Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,724 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:882
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 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 Asset and Data Discovery View Data Access Intelligence & Governance View
+    Data Privacy Automation View
+  sentences:
+  - How does coordinating a response in managing a data breach and meeting global
+    regulatory obligations help automate compliance with global privacy regulations?
+  - What law replaced Law No. 1682/2001 in Paraguay's data protection regulations
+    and what are the restrictions on publicizing sensitive data under it?
+  - What are the different components or tools related to Data Discovery & Classification?
+- source_sentence: 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 AW,  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 AW
+  sentences:
+  - What can the data principal do if the data fiduciary disagrees with their request
+    for correction, completion, update, or erasure, and how does cross-border data
+    transfer factor in?
+  - What is the purpose of the Vendor Risk Assessment for data security and governance?
+  - How can privacy automation help in complying with global privacy regulations?
+- source_sentence: 'of 2021 is the British Virgin Island’s main data protection law
+    on par with the EU and UK standards. Learn more ### Jamaica The Data Protection
+    Act No. 7 of 2020 is Jamaica’s data protection regulation, enforced by the Office
+    of the Information Commissioner. Learn more ### Ukraine The Law on Personal Data
+    Protection is Ukraine’s main data protection law, making it one of the few such
+    regulations that precede the GDPR in Europe. Learn more ### Uzbekistan Uzbekistan
+    has several regulations that govern different aspects of data protection within
+    the country. Learn more about : Law on Personal Data Bill to Improve the Legal
+    Framework for Personal Data Draft Law on Advertising Law on Cybersecurity (No.
+    RK 764) ### Monaco Act No. 1.165 on the Protection of Personal Data regulates
+    personal data protection-related matters in the Principality of Monaco'
+  sentences:
+  - What are the conditions for parental consent under PIPL and the requirements for
+    privacy notices?
+  - What does the Knowledge Center provide information on in relation to security?
+  - Which European country has a data protection law that predates the GDPR and is
+    enforced by the Information Commissioner's Office?
+- source_sentence: Data Lineage View Data Quality View Asset and Data Discovery View
+    Data Access Intelligence & Governance View Data Privacy Automation View Sensitive
+    Data Intelligence View Data Flow Intelligence & Governance View Data Consent Automation
+    View Data Security Posture Management View Data Breach Impact Analysis & Response
+    View Data Catalog View Data Lineage View Solutions Technologies Regulations Roles
+    Back Snowflake View AWS View Microsoft 365 View Salesforce View Workday View GCP
+    View Azure View Oracle View US California CCPA View US California CPRA View
+  sentences:
+  - What is the role of data privacy automation in ensuring data protection and compliance?
+  - What risks does data security and the cloud help control for enterprises to safely
+    harness their power?
+  - What is the term for the right to delete personal data upon request, also known
+    as 'the right to be forgotten', and what are the other data protection rights
+    under GDPR?
+- source_sentence: Consent of an individual is valid if it is reasonable to expect
+    that an individual to whom the organization’s activities are directed would understand
+    the nature, purpose, and consequences of the collection, use, or disclosure of
+    the personal information to which they are consenting. The information must be
+    provided in manageable and easily accessible ways to data subjects and data subjects
+    must be allowed to withdraw consent. If there is a use or disclosure a data subject
+    would not reasonably expect to be occurring, such as certain sharing of information
+    with a third party or the tracking of location, express consent would likely be
+    required. However, the data subject’s consent may not be required for certain
+    data processing activities such as when the collection is “clearly” in the interests
+    of the individual and consent cannot be obtained in a timely way, data is being
+    collected in the course of employment, journalistic, is already publicly available,
+    information is being collected for the detection and prevention of fraud or for
+  sentences:
+  - How should information be provided to data subjects in manageable and easily accessible
+    ways?
+  - What are the obligations and requirements for businesses under China's Personal
+    Information Protection Law?
+  - Which state, following California, Virginia, and Colorado, recently passed privacy
+    legislation like the VCDPA?
