LamaDiab/MiniLM-v28-SemanticEngine

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-v28-SemanticEngine")
# Run inference
sentences = [
    'xbase 100 kids swimming goggles -  clear lenses - blue / yellow',
    'blue and yellow swimming goggles',
    'snuggs wearable blanket monk red christmas deer',
]
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,  0.7468,  0.0225],
#         [ 0.7468,  1.0000, -0.0354],
#         [ 0.0225, -0.0354,  1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9803

Training Details

Training Dataset

Unnamed Dataset

• Size: 798,551 training samples
• Columns: anchor, positive, itemCategory, shoppingCategory, and shoppingCategory_normalized
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	itemCategory	shoppingCategory	shoppingCategory_normalized
  type	string	string	string	string	string
  details	min: 3 tokens mean: 11.21 tokens max: 93 tokens	min: 3 tokens mean: 5.92 tokens max: 32 tokens	min: 3 tokens mean: 3.94 tokens max: 9 tokens	min: 3 tokens mean: 3.38 tokens max: 5 tokens	min: 3 tokens mean: 4.47 tokens max: 5 tokens

• Samples:

  anchor	positive	itemCategory	shoppingCategory	shoppingCategory_normalized
  sky blue dotted t-chemise	t-shirt sky dotted	top	fashion	fashion
  coffee - set of scented candles	pleasant aroma candle	candle	home and garden	home_garden
  nasturtium passion fruit chocolate	chocolate	sweet	restaurants	food_dining

• 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, negative, itemCategory, shoppingCategory, and shoppingCategory_normalized
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	negative	itemCategory	shoppingCategory	shoppingCategory_normalized
  type	string	string	string	string	string	string
  details	min: 3 tokens mean: 9.63 tokens max: 43 tokens	min: 3 tokens mean: 6.52 tokens max: 150 tokens	min: 3 tokens mean: 9.5 tokens max: 33 tokens	min: 3 tokens mean: 3.86 tokens max: 9 tokens	min: 3 tokens mean: 3.36 tokens max: 5 tokens	min: 3 tokens mean: 4.44 tokens max: 5 tokens

• Samples:

  anchor	positive	negative	itemCategory	shoppingCategory	shoppingCategory_normalized
  pilot mechanical pencil progrex h-127 - 0.7 mm	0.7 mm pencil	rush tip marker set, 6 pastel colors, carton box, black edition no. 116453	pencil	stationary	office_school
  superior drawing marker -pen - set of 12 colors - 2 nib	marker pen set	palestine scarf notebook (spirals)	marker	stationary	office_school
  first person singular author: haruki murakami	haruki murakami book	chocolate flakes mocha	literature and fiction	entertainment	sports_entertainment

• 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: 3e-05
• weight_decay: 0.001
• warmup_ratio: 0.1
• fp16: True
• dataloader_num_workers: 1
• dataloader_prefetch_factor: 2
• dataloader_persistent_workers: True
• push_to_hub: True
• hub_model_id: LamaDiab/MiniLM-v28-SemanticEngine
• hub_strategy: all_checkpoints

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: 3e-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: 3
• 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: 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-v28-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: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	cosine_accuracy
0.0003	1	2.1128	-	-
0.3205	1000	1.6035	0.7383	0.9653
0.6410	2000	1.0575	0.6787	0.9737
0.9615	3000	1.8049	0.6591	0.9739
1.2819	4000	1.2967	0.6036	0.9779
1.6022	5000	1.1471	0.5827	0.9798
1.9225	6000	1.0816	0.5906	0.9800
2.2428	7000	1.0567	0.5924	0.9795
2.5631	8000	1.0046	0.5827	0.9803
2.8834	9000	1.0313	0.5850	0.9803

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",
}