metadata

base_model: Snowflake/snowflake-arctic-embed-m
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:600
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      How does the Blueprint for an AI Bill of Rights aim to protect the rights
      of the American public?
    sentences:
      - >-
        and use prohibitions. You and your communities should be free from
        unchecked surveillance; surveillance 

        technologies should be subject to heightened oversight that includes at
        least pre-deployment assessment of their 

        potential harms and scope limits to protect privacy and civil liberties.
        Continuous surveillance and monitoring
      - >-
        steps to move these principles into practice and promote common
        approaches that allow technological 

        innovation to flourish while protecting people from harm. 

        9
      - >-
        ABOUT THIS FRAMEWORK

        The Blueprint for an AI Bill of Rights is a set of five principles and
        associated practices to help guide the 

        design, use, and deployment of automated systems to protect the rights
        of the American public in the age of 

        artificial intel-ligence. Developed through extensive consultation with
        the American public, these principles are
  - source_sentence: >-
      How can organizations monitor the impact of proxy features on algorithmic
      discrimination?
    sentences:
      - >-
        sociodemographic variables that adjust or “correct” the algorithm’s
        output on the basis of a patient’s race or

        ethnicity, which can lead to race-based health inequities.47

        25

        Algorithmic 

        Discrimination 

        Protections
      - >-
        proxy; if needed, it may be possible to identify alternative attributes
        that can be used instead. At a minimum, 

        organizations should ensure a proxy feature is not given undue weight
        and should monitor the system closely 

        for any resulting algorithmic discrimination.   

        26

        Algorithmic 

        Discrimination 

        Protections
      - |-
        velopment, and deployment of automated systems, and from the 
        compounded harm of its reuse. Independent evaluation and report
        ing that confirms that the system is safe and effective, including re
        porting of steps taken to mitigate potential harms, should be per
        formed and the results made public whenever possible. 
        15
  - source_sentence: >-
      What measures can be taken to ensure that AI systems are designed to be
      accessible for people with disabilities?
    sentences:
      - >-
        potential for meaningful impact on people’s rights, opportunities, or
        access and include those to impacted 

        communities that may not be direct users of the automated system, risks
        resulting from purposeful misuse of 

        the system, and other concerns identified via the consultation process.
        Assessment and, where possible, mea
      - >-
        and as a lifecycle minimum performance standard. Decision possibilities
        resulting from performance testing 

        should include the possibility of not deploying the system. 

        Risk identification and mitigation. Before deployment, and in a
        proactive and ongoing manner, poten

        tial risks of the automated system should be identified and mitigated.
        Identified risks should focus on the
      - >-
        individuals 

        and 

        communities 

        from algorithmic 

        discrimination and to use and design systems in an equitable way. This
        protection should include proactive 

        equity assessments as part of the system design, use of representative
        data and protection against proxies 

        for demographic features, ensuring accessibility for people with
        disabilities in design and development,
  - source_sentence: >-
      How should organizations address concerns raised during public
      consultations regarding AI data processing and interpretation?  
    sentences:
      - >-
        and testing and evaluation of AI technologies and systems. It is
        expected to be released in the winter of 2022-23. 

        21
      - >-
        provide guidance whenever automated systems can meaningfully impact the
        public’s rights, opportunities, 

        or access to critical needs. 

        3
      - >-
        learning models or for other purposes, including how data sources were
        processed and interpreted, a 

        summary of what data might be missing, incomplete, or erroneous, and
        data relevancy justifications; the 

        results of public consultation such as concerns raised and any decisions
        made due to these concerns; risk
  - source_sentence: >-
      What role do ethical considerations play in the development and
      implementation of automated systems?
    sentences:
      - >-
        tial to meaningfully impact rights, opportunities, or access.
        Additionally, this framework does not analyze or 

        take a position on legislative and regulatory proposals in municipal,
        state, and federal government, or those in 

        other countries. 