+model-index:
+- name: SentenceTransformer based on BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.4020618556701031
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5567010309278351
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6804123711340206
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7525773195876289
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.4020618556701031
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1855670103092783
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1360824742268041
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07525773195876287
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.4020618556701031
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5567010309278351
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6804123711340206
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7525773195876289
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5649836192344125
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5059687448862709
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5167362215588647
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.3917525773195876
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5876288659793815
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6288659793814433
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7525773195876289
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.3917525773195876
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19587628865979378
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.12577319587628866
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07525773195876287
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.3917525773195876
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5876288659793815
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6288659793814433
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7525773195876289
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5625195371806965
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5031173294059894
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5141611082081141
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.38144329896907214
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5773195876288659
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6391752577319587
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.711340206185567
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.38144329896907214
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.1924398625429553
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.12783505154639174
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07113402061855668
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.38144329896907214
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5773195876288659
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6391752577319587
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.711340206185567
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5460935382949205
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.49311078383243345
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5067772343986099
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/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](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### 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:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("MugheesAwan11/bge-base-securiti-dataset-1-v19")
+# Run inference
+sentences = [
+    'Consent of an individual is valid if it is reasonable to expect that an individual to whom the organization’s activities are directed would understand the nature, purpose, and consequences of the collection, use, or disclosure of the personal information to which they are consenting. The information must be provided in manageable and easily accessible ways to data subjects and data subjects must be allowed to withdraw consent. If there is a use or disclosure a data subject would not reasonably expect to be occurring, such as certain sharing of information with a third party or the tracking of location, express consent would likely be required. However, the data subject’s consent may not be required for certain data processing activities such as when the collection is “clearly” in the interests of the individual and consent cannot be obtained in a timely way, data is being collected in the course of employment, journalistic, is already publicly available, information is being collected for the detection and prevention of fraud or for',
+    'How should information be provided to data subjects in manageable and easily accessible ways?',
+    'Which state, following California, Virginia, and Colorado, recently passed privacy legislation like the VCDPA?',
+]
+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]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.4021     |
+| cosine_accuracy@3   | 0.5567     |
+| cosine_accuracy@5   | 0.6804     |
+| cosine_accuracy@10  | 0.7526     |
+| cosine_precision@1  | 0.4021     |
+| cosine_precision@3  | 0.1856     |
+| cosine_precision@5  | 0.1361     |
+| cosine_precision@10 | 0.0753     |
+| cosine_recall@1     | 0.4021     |
+| cosine_recall@3     | 0.5567     |
+| cosine_recall@5     | 0.6804     |
+| cosine_recall@10    | 0.7526     |
+| cosine_ndcg@10      | 0.565      |
+| cosine_mrr@10       | 0.506      |
+| **cosine_map@100**  | **0.5167** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.3918     |
+| cosine_accuracy@3   | 0.5876     |
+| cosine_accuracy@5   | 0.6289     |
+| cosine_accuracy@10  | 0.7526     |
+| cosine_precision@1  | 0.3918     |
+| cosine_precision@3  | 0.1959     |
+| cosine_precision@5  | 0.1258     |
+| cosine_precision@10 | 0.0753     |
+| cosine_recall@1     | 0.3918     |
+| cosine_recall@3     | 0.5876     |
+| cosine_recall@5     | 0.6289     |
+| cosine_recall@10    | 0.7526     |
+| cosine_ndcg@10      | 0.5625     |
+| cosine_mrr@10       | 0.5031     |
+| **cosine_map@100**  | **0.5142** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.3814     |
+| cosine_accuracy@3   | 0.5773     |
+| cosine_accuracy@5   | 0.6392     |
+| cosine_accuracy@10  | 0.7113     |
+| cosine_precision@1  | 0.3814     |
+| cosine_precision@3  | 0.1924     |
+| cosine_precision@5  | 0.1278     |
+| cosine_precision@10 | 0.0711     |
+| cosine_recall@1     | 0.3814     |
+| cosine_recall@3     | 0.5773     |
+| cosine_recall@5     | 0.6392     |
+| cosine_recall@10    | 0.7113     |
+| cosine_ndcg@10      | 0.5461     |
+| cosine_mrr@10       | 0.4931     |
