MugheesAwan11/bge-base-securiti-dataset-1-v11

SentenceTransformer based on BAAI/bge-base-en-v1.5

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 tokens
• 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("MugheesAwan11/bge-base-securiti-dataset-1-v11")
# Run inference
sentences = [
    "View GCP View Azure View Oracle View US California CCPA View US California CPRA View European Union GDPR View Thailand’s PDPA View China PIPL View Canada PIPEDA View Brazil's LGPD View \\+ More View Privacy View Security View Governance View Marketing View Resources Blog View Collateral View Knowledge Center View Securiti Education View Company About Us View Partner Program View Contact Us View News Coverage View Press Releases View Careers View Events Spotlight Talks IDC Names Securiti a Worldwide Leader in Data Privacy View Events Spotlight Talks Education Contact Us Schedule a Demo Products By Use Cases By Roles Data Command Center View Learn more Asset and Data Discovery Discover dark and native data assets Learn more Data Access Intelligence & Governance Identify which users have access to sensitive data and prevent unauthorized access Learn more Data Privacy Automation PrivacyCenter.Cloud | Data Mapping | DSR Automation | Assessment Automation | Vendor Assessment | Breach Management | Privacy Notice Learn more Sensitive Data Intelligence Discover & Classify Structured and Unstructured Data | People Data Graph Learn more Data Flow Intelligence & Governance Prevent sensitive data sprawl through real-time streaming platforms Learn more Data Consent Automation First Party Consent | Third Party & Cookie Consent Learn more Data Security Posture Management Secure sensitive data in hybrid multicloud and SaaS environments Learn more Data Breach Impact Analysis & Response Analyze impact of a data breach and coordinate response per global regulatory obligations Learn more Data Catalog Automatically catalog datasets and enable users to find, understand, trust and access data Learn more Data Lineage ,  GCP View Azure View Oracle View US California CCPA View US California CPRA View European Union GDPR View Thailand’s PDPA View China PIPL View Canada PIPEDA View Brazil's LGPD View \\+ More View Privacy View Security View Governance View Marketing View Resources Blog View Collateral View Knowledge Center View Securiti Education View Company About Us View Partner Program View Contact Us View News Coverage View Press Releases View Careers View Events Spotlight Talks IDC Names Securiti a Worldwide Leader in Data Privacy View Events Spotlight Talks Education Contact Us Schedule a Demo Products By Use Cases By Roles Data Command Center View Learn more Asset and Data Discovery Discover dark and native data assets Learn more Data Access Intelligence & Governance Identify which users have access to sensitive data and prevent unauthorized access Learn more Data Privacy Automation PrivacyCenter.Cloud | Data Mapping | DSR Automation | Assessment Automation | Vendor Assessment | Breach Management | Privacy Notice Learn more Sensitive Data Intelligence Discover & Classify Structured and Unstructured Data | People Data Graph Learn more Data Flow Intelligence & Governance Prevent sensitive data sprawl through real-time streaming platforms Learn more Data Consent Automation First Party Consent | Third Party & Cookie Consent Learn more Data Security Posture Management Secure sensitive data in hybrid multicloud and SaaS environments Learn more Data Breach Impact Analysis & Response Analyze impact of a data breach and coordinate response per global regulatory obligations Learn more Data Catalog Automatically catalog datasets and enable users to find, understand, trust and access data Learn more Data Lineage Track changes",
    'What products and solutions does Oracle offer for data privacy and security, and how do they comply with regulations in different regions and countries?',
    'What are the key provisions and changes in the Personal Data Protection Bill 2021 in India, and how can Securiti assist with compliance?',
]
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

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1
cosine_accuracy@3	0.36
cosine_accuracy@5	0.52
cosine_accuracy@10	0.75
cosine_precision@1	0.1
cosine_precision@3	0.12
cosine_precision@5	0.104
cosine_precision@10	0.075
cosine_recall@1	0.1
cosine_recall@3	0.36
cosine_recall@5	0.52
cosine_recall@10	0.75
cosine_ndcg@10	0.3853
cosine_mrr@10	0.2732
cosine_map@100	0.2814

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.09
cosine_accuracy@3	0.37
cosine_accuracy@5	0.51
cosine_accuracy@10	0.74
cosine_precision@1	0.09
cosine_precision@3	0.1233
cosine_precision@5	0.102
cosine_precision@10	0.074
cosine_recall@1	0.09
cosine_recall@3	0.37
cosine_recall@5	0.51
cosine_recall@10	0.74
cosine_ndcg@10	0.3758
cosine_mrr@10	0.2635
cosine_map@100	0.2725

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.1
cosine_accuracy@3	0.35
cosine_accuracy@5	0.47
cosine_accuracy@10	0.72
cosine_precision@1	0.1
cosine_precision@3	0.1167
cosine_precision@5	0.094
cosine_precision@10	0.072
cosine_recall@1	0.1
cosine_recall@3	0.35
cosine_recall@5	0.47
cosine_recall@10	0.72
cosine_ndcg@10	0.37
cosine_mrr@10	0.2625
cosine_map@100	0.2733

