chelleboyer/legal-ft-6c2775cc-995a-41a8-b19f-aadf6fe29c2a

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

This is a sentence-transformers model finetuned from Snowflake/snowflake-arctic-embed-l. 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: Snowflake/snowflake-arctic-embed-l
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 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': 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})
  (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("chelleboyer/legal-ft-6c2775cc-995a-41a8-b19f-aadf6fe29c2a")
# Run inference
sentences = [
    'What types of animals can be seen near the Wildlife Loop Road at Custer State Park?',
    "Bison, prairie dogs, elk and other creatures roam near (and often cross!) the Wildlife Loop Road at Custer State Park, about 45 miles southwest of Rapid City. But animals are just the beginning here. Scenic Needles Highway winds through the park, hiking trails beg for exploration, and even rookie campers will feel at home at the park's Blue Bell campground.\n\nA Two-Day Black Hills Getaway\n\n\n \n07\nof 25\n\n\n  Chicago  \n \n\n\n\n\n\n \n John Noltner",
    'Family Travel\n \n\n Road Rally\n \n\n View All\n \n\n\n\n\n\nDestinations\n\n\n\n\n\n\n\n\n\n\n\nDestinations\n\n\n\n Illinois\n \n\n Indiana\n \n\n Iowa\n \n\n Kansas\n \n\n Michigan\n \n\n Minnesota\n \n\n Missouri\n \n\n Nebraska\n \n\n North Dakota\n \n\n Ohio\n \n\n South Dakota\n \n\n Wisconsin\n \n\n View All\n \n\n\n\n\n\nHome + Garden\n\n\n\n\n\n\n\n\n\n\n\nHome + Garden\n\n\n\n Home\n \n\n Garden\n \n\n\n\n\n\nRecipes\n\n\n\n\n\n\n\n\n\n\n\nRecipes\n\n\n\n Dinner Ideas\n \n\n Breakfast and Brunch\n \n\n Salads and Sides\n \n\n Desserts\n \n\n Holidays\n \n\n View All\n \n\n\n\n\n Voices\n \n\n Current Issue\n \n\n About Us\n \n\n Subscribe\n \n\n\n\n\n \n\n\n\nLog In\n\n \n\n\n\n\n\nMy Account\n\n\n\n\n\n\n\n\n\n\n\nMy Account\n\n\n\n Log Out\n \n\n\n\n\n\nMagazine\n\n\n\n\n\n\n\n\n\n\n\nMagazine\n\n\n\n Subscribe\n \n\n Current Issue\n \n\n Give a Gift Subscription\n \n\n Manage Your Subscription\n \n\n\n\nNewsletters\n\n\n Sweepstakes',
]
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	0.9375
cosine_accuracy@3	0.9792
cosine_accuracy@5	0.9792
cosine_accuracy@10	1.0
cosine_precision@1	0.9375
cosine_precision@3	0.3264
cosine_precision@5	0.1958
cosine_precision@10	0.1
cosine_recall@1	0.9375
cosine_recall@3	0.9792
cosine_recall@5	0.9792
cosine_recall@10	1.0
cosine_ndcg@10	0.9653
cosine_mrr@10	0.9544
cosine_map@100	0.9544

Training Details

Training Dataset

Unnamed Dataset

• Size: 26 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 26 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 14 tokens mean: 18.73 tokens max: 27 tokens	min: 66 tokens mean: 103.62 tokens max: 159 tokens

• Samples:

  sentence_0	sentence_1
  What types of trip ideas are featured in the "25 Perfect Weekend Getaways" from Midwest Living?	25 Perfect Weekend Getaways ​ Skip to content Midwest Living Search Please fill out this field. Log In My Account Log Out Magazine Subscribe Current Issue Give a Gift Subscription Manage Your Subscription Newsletters Sweepstakes Subscribe Search Please fill out this field. Trip Ideas Trip Ideas Around the Midwest Beyond the Midwest Weekend Getaways Nature Travel State and National Parks Family Travel
  Which categories of travel does Midwest Living suggest for planning weekend getaways?	25 Perfect Weekend Getaways ​ Skip to content Midwest Living Search Please fill out this field. Log In My Account Log Out Magazine Subscribe Current Issue Give a Gift Subscription Manage Your Subscription Newsletters Sweepstakes Subscribe Search Please fill out this field. Trip Ideas Trip Ideas Around the Midwest Beyond the Midwest Weekend Getaways Nature Travel State and National Parks Family Travel
  Which states are listed under the Destinations section in the context provided?	Family Travel Road Rally View All Destinations Destinations Illinois Indiana Iowa Kansas Michigan Minnesota Missouri Nebraska North Dakota Ohio South Dakota Wisconsin View All Home + Garden Home + Garden Home Garden Recipes Recipes Dinner Ideas Breakfast and Brunch Salads and Sides Desserts Holidays View All Voices Current Issue About Us Subscribe Log In My Account My Account Log Out Magazine Magazine Subscribe Current Issue Give a Gift Subscription Manage Your Subscription Newsletters Sweepstakes

• 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}
• tp_size: 0
• 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
• 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	3	0.8195
2.0	6	0.9557
3.0	9	0.9638
4.0	12	0.9638
5.0	15	0.9638
6.0	18	0.9638
7.0	21	0.9653
8.0	24	0.9653
9.0	27	0.9653
10.0	30	0.9653

Framework Versions

• Python: 3.13.2
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.7.0+cu126
• Accelerate: 1.6.0
• Datasets: 3.5.1
• Tokenizers: 0.21.1

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}
}