all-MiniLM-L6-v37-pair_score

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2 on the pairs_with_scores_v31 dataset. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • pairs_with_scores_v31
• Language: en
• License: apache-2.0

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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'cinnamon apple dessert',
    'looking through the window oversized hoodie last piece, fashion casual wear top sweatshirt, women hoodie winter hoodie cotton hoodie evil eye hoodie oversized hoodie hoodie looking through the window hoodie, hoodie looking through the window hoodie oversized hoodie, gender women design kaf generic hoodie looking through the window m - l features reflective sleeve style long fit oversized cotton black evil eye season winter, model wears medium oversizedi m protected. i m safe. i m secured. evil eye. 100 cotton model wears medium oversized weight 55 height 162',
    '100 men s 1.5 mm neoprene shorty surfing wetsuit - navy blue, surfing shorty suit surfing suit for warm water surfing shorty suit for bodyboarding surfing suit water sports wetsuit, wetsuit, gender men decathlon generic wetsuit xs cut shorty neoprene navy blue activity surfing numeric 1.5 mm target group men sport surfing fashion style shorty, our team has developed a wetsuit that s particularly suited to summer surfing and bodyboarding in waters warmer than 21 c. a surfing shorty wetsuit that s particularly suited to discovering the gliding experience on a surfboard or bodyboard in water warmer than 21 c.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.1591, -0.1914],
#         [-0.1591,  1.0000,  0.0767],
#         [-0.1914,  0.0767,  1.0000]])

Training Details

Training Dataset

pairs_with_scores_v31

• Dataset: pairs_with_scores_v31 at 73de461
• Size: 19,761,179 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 5.33 tokens max: 22 tokens	min: 4 tokens mean: 82.95 tokens max: 256 tokens	min: 0.0 mean: 0.05 max: 1.0

• Samples:

  sentence1	sentence2	score
  nail polish	strawberry yogurt, yogurt drink strawberry yogurt yogurt nan strawberry nan strawberry yoghurt yoghurt, strawberry yogurt yogurt nan strawberry nan strawberry yoghurt yoghurt	0.0
  racket	super sexy dress, fashion designer wear dress dress, women dress red dress dress sexy dress super sexy dress, dress sexy dress super sexy dress, gender women decollete boutique generic dress super sexy s red, red dress.	0.0
  duvet	golden chinese tweezers, golden tweezers tweezers	0.0

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Evaluation Dataset

pairs_with_scores_v31

• Dataset: pairs_with_scores_v31 at 73de461
• Size: 99,303 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 3 tokens mean: 5.37 tokens max: 21 tokens	min: 10 tokens mean: 80.08 tokens max: 256 tokens	min: 0.0 mean: 0.05 max: 1.0

• Samples:

  sentence1	sentence2	score
  uriage micellar water	uriage thermal micellar water oily skin 250 ml, micellar water micellar water oily skin thermal micellar water oily skin uriage uriage micellar water, units 250 millilitre	1.0
  bag snorkelling mask	aloe eva hair oil 100 ml aloe vera, aloe eva aloe eva hair oil aloe eva hair oil aloe vera hair oil hair oil aloe vera aloe eva hair zet aloe eva hair zet aloe vera hair zet hair zet aloe vera, units 100 millilitre	0.0
  red hair curler	complavin 75 mg/100 mg 30/f.c.tab, complavin complavin tablets, units 0.075 gram 0.1 gram	0.0

• Loss: CoSENTLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "pairwise_cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• 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: 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: 1
• max_steps: -1
• lr_scheduler_type: linear
• 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: False
• fp16: True
• 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
• hub_revision: None
• 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
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Click to expand

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.1.0
• Transformers: 4.55.4
• PyTorch: 2.6.0+cu124
• Accelerate: 1.10.1
• Datasets: 4.0.0
• Tokenizers: 0.21.4

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",
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}