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.07
cosine_accuracy@3	0.33
cosine_accuracy@5	0.48
cosine_accuracy@10	0.71
cosine_precision@1	0.07
cosine_precision@3	0.11
cosine_precision@5	0.096
cosine_precision@10	0.071
cosine_recall@1	0.07
cosine_recall@3	0.33
cosine_recall@5	0.48
cosine_recall@10	0.71
cosine_ndcg@10	0.3526
cosine_mrr@10	0.2425
cosine_map@100	0.2532

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.06
cosine_accuracy@3	0.32
cosine_accuracy@5	0.46
cosine_accuracy@10	0.68
cosine_precision@1	0.06
cosine_precision@3	0.1067
cosine_precision@5	0.092
cosine_precision@10	0.068
cosine_recall@1	0.06
cosine_recall@3	0.32
cosine_recall@5	0.46
cosine_recall@10	0.68
cosine_ndcg@10	0.3393
cosine_mrr@10	0.2341
cosine_map@100	0.2451

Training Details

Training Dataset

Unnamed Dataset

• Size: 900 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 159 tokens mean: 444.92 tokens max: 512 tokens	min: 7 tokens mean: 21.97 tokens max: 82 tokens

• Samples:

  positive	anchor
  Consent	Third Party & Cookie Consent Learn more Data Security Posture Management Secure sensitive data in hybrid multicloud and SaaS environments Learn more Data Breach Impact Analysis & Response Analyze impact of a data breach and coordinate response per global regulatory obligations Learn more Data Catalog Automatically catalog datasets and enable users to find, understand, trust and access data Learn more Data Lineage Track changes and transformations of data throughout its lifecycle Data Controls Orchestrator View Data Command Center View Sensitive Data Intelligence View Asset Discovery Data Discovery & Classification Sensitive Data Catalog People Data Graph Learn more Privacy Automate compliance with global privacy regulations Data Mapping Automation View Data Subject Request Automation View People Data Graph View Assessment Automation View Cookie Consent View Universal Consent View Vendor Risk Assessment View Breach Management View Privacy Policy Management View Privacy Center View Learn more Security Identify data risk and enable protection & control Data Security Posture Management View Data Access Intelligence & Governance View Data Risk Management View Data Breach Analysis View Learn more Governance Optimize Data Governance with granular insights into your data Data Catalog View Data Lineage View Data Quality View Data Controls Orchestrator View Solutions Technologies Covering you everywhere with 1000+ integrations across data systems. Snowflake View AWS View Microsoft 365 View Salesforce View Workday View GCP View Azure View Oracle View Learn more Regulations Automate compliance with global privacy regulations. US California CCPA View US California CPRA View European Union GDPR View Thailand’s PDPA View China PIPL View Canada, Consent
  PA View China PIPL View Canada PIPEDA View Brazil's LGPD View + More View Privacy View Security View Governance View Marketing View Resources Blog View Collateral View Knowledge Center View Securiti Education View Company About Us View Partner Program View Contact Us View News Coverage View Press Releases View Careers View Events Spotlight Talks IDC Names Securiti a Worldwide Leader in Data Privacy View Events Spotlight Talks Education Contact Us Schedule a Demo Products By Use Cases By Roles Data Command Center View Learn more Asset and Data Discovery Discover dark and native data assets Learn more Data Access Intelligence & Governance Identify which users have access to sensitive data and prevent unauthorized access Learn more Data Privacy Automation PrivacyCenter.Cloud	Data Mapping
  MoTC is responsible for the enforcement of the DPL. . 4 The MoTC can also impose fines of up to QAR 5 million (US$1.4 million) for violations of certain provisions of the DPL. 5 There is currently no obligation for organizations in Qatar to appoint a data protection officer under the DPL. ### Forrester Names Securiti a Leader in the Privacy Management Wave Q4, 2021 Read the Report ### Securiti named a Leader in the IDC MarketScape for Data Privacy Compliance Software Read the Report At Securiti, our mission is to enable enterprises to safely harness the incredible power of data and the cloud by controlling the complex security, privacy and compliance risks. Copyright (C) 2023 Securiti Sitemap XML Sitemap #### Newsletter #### Company About Us Careers Contact Us Partner Program News Coverage Press Releases #### Resources Blog Collateral Knowledge Center Securiti Education Privacy Center Free Do Not Sell Tool What is DSPM #### Terms Terms & Policies Security & Compliance Manage cookie preferences My Privacy Center #### Get in touch email protected 300 Santana Row Suite 450. San Jose, CA 95128 Contact Us Schedule a Demo Products By Role Data Command Center Sensitive Data Intelligence Privacy Security Governance Data Controls Orchestrator By Use Cases Back Asset Discovery Asset Discovery Data Discovery & Classification Data Discovery & Classification Sensitive Data Catalog Sensitive Data Catalog People Data Graph People Data Graph Data Mapping Automation View Data Subject Request Automation View People Data Graph View Assessment Automation View Cookie Consent View Universal Consent View Vendor Risk Assessment View Breach Management View Privacy Policy Management View Privacy Center View Data Security Posture Management View Data Access Intelligence & Governance View Data Risk Management , . 5 Infringement of the provisions of the DPA may be penalized by not more than KES 5 million or 1% of the previous fiscal year’s annual turnover. ### Forrester Names Securiti a Leader in the Privacy Management Wave Q4, 2021 Read the Report ### Securiti named a Leader in the IDC MarketScape for Data Privacy Compliance Software Read the Report At Securiti, our mission is to enable enterprises to safely harness the incredible power of data and the cloud by controlling the complex security, privacy and compliance risks. Copyright (C) 2023 Securiti Sitemap XML Sitemap #### Newsletter #### Company About Us Careers Contact Us Partner Program News Coverage Press Releases #### Resources Blog Collateral Knowledge Center Securiti Education Privacy Center Free Do Not Sell Tool What is DSPM #### Terms Terms & Policies Security & Compliance Manage cookie preferences My Privacy Center #### Get in touch email protected 300 Santana Row Suite 450. San Jose, CA 95128 Contact Us Schedule a Demo Products By Role Data Command Center Sensitive Data Intelligence Privacy Security Governance Data Controls Orchestrator By Use Cases Back Asset Discovery Asset Discovery Data Discovery & Classification Data Discovery & Classification Sensitive Data Catalog Sensitive Data Catalog People Data Graph People Data Graph Data Mapping Automation View Data Subject Request Automation View People Data Graph View Assessment Automation View Cookie Consent View Universal Consent View Vendor Risk Assessment View Breach Management View Privacy Policy Management View Privacy Center View Data Security Posture Management View Data Access Intelligence & Governance View Data Risk Management View Data Breach Analysis View Data Catalog View Data Lineage View Data Quality View	What does Securiti aim to achieve in terms of data security, privacy, and compliance risks?

