dfisher-sentence-transformer-fine-tuned

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2 <!-- at revision 8b3219a92973c328a8e22fadcfa821b5dc75636a -->
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 tokens
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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})
  (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("danicafisher/dfisher-sentence-transformer-fine-tuned")
# Run inference
sentences = [
    'What methods are suggested for recording and integrating structured feedback about content provenance from various stakeholders in the context of GAI systems?',
    "39 \nMS-3.3-004 \nProvide input for training materials about the capabilities and limitations of GAI \nsystems related to digital content transparency for AI Actors, other \nprofessionals, and the public about the societal impacts of AI and the role of \ndiverse and inclusive content generation. \nHuman-AI Configuration; \nInformation Integrity; Harmful Bias \nand Homogenization \nMS-3.3-005 \nRecord and integrate structured feedback about content provenance from \noperators, users, and potentially impacted communities through the use of \nmethods such as user research studies, focus groups, or community forums. \nActively seek feedback on generated content quality and potential biases. \nAssess the general awareness among end users and impacted communities \nabout the availability of these feedback channels. \nHuman-AI Configuration; \nInformation Integrity; Harmful Bias \nand Homogenization \nAI Actor Tasks: AI Deployment, Affected Individuals and Communities, End-Users, Operation and Monitoring, TEVV \n \nMEASURE 4.2: Measurement results regarding AI system trustworthiness in deployment context(s) and across the AI lifecycle are \ninformed by input from domain experts and relevant AI Actors to validate whether the system is performing consistently as \nintended. Results are documented. \nAction ID \nSuggested Action \nGAI Risks \nMS-4.2-001 \nConduct adversarial testing at a regular cadence to map and measure GAI risks, \nincluding tests to address attempts to deceive or manipulate the application of \nprovenance techniques or other misuses. Identify vulnerabilities and \nunderstand potential misuse scenarios and unintended outputs. \nInformation Integrity; Information \nSecurity \nMS-4.2-002 \nEvaluate GAI system performance in real-world scenarios to observe its \nbehavior in practical environments and reveal issues that might not surface in \ncontrolled and optimized testing environments. \nHuman-AI Configuration; \nConfabulation; Information \nSecurity \nMS-4.2-003 \nImplement interpretability and explainability methods to evaluate GAI system \ndecisions and verify alignment with intended purpose. \nInformation Integrity; Harmful Bias \nand Homogenization \nMS-4.2-004 \nMonitor and document instances where human operators or other systems \noverride the GAI's decisions. Evaluate these cases to understand if the overrides \nare linked to issues related to content provenance. \nInformation Integrity \nMS-4.2-005 \nVerify and document the incorporation of results of structured public feedback \nexercises into design, implementation, deployment approval (“go”/“no-go” \ndecisions), monitoring, and decommission decisions. \nHuman-AI Configuration; \nInformation Security \nAI Actor Tasks: AI Deployment, Domain Experts, End-Users, Operation and Monitoring, TEVV",
    '46 \nMG-4.3-003 \nReport GAI incidents in compliance with legal and regulatory requirements (e.g., \nHIPAA breach reporting, e.g., OCR (2023) or NHTSA (2022) autonomous vehicle \ncrash reporting requirements. \nInformation Security; Data Privacy \nAI Actor Tasks: AI Deployment, Affected Individuals and Communities, Domain Experts, End-Users, Human Factors, Operation and \nMonitoring',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# 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.* --> <!-- ## 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: 274 training samples
• Columns: <code>sentence_0</code> and <code>sentence_1</code>
• Approximate statistics based on the first 274 samples:

  	sentence_0	sentence_1
  type	string	string
  details	<ul><li>min: 12 tokens</li><li>mean: 22.67 tokens</li><li>max: 38 tokens</li></ul>	<ul><li>min: 21 tokens</li><li>mean: 245.27 tokens</li><li>max: 256 tokens</li></ul>

• Samples:

  sentence_0	sentence_1
  <code>How does the Executive Order on Advancing Racial Equity define 'equity' and 'underserved communities'?</code>	<code>ENDNOTES<br>47. Darshali A. Vyas et al., Hidden in Plain Sight – Reconsidering the Use of Race Correction in Clinical<br>Algorithms, 383 N. Engl. J. Med.874, 876-78 (Aug. 27, 2020), https://www.nejm.org/doi/full/10.1056/<br>NEJMms2004740.<br>48. The definitions of 'equity' and 'underserved communities' can be found in the Definitions section of<br>this framework as well as in Section 2 of The Executive Order On Advancing Racial Equity and Support<br>for Underserved Communities Through the Federal Government. https://www.whitehouse.gov/<br>briefing-room/presidential-actions/2021/01/20/executive-order-advancing-racial-equity-and-support­<br>for-underserved-communities-through-the-federal-government/<br>49. Id.<br>50. Various organizations have offered proposals for how such assessments might be designed. See, e.g.,<br>Emanuel Moss, Elizabeth Anne Watkins, Ranjit Singh, Madeleine Clare Elish, and Jacob Metcalf.<br>Assembling Accountability: Algorithmic Impact Assessment for the Public Interest. Data & Society<br>Research Institute Report. June 29, 2021. https://datasociety.net/library/assembling-accountability­<br>algorithmic-impact-assessment-for-the-public-interest/; Nicol Turner Lee, Paul Resnick, and Genie<br>Barton. Algorithmic bias detection and mitigation: Best practices and policies to reduce consumer harms.<br>Brookings Report. May 22, 2019.<br>https://www.brookings.edu/research/algorithmic-bias-detection-and-mitigation-best-practices-and­<br>policies-to-reduce-consumer-harms/; Andrew D. Selbst. An Institutional View Of Algorithmic Impact<br>Assessments. Harvard Journal of Law & Technology. June 15, 2021. https://ssrn.com/abstract=3867634;<br>Dillon Reisman, Jason Schultz, Kate Crawford, and Meredith Whittaker. Algorithmic Impact<br>Assessments: A Practical Framework for Public Agency Accountability. AI Now Institute Report. April<br>2018. https://ainowinstitute.org/aiareport2018.pdf<br>51. Department of Justice. Justice Department Announces New Initiative to Combat Redlining. Oct. 22,<br>2021. https://www.justice.gov/opa/pr/justice-department-announces-new-initiative-combat-redlining<br>52. PAVE Interagency Task Force on Property Appraisal and Valuation Equity. Action Plan to Advance<br>Property Appraisal and Valuation Equity: Closing the Racial Wealth Gap by Addressing Mis-valuations for<br>Families and Communities of Color. March 2022. https://pave.hud.gov/sites/pave.hud.gov/files/<br>documents/PAVEActionPlan.pdf<br>53. U.S. Equal Employment Opportunity Commission. The Americans with Disabilities Act and the Use of<br>Software, Algorithms, and Artificial Intelligence to Assess Job Applicants and Employees. EEOC­<br>NVTA-2022-2. May 12, 2022. https://www.eeoc.gov/laws/guidance/americans-disabilities-act-and-use­<br>software-algorithms-and-artificial-intelligence; U.S. Department of Justice. Algorithms, Artificial<br>Intelligence, and Disability Discrimination in Hiring. May 12, 2022. https://beta.ada.gov/resources/ai­<br>guidance/<br>54. Ziad Obermeyer, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. Dissecting racial bias in<br>an algorithm used to manage the health of populations. Science. Vol. 366, No. 6464. Oct. 25, 2019. https://<br>www.science.org/doi/10.1126/science.aax2342<br>55. Data & Trust Alliance. Algorithmic Bias Safeguards for Workforce: Overview. Jan. 2022. https://<br>dataandtrustalliance.org/Algorithmic_Bias_Safeguards_for_Workforce_Overview.pdf<br>56. Section 508.gov. IT Accessibility Laws and Policies. Access Board. https://www.section508.gov/<br>manage/laws-and-policies/<br>67</code>
  <code>What are the key expectations for automated systems as outlined in the context?</code>	<code>HUMAN ALTERNATIVES, <br>CONSIDERATION, AND <br>FALLBACK <br>WHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS<br>The expectations for automated systems are meant to serve as a blueprint for the development of additional <br>technical standards and practices that are tailored for particular sectors and contexts. <br>Equitable. Consideration should be given to ensuring outcomes of the fallback and escalation system are <br>equitable when compared to those of the automated system and such that the fallback and escalation <br>system provides equitable access to underserved communities.105 <br>Timely. Human consideration and fallback are only useful if they are conducted and concluded in a <br>timely manner. The determination of what is timely should be made relative to the specific automated <br>system, and the review system should be staffed and regularly assessed to ensure it is providing timely <br>consideration and fallback. In time-critical systems, this mechanism should be immediately available or, <br>where possible, available before the harm occurs. Time-critical systems include, but are not limited to, <br>voting-related systems, automated building access and other access systems, systems that form a critical <br>component of healthcare, and systems that have the ability to withhold wages or otherwise cause <br>immediate financial penalties. <br>Effective. The organizational structure surrounding processes for consideration and fallback should <br>be designed so that if the human decision-maker charged with reassessing a decision determines that it <br>should be overruled, the new decision will be effectively enacted. This includes ensuring that the new <br>decision is entered into the automated system throughout its components, any previous repercussions from <br>the old decision are also overturned, and safeguards are put in place to help ensure that future decisions do <br>not result in the same errors. <br>Maintained. The human consideration and fallback process and any