Portfolio Review for Personal Loans from the Risk Perspective like Delinquency & Bounce Trend and Credit Appraisal Process 5.Incorporate the necessary changes required in the Lending Policy consid...	=== PERSON === Rajesh Baj N/A Hyderabad, Telangana, India 491 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Sr.Officer Finance and Accounts 2010-10 - N/A N/A JK Agri Genetics Limited jk-agri-genetics-limited Biotechnology Research Harvesting Happiness Through Innovations 107873 Company Role #2: Assistant Manager 2013-10 - N/A N/A JK Agri Genetics Limited jk-agri-genetics-limited Biotechnology Research Harvesting Happiness Through Innovations 107873 Company Role #3: Officer- Finance and Accounts 2007-05 - 2007-07 Market Research in following Areas:- 1. Bandra-Kurla complex 2. Solitaire corporate Park Andheri 3. Udyog Bhavan, Garegaon HSBC hsbc Financial Services N/A N/A >>> SCHOOL ROLES <<< No school roles listed.
  === PERSON === Gabriela Menezes • Experiência em localização Brasil - TAXBRA, Nota Fiscal Eletrônica. • Conhecimento em SAP Activate e ASAP. • Experiência em suporte ao Cliente - AMS São Paulo, São Paulo, Brazil 454 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Consultora SAP SD S/4HANA 2023 - N/A Atuação em - AMS Analise e resolução de chamados dentro do SLA estabelecido. Atuação nas diversas solicitações de melhoria. Resolução de problemas relacionados a NF-e Testes unitários e integrados Configuração de impostos e leis fiscais. Configuração de conta contábil. Resolução de erros relacionados a Pricing. Conhecimento e vivência no processo de Retorno Simbólico. Apoio as frentes MM e FI Apoio a equipe de projetos em configurações, testes unitários e integrados. ITGCON Integração e Consultoria em Sistemas itgcon IT Services and IT Consulting Mais que uma implementadora, somos a ITGCON consultoria. 4116 Company Role #2: Co...	=== PERSON === Rafael Menezes Consultor funcional SD com experiência em AMS, formado em Tecnologia da Informação. - Principais qualificações: - Conhecimento em Localização Brasil, Pricing, Nota Fiscal Eletrônica e GRC. - Conhecimento das principais tabelas do módulo SD. - Conhecimento na configuração de impostos na J1BTAX - Conhecimento no cadastro de dados mestres de clientes e materiais. São Paulo, Brazil 117 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Consultor SAP SD Pleno 2023-05 - N/A N/A Capgemini capgemini IT Services and IT Consulting Get the future you want 6721701 Company Role #2: Consultor Funcional SD JR/PL 2021-12 - 2023-01 - Suporte ao cliente – AMS; - Análise e resolução de chamados respeitando SLA; - Testes em cenários de vendas; - Configuração de impostos – J1BTAX; - Resolução de erros referentes a rejeição de NF-e - Resolução de erros referentes a CFOP - Resolução de erros referentes a contas contábeis - Criação de...
  === PERSON === Anastasia Hanan, M.S., M.B.A (she/her) ~10 years of user research in both startups and enterprise. I am a senior researcher passionate about leading research that grounds product vision in data and emotion, highlights the user voice along with immediate/long term project risks, and optimizes for radically collaborative tactical execution through ambiguous problem spaces. Specialties: Complex systems research, moving between qualitative research to quantitative insights at scale, crypto, Qualtrics, innovation and strategy, process optimization, rapid insight, cross functional collaboration, making AI make sense, visual storytelling, presentations that win contests, get millions in funding, and/or create actionable product roadmaps. United States 1101 === ROLES === >>> COMPANY ROLES <<< Company Role #1: UX Researcher 2022-11 - N/A N/A United States Digital Service united-states-digital-service Government Administration We're mission-driven professio...	=== PERSON === Stephanie Kokotakis N/A Los Angeles, California, United States 325 === ROLES === >>> COMPANY ROLES <<< No company roles listed. >>> SCHOOL ROLES <<< No school roles listed.

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 47,595 evaluation samples
• Columns: text1, text2, and label
• Approximate statistics based on the first 1000 samples:

  	text1	text2	label
  type	string	string	int
  details	min: 5 tokens mean: 221.5 tokens max: 2048 tokens	min: 50 tokens mean: 605.95 tokens max: 2048 tokens	0: ~82.40% 1: ~17.60%