• 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: 32
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 10
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• bf16: True
• tf32: 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: 32
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_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: 10
• 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: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: True
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_128_cosine_map@100	dim_256_cosine_map@100	dim_512_cosine_map@100	dim_64_cosine_map@100	dim_768_cosine_map@100
0.3448	10	9.0172	-	-	-	-	-
0.6897	20	7.8791	-	-	-	-	-
1.0	29	-	0.2696	0.2535	0.2642	0.2317	0.2805
1.0345	30	6.1959	-	-	-	-	-
1.3793	40	5.1573	-	-	-	-	-
1.7241	50	3.9165	-	-	-	-	-
2.0	58	-	0.2545	0.2678	0.2693	0.2320	0.2609
2.0690	60	3.6232	-	-	-	-	-
2.4138	70	3.0077	-	-	-	-	-
2.7586	80	2.951	-	-	-	-	-
3.0	87	-	0.2663	0.2909	0.2663	0.2438	0.2677
3.1034	90	2.3699	-	-	-	-	-
3.4483	100	2.404	-	-	-	-	-
3.7931	110	1.818	-	-	-	-	-
4.0	116	-	0.2752	0.279	0.2888	0.2447	0.2938
4.1379	120	1.4625	-	-	-	-	-
4.4828	130	1.9295	-	-	-	-	-
4.8276	140	1.5043	-	-	-	-	-
5.0	145	-	0.2633	0.2684	0.2771	0.2442	0.2841
5.1724	150	1.0966	-	-	-	-	-
5.5172	160	1.3741	-	-	-	-	-
5.8621	170	1.132	-	-	-	-	-
6.0	174	-	0.2635	0.2649	0.2861	0.2399	0.2760
6.2069	180	0.8199	-	-	-	-	-
6.5517	190	1.0209	-	-	-	-	-
6.8966	200	1.0516	-	-	-	-	-
7.0	203	-	0.2619	0.2738	0.2654	0.2474	0.2770
7.2414	210	0.7749	-	-	-	-	-
7.5862	220	1.0583	-	-	-	-	-
7.9310	230	0.832	-	-	-	-	-
8.0	232	-	0.2652	0.2739	0.2675	0.2441	0.2725
8.2759	240	0.7005	-	-	-	-	-
8.6207	250	0.8967	-	-	-	-	-
8.9655	260	0.8263	-	-	-	-	-
9.0	261	-	0.2609	0.2682	0.2656	0.2401	0.2817
9.3103	270	0.6493	-	-	-	-	-
9.6552	280	0.7889	-	-	-	-	-
10.0	290	0.7407	0.2532	0.2733	0.2725	0.2451	0.2814

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.14
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Accelerate: 0.31.0
• Datasets: 2.19.1
• Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

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}
}