metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:400
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: Snowflake/snowflake-arctic-embed-m
widget:
  - source_sentence: >-
      What types of objectives are mentioned as not being specific to AI systems
      in the context?
    sentences:
      - "The notion of ‘biometric identification’ referred to in this Regulation should be defined as the automated recognition of physical, physiological and behavioural human features such as the face, eye movement, body shape, voice, prosody, gait, posture, heart rate, blood pressure, odour, keystrokes characteristics, for the purpose of establishing an individual’s identity by comparing biometric data of that individual to stored biometric data of individuals in a\_reference database, irrespective of whether the individual has given its consent or not. This excludes AI systems intended to be used for biometric verification, which includes authentication, whose sole purpose is to confirm that a\_specific natural person is the person he or she"
      - >-
        are not specific to AI systems and pursue other legitimate public
        interest objectives, should not be affected by this Regulation.
      - >-
        for supervision of the law enforcement and judicial authorities under
        this Regulation should assess whether those frameworks for cooperation
        or international agreements include adequate safeguards with respect to
        the protection of fundamental rights and freedoms of individuals.
        Recipient national authorities and Union institutions, bodies, offices
        and agencies making use of such outputs in the Union remain accountable
        to ensure their use complies with Union law. When those international
        agreements are revised or new ones are concluded in the future, the
        contracting parties should make utmost efforts to align those agreements
        with the requirements of this Regulation.
  - source_sentence: How does the context relate to the concept of 49?
    sentences:
      - (49)
      - (56)
      - (25)
  - source_sentence: >-
      How does a serious disruption of critical infrastructure relate to the
      threat to life or physical safety of individuals?
    sentences:
      - "or otherwise, for example, public roads and squares, parks, forests, playgrounds. A\_space should also be classified as being publicly accessible if, regardless of potential capacity or security restrictions, access is subject to certain predetermined conditions which can be fulfilled by an undetermined number of persons, such as the purchase of a\_ticket or title of transport, prior registration or having a\_certain age. In contrast, a\_space should not be considered to be publicly accessible if access is limited to specific and defined natural persons through either Union or national law directly related to public safety or security or through the clear manifestation of will by the person having the relevant authority over the space. The"
      - "to highly varying degrees for the practical pursuit of the localisation or identification of a\_perpetrator or suspect of the different criminal offences listed and having regard to the likely differences in the seriousness, probability and scale of the harm or possible negative consequences. An imminent threat to life or the physical safety of natural persons could also result from a\_serious disruption of critical infrastructure, as defined in Article\_2, point (4) of Directive (EU) 2022/2557 of the European Parliament and of the Council\_(19), where the disruption or destruction of such critical infrastructure would result in an imminent threat to life or the physical safety of a\_person, including through serious harm to the provision of"
      - "As regards high-risk AI systems that are safety components of products or systems, or which are themselves products or systems falling within the scope of Regulation (EC)\_No\_300/2008 of the European Parliament and of the Council\_(24), Regulation (EU)\_No\_167/2013 of the European Parliament and of the Council\_(25), Regulation (EU)\_No\_168/2013 of the European Parliament and of the Council\_(26), Directive 2014/90/EU of the European Parliament and of the Council\_(27), Directive (EU) 2016/797 of the European Parliament and of the Council\_(28), Regulation (EU) 2018/858 of the European Parliament and of the Council\_(29), Regulation (EU) 2018/1139 of the European Parliament and of the Council\_(30), and Regulation (EU)\_2019/2144 of the European"
  - source_sentence: >-
      What specific rights of children are highlighted in Article 24 of the
      Charter and the United Nations Convention on the Rights of the Child?
    sentences:
      - "it is important to highlight the fact that children have specific rights as enshrined in Article\_24 of the Charter and in the United Nations Convention on the Rights of the Child, further developed in the UNCRC General Comment No\_25 as regards the digital environment, both of which require consideration of the children’s vulnerabilities and provision of such protection and care as necessary for their well-being. The fundamental right to a\_high level of environmental protection enshrined in the Charter and implemented in Union policies should also be considered when assessing the severity of the harm that an AI system can cause, including in relation to the health and safety of persons."
      - of AI systems that are high-risk and use cases that are not.
      - "As regards high-risk AI systems that are safety components of products or systems, or which are themselves products or systems falling within the scope of Regulation (EC)\_No\_300/2008 of the European Parliament and of the Council\_(24), Regulation (EU)\_No\_167/2013 of the European Parliament and of the Council\_(25), Regulation (EU)\_No\_168/2013 of the European Parliament and of the Council\_(26), Directive 2014/90/EU of the European Parliament and of the Council\_(27), Directive (EU) 2016/797 of the European Parliament and of the Council\_(28), Regulation (EU) 2018/858 of the European Parliament and of the Council\_(29), Regulation (EU) 2018/1139 of the European Parliament and of the Council\_(30), and Regulation (EU)\_2019/2144 of the European"
  - source_sentence: What is the significance of the number 4 in the provided context?
    sentences:
      - >-
        are intended to be used solely for the purpose of enabling cybersecurity
        and personal data protection measures should not be considered to be
        high-risk AI systems.
      - (4)
      - >-
        (5)