• Samples:

  text1	text2	label
  Nonprofit and association management expert	=== PERSON === Marius Strydom Marius Strydom has spent 20 years producing innovative research on the SA financial services industry, with a specific focus on insurance. He was rated the top SA life assurance analyst twice and the top short-term insurance analyst 5 times while working at Investec and BJM. At Bank of America Merrill Lynch, Marius led the EEMEA Financial Sector Research team to a second place in the 2013 Institutional Investor survey. During 2013 and 2014, he worked on academic research, culminating in being published in the South African Actuarial Journal. Since 2015, as part of his work with MLAX Consulting, Marius analysed and produced bespoke research on numerous SA and UK financial companies. In 2020, Marius founded Austin Lawrence Gidon and together with global partner, Edison Investment Research, they are driving the sponsored research revolution in South Africa. City of Cape Town, Western Cape, South Africa 1351 === ROLES === >>> COMPANY ROLES <<< Company Role #...	0
  Expert in Alienware product support	=== PERSON === Ryan Talbot With over 25 years of experience in physical security, Identity management, and video surveillance, Ryan is recognized as a leader in the design and implementation of major technology solutions. Ryan has managed major security and IT system implementations for government, commercial, transport, data centres, gaming & casinos, retail, law enforcement and critical infrastructure environments. Ryan has worked closely with major technology brands in the design and development of hardware and software products throughout; Australia, Europe, North America and Asia. A leader in advanced video solutions and a former committee member of the AS/NZS 62676:5 standards, an experienced project manager and is PRINCE2 certified. He has a certificate IV in security risk management and qualifications in security electronics and sports performance. Ryan has also been involved in the development and design of many new technologies for IP cameras, customised ...	0
  === PERSON === Kevin Watson Specialties: Parametric cost estimation, WLC / LCC analysis, Logistics and supportability modelling. Economic LORA, Spares modelling, Tools / Applications: PRICE® TruePlanning®, EDCAS®, VMetric® United Kingdom 389 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Senior Consultant 2013-09 - N/A N/A QinetiQ qinetiq_2 Defense and Space Manufacturing Create It. Test It. Use It. 122597 Company Role #2: Support Modelling Team Lead 2004-06 - 2011-02 N/A General Dynamics UK Limited general-dynamics-uk-limited Defense and Space Manufacturing General Dynamics UK is one of the UK’s leading defence companies and an important supplier to the UK Ministry of Defence 29195 Company Role #3: Estimation Specialist Senior Engineer 2011-02 - 2013-09 N/A General Dynamics UK Limited general-dynamics-uk-limited Defense and Space Manufacturing General Dynamics UK is one of the UK’s leading defence com...	=== PERSON === Kyle Biron, M.S. N/A Raleigh-Durham-Chapel Hill Area 308 === ROLES === >>> COMPANY ROLES <<< Company Role #1: Clinical Informatics Analyst Associate 2017-05 - 2018-05 • Data analyst at the Grow Baby Grow biostatistics lab at Kennesaw State University • Statistical programming and statistical modeling using the Pediatrix Medical Group, Inc. database of over 1.2 million infant records to solve medical problems • Received acknowledgement in a Neonatology publication comparing BMI with other proportionality measurements • En route to another publication comparing popular intrauterine preterm growth curves • Supervisory experience by managing and collaborating with other biostatisticians Kennesaw State University kennesaw-state-university N/A We are KSU Owls. And together, we're ascending. 167722 Company Role #2: Health Data Analyst II 2022-06 - N/A N/A Nuna Inc. nuna-inc IT Services and IT Consulting Driven by Data, Guided by Com...	0

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 32
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 32
• 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: 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: 1
• max_steps: -1
• lr_scheduler_type: linear
• 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: True
• 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: 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
• 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

