metadata

base_model: Alibaba-NLP/gte-large-en-v1.5
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:500
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      narrow identified goals, to avoid "mission creep."  Anticipated data
      collection should be determined to be 

      strictly necessary to the identified goals and should be minimized as much
      as possible. Data collected based on 

      these identified goals and for a specific context should not be used in a
      different context without assessing for 

      new privacy risks and implementing appropriate mitigation measures, which
      may include express consent.
    sentences:
      - >-
        What measures should be taken if data collected for specific identified
        goals is to be used in a different context?
      - >-
        What measures should be taken to ensure the privacy of sensitive data
        and limit access to it?
      - >-
        What special requirements are mentioned in the white paper regarding
        national security and defense activities in relation to trustworthy
        artificial intelligence?
  - source_sentence: >-
      •

      Karen Levy, Assistant Professor, Department of Information Science,
      Cornell University

      •

      Natasha Duarte, Project Director, Upturn

      •

      Elana Zeide, Assistant Professor, University of Nebraska College of Law

      •

      Fabian Rogers, Constituent Advocate, Office of NY State Senator Jabari
      Brisport and Community

      Advocate and Floor Captain, Atlantic Plaza Towers Tenants Association

      The individual panelists described the ways in which AI systems and other
      technologies are increasingly being
    sentences:
      - >-
        What are some of the challenges posed to democracy by the use of
        technology and automated systems, as mentioned in the foreword?
      - >-
        What principles has the U.S. Intelligence Community developed to guide
        personnel in the ethical use of AI?
      - >-
        What roles do the panelists hold in relation to the discussion on AI
        systems and technology?
  - source_sentence: |-
      impacts disfavoring people based on their race, color, ethnicity, 
      sex 
      (including 
      pregnancy, 
      childbirth, 
      and 
      related 
      medical 
      conditions, 
      gender 
      identity, 
      intersex 
      status, 
      and 
      sexual 
      orientation), religion, age, national origin, disability, veteran status,
    sentences:
      - >-
        What does the term "HUMAN ALTERNATIVES" refer to in the context
        provided?
      - What types of discrimination are mentioned in the context?
      - >-
        What are the expectations for automated systems in relation to public
        protection from surveillance?
  - source_sentence: >-
      establish and maintain the capabilities that will allow individuals to use
      their own automated systems to help 

      them make consent, access, and control decisions in a complex data
      ecosystem. Capabilities include machine 

      readable data, standardized data formats, metadata or tags for expressing
      data processing permissions and 

      preferences and data provenance and lineage, context of use and
      access-specific tags, and training models for 

      assessing privacy risk.
    sentences:
      - >-
        What measures should be taken to ensure that independent evaluations of
        algorithmic discrimination are conducted while balancing individual
        privacy and data access needs?
      - >-
        What capabilities are necessary for individuals to effectively manage
        consent and control decisions in a complex data ecosystem?
      - >-
        What are some examples of classifications that are protected by law
        against discrimination?
  - source_sentence: >-
      SAFE AND EFFECTIVE 

      SYSTEMS 

      WHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS

      The expectations for automated systems are meant to serve as a blueprint
      for the development of additional 

      technical standards and practices that are tailored for particular sectors
      and contexts. 

      Derived data sources tracked and reviewed carefully. Data that is derived
      from other data through
    sentences:
      - >-
        What is the purpose of the expectations set for automated systems in
        relation to technical standards and practices?
      - >-
        What factors influence the appropriate application of the principles
        outlined in the white paper regarding automated systems?
      - >-
        What actions can a court take if a federal agency fails to comply with
        the Privacy Act regarding an individual's records?
model-index:
  - name: SentenceTransformer based on Alibaba-NLP/gte-large-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.88
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.9866666666666667
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9866666666666667
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.88
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3288888888888888
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1973333333333333
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09999999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.88
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.9866666666666667
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9866666666666667
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9499978881111136
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9330158730158731
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9330158730158731
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.88
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.9866666666666667
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.9866666666666667
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 1
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.88
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.3288888888888888
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.1973333333333333
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09999999999999998
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.88
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.9866666666666667
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.9866666666666667
            name: Dot Recall@5
          - type: dot_recall@10
            value: 1
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.9499978881111136
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.9330158730158731
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.9330158730158731
            name: Dot Map@100