        At the same time, depending on the circumstances regarding its specific
        application, use, and level of technological development, AI may
        generate risks and cause harm to public interests and fundamental rights
        that are protected by Union law. Such harm might be material or
        immaterial, including physical, psychological, societal or economic
        harm.













        (6)
pipeline_tag: sentence-similarity
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
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: 0.9375
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 1
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 1
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 1
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.9375
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.3333333333333333
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.19999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09999999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.9375
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 1
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 1
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 1
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.9742054063988107
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.9652777777777777
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.9652777777777778
            name: Cosine 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 dimensions
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("Mdean77/legal-ft-1")
# Run inference
sentences = [
    'What is the significance of the number 4 in the provided context?',
    '(4)',
    'are intended to be used solely for the purpose of enabling cybersecurity and personal data protection measures should not be considered to be high-risk AI systems.',
]
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	0.9375
cosine_accuracy@3	1.0
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_precision@1	0.9375
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.9375
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9742
cosine_mrr@10	0.9653
cosine_map@100	0.9653

Training Details

Training Dataset

Unnamed Dataset

Size: 400 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 400 samples:
sentence_0 sentence_1
type string string
details
min: 10 tokens
mean: 20.43 tokens
max: 35 tokens

min: 5 tokens
mean: 93.01 tokens
max: 186 tokens

	sentence_0	sentence_1
type	string	string
details	min: 10 tokens mean: 20.43 tokens max: 35 tokens	min: 5 tokens mean: 93.01 tokens max: 186 tokens

Samples:

sentence_0	sentence_1
`What is the significance of the number 50 in the given context?`	`(50)`
`How does the context relate to the concept of fifty?`	`(50)`
`What are the ethical principles mentioned in the context for developing voluntary best practices and standards?`	`encouraged to take into account, as appropriate, the ethical principles for the development of voluntary best practices and standards.`

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: 10
per_device_eval_batch_size: 10
num_train_epochs: 10
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: 10
per_device_eval_batch_size: 10
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: 10
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: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
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
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_ndcg@10
1.0	40	0.9503
1.25	50	0.9547
2.0	80	0.9742
2.5	100	0.9728
3.0	120	0.9742
3.75	150	0.9692
4.0	160	0.9769
5.0	200	0.9692
6.0	240	0.9742
6.25	250	0.9742
7.0	280	0.9665
7.5	300	0.9665
8.0	320	0.9692
8.75	350	0.9665
9.0	360	0.9665
10.0	400	0.9742

Framework Versions

Python: 3.13.0
Sentence Transformers: 3.4.1
Transformers: 4.48.3
PyTorch: 2.6.0
Accelerate: 1.3.0
Datasets: 3.2.0
Tokenizers: 0.21.0

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}
}