Click to expand

Epoch	Step	Training Loss	Validation Loss	max_ap	rec_test_evaluator_max_ap	query_test_evaluator_max_ap
0	0	-	-	0.4584	0.5698	0.7804
0.0051	50	1.9282	-	-	-	-
0.0103	100	1.754	-	-	-	-
0.0154	150	1.4681	-	-	-	-
0.0206	200	1.1736	-	-	-	-
0.0257	250	1.0527	-	-	-	-
0.0308	300	0.9073	-	-	-	-
0.0360	350	0.9088	-	-	-	-
0.0411	400	0.8556	-	-	-	-
0.0463	450	0.77	-	-	-	-
0.0514	500	0.7768	-	-	-	-
0.0565	550	0.5559	-	-	-	-
0.0617	600	0.7102	-	-	-	-
0.0668	650	0.6498	-	-	-	-
0.0719	700	0.699	-	-	-	-
0.0771	750	0.6628	-	-	-	-
0.0822	800	0.7298	-	-	-	-
0.0874	850	0.6278	-	-	-	-
0.0925	900	0.6033	-	-	-	-
0.0976	950	0.5783	-	-	-	-
0.1028	1000	0.6187	-	-	-	-
0.1079	1050	0.5712	-	-	-	-
0.1131	1100	0.6375	-	-	-	-
0.1182	1150	0.6028	-	-	-	-
0.1233	1200	0.6227	-	-	-	-
0.1285	1250	0.5955	-	-	-	-
0.1336	1300	0.6402	-	-	-	-
0.1388	1350	0.5982	-	-	-	-
0.1439	1400	0.6085	-	-	-	-
0.1490	1450	0.6163	-	-	-	-
0.1542	1500	0.6304	-	-	-	-
0.1593	1550	0.5499	-	-	-	-
0.1645	1600	0.5648	-	-	-	-
0.1696	1650	0.6121	-	-	-	-
0.1747	1700	0.5499	-	-	-	-
0.1799	1750	0.518	-	-	-	-
0.1850	1800	0.565	-	-	-	-
0.1902	1850	0.5966	-	-	-	-
0.1953	1900	0.559	-	-	-	-
0	0	-	-	0.9020	-	-
0.2000	1946	-	4.7301	-	-	-
0.2004	1950	0.6196	-	-	-	-
0.2056	2000	0.5304	-	-	-	-
0.2107	2050	0.5613	-	-	-	-
0.2158	2100	0.5716	-	-	-	-
0.2210	2150	0.5914	-	-	-	-
0.2261	2200	0.5692	-	-	-	-
0.2313	2250	0.5049	-	-	-	-
0.2364	2300	0.5064	-	-	-	-
0.2415	2350	0.5624	-	-	-	-
0.2467	2400	0.482	-	-	-	-
0.2518	2450	0.5529	-	-	-	-
0.2570	2500	0.5037	-	-	-	-
0.2621	2550	0.5702	-	-	-	-
0.2672	2600	0.5219	-	-	-	-
0.2724	2650	0.4623	-	-	-	-
0.2775	2700	0.5232	-	-	-	-
0.2827	2750	0.5867	-	-	-	-
0.2878	2800	0.5514	-	-	-	-
0.2929	2850	0.5288	-	-	-	-
0.2981	2900	0.5069	-	-	-	-
0.3032	2950	0.5761	-	-	-	-
0.3084	3000	0.525	-	-	-	-
0.3135	3050	0.5664	-	-	-	-
0.3186	3100	0.6317	-	-	-	-
0.3238	3150	0.5479	-	-	-	-
0.3289	3200	0.553	-	-	-	-
0.3341	3250	0.4752	-	-	-	-
0.3392	3300	0.5127	-	-	-	-
0.3443	3350	0.5699	-	-	-	-
0.3495	3400	0.5394	-	-	-	-
0.3546	3450	0.507	-	-	-	-
0.3597	3500	0.5938	-	-	-	-
0.3649	3550	0.539	-	-	-	-
0.3700	3600	0.525	-	-	-	-
0.3752	3650	0.4864	-	-	-	-
0.3803	3700	0.5308	-	-	-	-
0.3854	3750	0.4859	-	-	-	-
0.3906	3800	0.513	-	-	-	-
0.3957	3850	0.5332	-	-	-	-
0	0	-	-	0.9121	-	-
0.4000	3892	-	4.7785	-	-	-
0.4009	3900	0.474	-	-	-	-
0.4060	3950	0.458	-	-	-	-
0.4111	4000	0.5066	-	-	-	-
0.4163	4050	0.5217	-	-	-	-
0.4214	4100	0.5381	-	-	-	-
0.4266	4150	0.4994	-	-	-	-
0.4317	4200	0.508	-	-	-	-
0.4368	4250	0.4696	-	-	-	-
0.4420	4300	0.5563	-	-	-	-
0.4471	4350	0.4831	-	-	-	-
0.4523	4400	0.4532	-	-	-	-
0.4574	4450	0.5056	-	-	-	-
0.4625	4500	0.5409	-	-	-	-
0.4677	4550	0.5122	-	-	-	-
0.4728	4600	0.4593	-	-	-	-
0.4780	4650	0.5206	-	-	-	-
0.4831	4700	0.4803	-	-	-	-
0.4882	4750	0.478	-	-	-	-
0.4934	4800	0.5563	-	-	-	-
0.4985	4850	0.5191	-	-	-	-
0.5036	4900	0.4981	-	-	-	-
0.5088	4950	0.5075	-	-	-	-