SentenceTransformer based on Alibaba-NLP/gte-large-en-v1.5

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-large-en-v1.5 on the json dataset. It maps sentences & paragraphs to a 1024-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: Alibaba-NLP/gte-large-en-v1.5
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- json

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': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)

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("sentence_transformers_model_id")
# Run inference
sentences = [
    'SAFE AND EFFECTIVE \nSYSTEMS \nWHAT SHOULD BE EXPECTED OF AUTOMATED SYSTEMS\nThe expectations for automated systems are meant to serve as a blueprint for the development of additional \ntechnical standards and practices that are tailored for particular sectors and contexts. \nDerived data sources tracked and reviewed carefully. Data that is derived from other data through',
    'What is the purpose of the expectations set for automated systems in relation to technical standards and practices?',
    'What factors influence the appropriate application of the principles outlined in the white paper regarding automated systems?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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	0.88
cosine_accuracy@3	0.9867
cosine_accuracy@5	0.9867
cosine_accuracy@10	1.0
cosine_precision@1	0.88
cosine_precision@3	0.3289
cosine_precision@5	0.1973
cosine_precision@10	0.1
cosine_recall@1	0.88
cosine_recall@3	0.9867
cosine_recall@5	0.9867
cosine_recall@10	1.0
cosine_ndcg@10	0.95
cosine_mrr@10	0.933
cosine_map@100	0.933
dot_accuracy@1	0.88
dot_accuracy@3	0.9867
dot_accuracy@5	0.9867
dot_accuracy@10	1.0
dot_precision@1	0.88
dot_precision@3	0.3289
dot_precision@5	0.1973
dot_precision@10	0.1
dot_recall@1	0.88
dot_recall@3	0.9867
dot_recall@5	0.9867
dot_recall@10	1.0
dot_ndcg@10	0.95
dot_mrr@10	0.933
dot_map@100	0.933

Training Details

Training Dataset

json

Dataset: json
Size: 500 training samples
Columns: anchor and positive
Approximate statistics based on the first 500 samples:
anchor positive
type string string
details
min: 12 tokens
mean: 21.76 tokens
max: 37 tokens

min: 11 tokens
mean: 78.92 tokens
max: 104 tokens

	anchor	positive
type	string	string
details	min: 12 tokens mean: 21.76 tokens max: 37 tokens	min: 11 tokens mean: 78.92 tokens max: 104 tokens

Samples:

anchor	positive
`What is the primary purpose of the AI Bill of Rights outlined in the October 2022 blueprint?`	`BLUEPRINT FOR AN AI BILL OF RIGHTS MAKING AUTOMATED SYSTEMS WORK FOR THE AMERICAN PEOPLE OCTOBER 2022`
`What was the purpose of the Blueprint for an AI Bill of Rights published 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`
`What initiative did the OSTP announce a year prior to the release of the framework for a bill of rights for an AI-powered world?`	`released one year after OSTP announced the launch of a process to develop “a bill of rights for an AI-powered world.” Its release follows a year of public engagement to inform this initiative. The framework is available online at: https://www.whitehouse.gov/ostp/ai-bill-of-rights About the Office of Science and Technology Policy The Office of Science and Technology Policy (OSTP) was established by the National Science and Technology`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        1024,
        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
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 5
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: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 5
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
eval_on_start: False
eval_use_gather_object: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	cosine_map@100
1.0	1	0.9022
2.0	2	0.9311
3.0	3	0.9397
4.0	4	0.9330
5.0	5	0.9330

The bold row denotes the saved checkpoint.

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: 3.0.1
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}
}