gmedrano/snowflake-arctic-embed-m-finetuned

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("gmedrano/snowflake-arctic-embed-m-finetuned")
# Run inference
sentences = [
    'How does the AI Bill of Rights protect individual privacy?',
    'principles for managing information about individuals have been incorporated into data privacy laws and \npolicies across the globe.5 The Blueprint for an AI Bill of Rights embraces elements of the FIPPs that are \nparticularly 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,',
    'harmful \nuses. \nThe \nNIST \nframework \nwill \nconsider \nand \nencompass \nprinciples \nsuch \nas \ntransparency, accountability, and fairness during pre-design, design and development, deployment, use, \nand testing and evaluation of AI technologies and systems. It is expected to be released in the winter of 2022-23. \n21',
]
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

Semantic Similarity

• Dataset: val
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6585
spearman_cosine	0.7
pearson_manhattan	0.5827
spearman_manhattan	0.6
pearson_euclidean	0.6723
spearman_euclidean	0.7
pearson_dot	0.6585
spearman_dot	0.7
pearson_max	0.6723
spearman_max	0.7

Semantic Similarity

• Dataset: test
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7463
spearman_cosine	0.8
pearson_manhattan	0.7475
spearman_manhattan	0.8
pearson_euclidean	0.7592
spearman_euclidean	0.8
pearson_dot	0.7463
spearman_dot	0.8
pearson_max	0.7592
spearman_max	0.8

Training Details

Training Dataset

Unnamed Dataset

• Size: 40 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 40 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 12 tokens mean: 14.43 tokens max: 18 tokens	min: 41 tokens mean: 80.55 tokens max: 117 tokens	min: 0.53 mean: 0.61 max: 0.76

• Samples:

  sentence_0	sentence_1	label
  What should business leaders understand about AI risk management?	57 National Institute of Standards and Technology (2023) AI Risk Management Framework, Appendix B: How AI Risks Differ from Traditional Software Risks. https://airc.nist.gov/AI_RMF_Knowledge_Base/AI_RMF/Appendices/Appendix_B National Institute of Standards and Technology (2023) AI RMF Playbook. https://airc.nist.gov/AI_RMF_Knowledge_Base/Playbook National Institue of Standards and Technology (2023) Framing Risk	0.5692041097520776
  What kind of data protection measures are required under current AI regulations?	GOVERN 1.1: Legal and regulatory requirements involving AI are understood, managed, and documented. Action ID Suggested Action GAI Risks GV-1.1-001 Align GAI development and use with applicable laws and regulations, including those related to data privacy, copyright and intellectual property law. Data Privacy; Harmful Bias and Homogenization; Intellectual Property AI Actor Tasks: Governance and Oversight	0.5830958798587019
  What are the implications of AI in decision-making processes?	state of the science of AI measurement and safety today. This document focuses on risks for which there is an existing empirical evidence base at the time this profile was written; for example, speculative risks that may potentially arise in more advanced, future GAI systems are not considered. Future updates may incorporate additional risks or provide further details on the risks identified below.	0.5317174553776045

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• 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: 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

Training Logs

Epoch	Step	test_spearman_max	val_spearman_max
1.0	3	-	0.6
2.0	6	-	0.7
3.0	9	0.8000	0.7

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.2.2
• 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",
}