0.5139	5000	0.5035	-	-	-	-
0.5191	5050	0.4375	-	-	-	-
0.5242	5100	0.515	-	-	-	-
0.5293	5150	0.4386	-	-	-	-
0.5345	5200	0.4757	-	-	-	-
0.5396	5250	0.4715	-	-	-	-
0.5448	5300	0.452	-	-	-	-
0.5499	5350	0.4789	-	-	-	-
0.5550	5400	0.4839	-	-	-	-
0.5602	5450	0.472	-	-	-	-
0.5653	5500	0.4779	-	-	-	-
0.5705	5550	0.4804	-	-	-	-
0.5756	5600	0.4778	-	-	-	-
0.5807	5650	0.4542	-	-	-	-
0.5859	5700	0.5099	-	-	-	-
0.5910	5750	0.5326	-	-	-	-
0.5962	5800	0.4859	-	-	-	-
0	0	-	-	0.9162	-	-
0.6001	5838	-	4.7525	-	-	-
0.6013	5850	0.4558	-	-	-	-
0.6064	5900	0.4429	-	-	-	-
0.6116	5950	0.4862	-	-	-	-
0.6167	6000	0.453	-	-	-	-
0.6219	6050	0.4795	-	-	-	-
0.6270	6100	0.4835	-	-	-	-
0.6321	6150	0.4517	-	-	-	-
0.6373	6200	0.4654	-	-	-	-
0.6424	6250	0.4076	-	-	-	-
0.6475	6300	0.4213	-	-	-	-
0.6527	6350	0.5258	-	-	-	-
0.6578	6400	0.4392	-	-	-	-
0.6630	6450	0.467	-	-	-	-
0.6681	6500	0.4382	-	-	-	-
0.6732	6550	0.4254	-	-	-	-
0.6784	6600	0.4647	-	-	-	-
0.6835	6650	0.4333	-	-	-	-
0.6887	6700	0.5067	-	-	-	-
0.6938	6750	0.4584	-	-	-	-
0.6989	6800	0.4843	-	-	-	-
0.7041	6850	0.441	-	-	-	-
0.7092	6900	0.4461	-	-	-	-
0.7144	6950	0.5262	-	-	-	-
0.7195	7000	0.463	-	-	-	-
0.7246	7050	0.4917	-	-	-	-
0.7298	7100	0.4288	-	-	-	-
0.7349	7150	0.4572	-	-	-	-
0.7401	7200	0.523	-	-	-	-
0.7452	7250	0.4868	-	-	-	-
0.7503	7300	0.4292	-	-	-	-
0.7555	7350	0.3998	-	-	-	-
0.7606	7400	0.4515	-	-	-	-
0.7658	7450	0.5028	-	-	-	-
0.7709	7500	0.4417	-	-	-	-
0.7760	7550	0.4908	-	-	-	-
0.7812	7600	0.4344	-	-	-	-
0.7863	7650	0.4956	-	-	-	-
0.7914	7700	0.3898	-	-	-	-
0.7966	7750	0.4512	-	-	-	-
0	0	-	-	0.9214	-	-
0.8001	7784	-	4.7145	-	-	-
0.8017	7800	0.5104	-	-	-	-
0.8069	7850	0.4543	-	-	-	-
0.8120	7900	0.4041	-	-	-	-
0.8171	7950	0.472	-	-	-	-
0.8223	8000	0.4535	-	-	-	-
0.8274	8050	0.4412	-	-	-	-
0.8326	8100	0.4776	-	-	-	-
0.8377	8150	0.3992	-	-	-	-
0.8428	8200	0.4332	-	-	-	-
0.8480	8250	0.4767	-	-	-	-
0.8531	8300	0.453	-	-	-	-
0.8583	8350	0.4321	-	-	-	-
0.8634	8400	0.4654	-	-	-	-
0.8685	8450	0.3688	-	-	-	-
0.8737	8500	0.4515	-	-	-	-
0.8788	8550	0.4693	-	-	-	-
0.8840	8600	0.404	-	-	-	-
0.8891	8650	0.5471	-	-	-	-
0.8942	8700	0.5301	-	-	-	-
0.8994	8750	0.4714	-	-	-	-
0.9045	8800	0.4863	-	-	-	-
0.9097	8850	0.4712	-	-	-	-
0.9148	8900	0.4446	-	-	-	-
0.9199	8950	0.41	-	-	-	-
0.9251	9000	0.4175	-	-	-	-
0.9302	9050	0.4678	-	-	-	-
0.9353	9100	0.4308	-	-	-	-
0.9405	9150	0.4532	-	-	-	-
0.9456	9200	0.4643	-	-	-	-
0.9508	9250	0.4197	-	-	-	-
0.9559	9300	0.4488	-	-	-	-
0.9610	9350	0.5365	-	-	-	-
0.9662	9400	0.475	-	-	-	-
0.9713	9450	0.438	-	-	-	-
0.9765	9500	0.3648	-	-	-	-
0.9816	9550	0.4277	-	-	-	-
0.9867	9600	0.4721	-	-	-	-
0.9919	9650	0.4603	-	-	-	-
0.9970	9700	0.3954	-	-	-	-
0	0	-	-	0.9214	0.8700	0.9475

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.8
• Sentence Transformers: 3.4.1
• Transformers: 4.48.1
• PyTorch: 2.6.0+cu124
• Accelerate: 1.3.0
• 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",
}