associated automated processes <br>should be maintained and supported as long as the relevant automated system continues to be in use. <br>Institute training, assessment, and oversight to combat automation bias and ensure any <br>human-based components of a system are effective. <br>Training and assessment. Anyone administering, interacting with, or interpreting the outputs of an auto­<br>mated system should receive training in that system, including how to properly interpret outputs of a system <br>in light of its intended purpose and in how to mitigate the effects of automation bias. The training should reoc­<br>cur regularly to ensure it is up to date with the system and to ensure the system is used appropriately. Assess­<br>ment should be ongoing to ensure that the use of the system with human involvement provides for appropri­<br>ate results, i.e., that the involvement of people does not invalidate the system's assessment as safe and effective <br>or lead to algorithmic discrimination. <br>Oversight. Human-based systems have the potential for bias, including automation bias, as well as other <br>concerns that may limit their effectiveness. The results of assessments of the efficacy and potential bias of <br>such human-based systems should be overseen by governance structures that have the potential to update the <br>operation of the human-based system in order to mitigate these effects. <br>50</code>
  <code>What is the focus of the report titled "Assembling Accountability: Algorithmic Impact Assessment for the Public Interest" by Emanuel Moss and others?</code>	<code>ENDNOTES<br>47. Darshali A. Vyas et al., Hidden in Plain Sight – Reconsidering the Use of Race Correction in Clinical<br>Algorithms, 383 N. Engl. J. Med.874, 876-78 (Aug. 27, 2020), https://www.nejm.org/doi/full/10.1056/<br>NEJMms2004740.<br>48. The definitions of 'equity' and 'underserved communities' can be found in the Definitions section of<br>this framework as well as in Section 2 of The Executive Order On Advancing Racial Equity and Support<br>for Underserved Communities Through the Federal Government. https://www.whitehouse.gov/<br>briefing-room/presidential-actions/2021/01/20/executive-order-advancing-racial-equity-and-support­<br>for-underserved-communities-through-the-federal-government/<br>49. Id.<br>50. Various organizations have offered proposals for how such assessments might be designed. See, e.g.,<br>Emanuel Moss, Elizabeth Anne Watkins, Ranjit Singh, Madeleine Clare Elish, and Jacob Metcalf.<br>Assembling Accountability: Algorithmic Impact Assessment for the Public Interest. Data & Society<br>Research Institute Report. June 29, 2021. https://datasociety.net/library/assembling-accountability­<br>algorithmic-impact-assessment-for-the-public-interest/; Nicol Turner Lee, Paul Resnick, and Genie<br>Barton. Algorithmic bias detection and mitigation: Best practices and policies to reduce consumer harms.<br>Brookings Report. May 22, 2019.<br>https://www.brookings.edu/research/algorithmic-bias-detection-and-mitigation-best-practices-and­<br>policies-to-reduce-consumer-harms/; Andrew D. Selbst. An Institutional View Of Algorithmic Impact<br>Assessments. Harvard Journal of Law & Technology. June 15, 2021. https://ssrn.com/abstract=3867634;<br>Dillon Reisman, Jason Schultz, Kate Crawford, and Meredith Whittaker. Algorithmic Impact<br>Assessments: A Practical Framework for Public Agency Accountability. AI Now Institute Report. April<br>2018. https://ainowinstitute.org/aiareport2018.pdf<br>51. Department of Justice. Justice Department Announces New Initiative to Combat Redlining. Oct. 22,<br>2021. https://www.justice.gov/opa/pr/justice-department-announces-new-initiative-combat-redlining<br>52. PAVE Interagency Task Force on Property Appraisal and Valuation Equity. Action Plan to Advance<br>Property Appraisal and Valuation Equity: Closing the Racial Wealth Gap by Addressing Mis-valuations for<br>Families and Communities of Color. March 2022. https://pave.hud.gov/sites/pave.hud.gov/files/<br>documents/PAVEActionPlan.pdf<br>53. U.S. Equal Employment Opportunity Commission. The Americans with Disabilities Act and the Use of<br>Software, Algorithms, and Artificial Intelligence to Assess Job Applicants and Employees. EEOC­<br>NVTA-2022-2. May 12, 2022. https://www.eeoc.gov/laws/guidance/americans-disabilities-act-and-use­<br>software-algorithms-and-artificial-intelligence; U.S. Department of Justice. Algorithms, Artificial<br>Intelligence, and Disability Discrimination in Hiring. May 12, 2022. https://beta.ada.gov/resources/ai­<br>guidance/<br>54. Ziad Obermeyer, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. Dissecting racial bias in<br>an algorithm used to manage the health of populations. Science. Vol. 366, No. 6464. Oct. 25, 2019. https://<br>www.science.org/doi/10.1126/science.aax2342<br>55. Data & Trust Alliance. Algorithmic Bias Safeguards for Workforce: Overview. Jan. 2022. https://<br>dataandtrustalliance.org/Algorithmic_Bias_Safeguards_for_Workforce_Overview.pdf<br>56. Section 508.gov. IT Accessibility Laws and Policies. Access Board. https://www.section508.gov/<br>manage/laws-and-policies/<br>67</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

<details><summary>Click to expand</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 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: 3
• 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: 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
• eval_on_start: False
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

</details>

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.4.1
• Accelerate: 0.34.2
• Datasets: 3.0.0
• 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",
}

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}
}

<!-- ## 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.* -->