README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:458830
  - loss:MultipleNegativesSymmetricRankingLoss
base_model: sentence-transformers/all-MiniLM-L6-v2
widget:
  - source_sentence: derby cap toe shoes - brown
    sentences:
      - chained strapped block heeled sandals
      - 100% premium natural leather - high quality sole.
      - puppy treats biscuits
  - source_sentence: juliette bundle
    sentences:
      - juliette body lotion
      - xiaomi 12 pro
      - reece - serving plate set
  - source_sentence: granville original one bite original rice crispy squares
    sentences:
      - ' samsung galaxy z flip case'
      - rice crispy squares dairy-free
      - nivea - rose care micellar water with organic rose water & oil - 400 ml
  - source_sentence: rosa fm farha istikana tea cup with plate set
    sentences:
      - premium rug
      - rosa fm farha
      - wall anchor bolt 1444 euro
  - source_sentence: jade life necklace
    sentences:
      - duplicate faces
      - protection necklace
      - carefree daily intimate wash
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
model-index:
  - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.9602481722831726
            name: Cosine Accuracy
          - type: cosine_accuracy
            value: 0.9310857653617859
            name: Cosine Accuracy

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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

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("LamaDiab/MiniLM-V10Data-256BATCH-SemanticEngine")
# Run inference
sentences = [
    'jade life necklace',
    'protection necklace',
    'duplicate faces',
]
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, 0.7094, 0.1424],
#         [0.7094, 1.0000, 0.1722],
#         [0.1424, 0.1722, 1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9602

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9311

Training Details

Training Dataset

Unnamed Dataset

• Size: 458,830 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 3 tokens mean: 8.01 tokens max: 119 tokens	min: 3 tokens mean: 6.27 tokens max: 66 tokens

• Samples:

  anchor	positive
  with mountain honey and lemon zest the taste of french childhood.	honey madeleines
  acetone	peach acetone
  yellow hair oil	argan hair oil

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 9,509 evaluation samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative
  type	string	string	string
  details	min: 3 tokens mean: 9.63 tokens max: 43 tokens	min: 2 tokens mean: 6.4 tokens max: 150 tokens	min: 3 tokens mean: 9.37 tokens max: 41 tokens

• Samples:

  anchor	positive	negative
  pilot mechanical pencil progrex h-127 - 0.7 mm	office supplies	hellmann's garlic mayonnaise
  superior drawing marker -pen - set of 12 colors - 2 nib	marker pen set	indian sambousak
  first person singular author: haruki murakami	english book	elle scarf

• Loss: MultipleNegativesSymmetricRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• learning_rate: 1e-05
• weight_decay: 0.001
• num_train_epochs: 5
• warmup_steps: 2867
• fp16: True
• dataloader_num_workers: 1
• dataloader_prefetch_factor: 2
• dataloader_persistent_workers: True
• push_to_hub: True
• hub_model_id: LamaDiab/MiniLM-V10Data-256BATCH-SemanticEngine
• hub_strategy: all_checkpoints
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 256
• per_device_eval_batch_size: 256
• 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: 1e-05
• weight_decay: 0.001
• 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: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0
• warmup_steps: 2867
• 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: 1
• dataloader_prefetch_factor: 2
• 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: True
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: True
• resume_from_checkpoint: None
• hub_model_id: LamaDiab/MiniLM-V10Data-256BATCH-SemanticEngine
• hub_strategy: all_checkpoints
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_accuracy
-1	-1	-	-	0.9311
0.0006	1	2.0553	-	-
0.5577	1000	-	1.0153	0.9486
1.0	1793	1.8693	-	-
1.1154	2000	-	0.9366	0.9526
1.6732	3000	-	0.9148	0.9576
2.0	3586	1.5407	-	-
2.2309	4000	-	0.9049	0.9572
2.7886	5000	-	0.8995	0.9595
3.0	5379	1.3949	-	-
3.3463	6000	-	0.8901	0.9598
3.9041	7000	-	0.8891	0.9598
4.0	7172	1.3221	-	-
4.4618	8000	-	0.8891	0.9602
5.0	8965	1.289	-	-

Framework Versions

• Python: 3.11.13
• Sentence Transformers: 5.1.2
• Transformers: 4.53.3
• PyTorch: 2.6.0+cu124
• Accelerate: 1.9.0
• Datasets: 4.4.1
• Tokenizers: 0.21.2

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",
}