        We have seen modest progress in recent years, with some state and local
        governments responding to these prob
      - >-
        •

        Searches for “Black girls,” “Asian girls,” or “Latina girls” return
        predominantly39 sexualized content, rather

        than role models, toys, or activities.40 Some search engines have been
        working to reduce the prevalence of

        these results, but the problem remains.41

        •

        Advertisement delivery systems that predict who is most likely to click
        on a job advertisement end up deliv-
      - >-
        particularly relevant to automated systems, without articulating a
        specific set of FIPPs or scoping 

        applicability or the interests served to a single particular domain,
        like privacy, civil rights and civil liberties, 

        ethics, or risk management. The Technical Companion builds on this prior
        work to provide practical next
model-index:
  - name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.83
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.96
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.98
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.99
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.83
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.31999999999999995
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19599999999999995
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09899999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.83
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.96
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.98
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.99
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9195971547817925
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.8960000000000001
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8966666666666666
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.83
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.96
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.98
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.99
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.83
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.31999999999999995
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.19599999999999995
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09899999999999999
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.83
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.96
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.98
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.99
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9195971547817925
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.8960000000000001
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.8966666666666666
            name: Dot Map@100

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

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-m. 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: Snowflake/snowflake-arctic-embed-m
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity

Model Sources

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

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 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("niting089/finetuned_arctic")
# Run inference
sentences = [
    'What role do ethical considerations play in the development and implementation of automated systems?',
    'particularly relevant to automated systems, without articulating a specific set of FIPPs or scoping \napplicability or the interests served to a single particular domain, like privacy, civil rights and civil liberties, \nethics, or risk management. The Technical Companion builds on this prior work to provide practical next',
    '•\nSearches for “Black girls,” “Asian girls,” or “Latina girls” return predominantly39 sexualized content, rather\nthan role models, toys, or activities.40 Some search engines have been working to reduce the prevalence of\nthese results, but the problem remains.41\n•\nAdvertisement delivery systems that predict who is most likely to click on a job advertisement end up deliv-',
]
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

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.83
cosine_accuracy@3	0.96
cosine_accuracy@5	0.98
cosine_accuracy@10	0.99
cosine_precision@1	0.83
cosine_precision@3	0.32
cosine_precision@5	0.196
cosine_precision@10	0.099
cosine_recall@1	0.83
cosine_recall@3	0.96
cosine_recall@5	0.98
cosine_recall@10	0.99
cosine_ndcg@10	0.9196
cosine_mrr@10	0.896
cosine_map@100	0.8967
dot_accuracy@1	0.83
dot_accuracy@3	0.96
dot_accuracy@5	0.98
dot_accuracy@10	0.99
dot_precision@1	0.83
dot_precision@3	0.32
dot_precision@5	0.196
dot_precision@10	0.099
dot_recall@1	0.83
dot_recall@3	0.96
dot_recall@5	0.98
dot_recall@10	0.99
dot_ndcg@10	0.9196
dot_mrr@10	0.896
dot_map@100	0.8967

Training Details

Training Dataset

Unnamed Dataset

Size: 600 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 600 samples:
sentence_0 sentence_1
type string string
details
min: 11 tokens
mean: 19.86 tokens
max: 36 tokens

min: 16 tokens
mean: 60.47 tokens
max: 94 tokens

	sentence_0	sentence_1
type	string	string
details	min: 11 tokens mean: 19.86 tokens max: 36 tokens	min: 16 tokens mean: 60.47 tokens max: 94 tokens

Samples:

sentence_0	sentence_1
`What are the key principles outlined in the AI Bill of Rights aimed at ensuring automated systems benefit the American people?`	`BLUEPRINT FOR AN AI BILL OF RIGHTS MAKING AUTOMATED SYSTEMS WORK FOR THE AMERICAN PEOPLE OCTOBER 2022`
`How does the AI Bill of Rights address potential ethical concerns related to automated decision-making systems?`	`BLUEPRINT FOR AN AI BILL OF RIGHTS MAKING AUTOMATED SYSTEMS WORK FOR THE AMERICAN PEOPLE OCTOBER 2022`
`What is the purpose of the Blueprint for an AI Bill of Rights as outlined by the White House Office of Science and Technology Policy?`	`About this Document The Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People was published by the White House Office of Science and Technology Policy in October 2022. This framework was released one year after OSTP announced the launch of a process to develop “a bill of rights for an AI-powered`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 20
per_device_eval_batch_size: 20
num_train_epochs: 5
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 20
per_device_eval_batch_size: 20
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: 5
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

Training Logs

Epoch	Step	cosine_map@100
1.0	30	0.8731
1.6667	50	0.89
2.0	60	0.895
3.0	90	0.8959
3.3333	100	0.8967

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.1.1
Transformers: 4.44.2
PyTorch: 2.4.1+cu121
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",
}

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}
}