+| **cosine_map@100**  | **0.5068** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 882 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                             | anchor                                                                              |
+  |:--------|:-------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                              |
+  | details | <ul><li>min: 18 tokens</li><li>mean: 227.32 tokens</li><li>max: 414 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 21.98 tokens</li><li>max: 102 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | anchor                                                                                                    |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------|
+  | <code>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</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | <code>What is the purpose of the Data Command Center?</code>                                              |
+  | <code>data subject must be notified of any such extension within one month of receiving the request, along with the reasons for the delay and the possibility of complaining to the supervisory authority. The right to restrict processing applies when the data subject contests data accuracy, the processing is unlawful, and the data subject opposes erasure and requests restriction. The controller must inform data subjects before any such restriction is lifted. Under GDPR, the data subject also has the right to obtain from the controller the rectification of inaccurate personal data and to have incomplete personal data completed. Article: 22 Under PDPL, if a decision is based solely on automated processing of personal data intended to assess the data subject regarding his/her performance at work, financial standing, credit-worthiness, reliability, or conduct, then the data subject has the right to request processing in a manner that is not solely automated. This right shall not apply where the decision is taken in the course of entering into</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | <code>What is the requirement for notifying the data subject of any extension under GDPR and PDPL?</code> |
+  | <code>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 and transformations of,  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 and transformations of data throughout its</code> | <code>What is the purpose of Third Party & Cookie Consent in data automation and security?</code>         |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256
+      ],
+      "matryoshka_weights": [
+          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`: 4
+- `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
+<details><summary>Click to expand</summary>
+
+- `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`: 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`: 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
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_768_cosine_map@100 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|
+| 0.3571  | 10     | 4.0517        | -                      | -                      | -                      |
+| 0.7143  | 20     | 2.5778        | -                      | -                      | -                      |
+| 1.0     | 28     | -             | 0.5304                 | 0.5224                 | 0.5234                 |
+| 1.0714  | 30     | 2.1161        | -                      | -                      | -                      |
+| 1.4286  | 40     | 1.5394        | -                      | -                      | -                      |
+| 1.7857  | 50     | 1.5162        | -                      | -                      | -                      |
+| **2.0** | **56** | **-**         | **0.5412**             | **0.5382**             | **0.5185**             |
+| 2.1429  | 60     | 1.202         | -                      | -                      | -                      |
+| 2.5     | 70     | 1.0456        | -                      | -                      | -                      |
+| 2.8571  | 80     | 1.1341        | -                      | -                      | -                      |
+| 3.0     | 84     | -             | 0.5340                 | 0.5554                 | 0.5498                 |
+| 3.2143  | 90     | 0.8724        | -                      | -                      | -                      |
+| 3.5714  | 100    | 0.932         | -                      | -                      | -                      |
+| 3.9286  | 110    | 0.9548        | -                      | -                      | -                      |
+| 4.0     | 112    | -             | 0.5296                 | 0.5487                 | 0.5491                 |
+| 0.3571  | 10     | 0.9958        | -                      | -                      | -                      |
+| 0.7143  | 20     | 0.8264        | -                      | -                      | -                      |
+| 1.0     | 28     | -             | 0.5155                 | 0.5250                 | 0.5269                 |
+| 1.0714  | 30     | 0.7969        | -                      | -                      | -                      |
+| 1.4286  | 40     | 0.6244        | -                      | -                      | -                      |
+| 1.7857  | 50     | 0.6368        | -                      | -                      | -                      |
+| **2.0** | **56** | **-**         | **0.5034**             | **0.5314**             | **0.5233**             |
+| 2.1429  | 60     | 0.4748        | -                      | -                      | -                      |
+| 2.5     | 70     | 0.4037        | -                      | -                      | -                      |
+| 2.8571  | 80     | 0.4615        | -                      | -                      | -                      |
+| 3.0     | 84     | -             | 0.5079                 | 0.5145                 | 0.5155                 |
+| 3.2143  | 90     | 0.3148        | -                      | -                      | -                      |
+| 3.5714  | 100    | 0.4142        | -                      | -                      | -                      |
+| 3.9286  | 110    | 0.366         | -                      | -                      | -                      |
+| 4.0     | 112    | -             | 0.5068                 | 0.5142                 | 0.5167                 |
+
+* 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
+```bibtex
+@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
+```bibtex
+@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
+```bibtex
+@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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f692b9720727a3a39313a250b99b34dca67676edae52b988f4626a4d224f5c59
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}