LamaDiab/NewMiniLM-V15Data-128BATCH-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/NewMiniLM-V15Data-128BATCH-SemanticEngine")
# Run inference
sentences = [
    'parker ingenuity ct black lacquer so959210',
    ' pen',
    'lagu-family barber shop toy',
]
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,  0.2524, -0.0132],
#         [ 0.2524,  1.0000,  0.1220],
#         [-0.0132,  0.1220,  1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9601

Training Details

Training Dataset

Unnamed Dataset

• Size: 704,308 training samples
• Columns: anchor, positive, and itemCategory
• Approximate statistics based on the first 1000 samples:

  	anchor	positive	itemCategory
  type	string	string	string
  details	min: 3 tokens mean: 8.06 tokens max: 41 tokens	min: 3 tokens mean: 5.35 tokens max: 97 tokens	min: 3 tokens mean: 3.93 tokens max: 9 tokens

• Samples:

  anchor	positive	itemCategory
  rilastil sunlaude comfort dye fluid spf50 50 ml	spf50 sunscreen	sunscreen
  lemon and powder leather slippers	genuine cow leather	slipper
  erastapex trio	erastapex trio olmesartan medoxomil	blood disorder medicine

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

  	anchor	positive	negative	itemCategory
  type	string	string	string	string
  details	min: 3 tokens mean: 9.63 tokens max: 43 tokens	min: 3 tokens mean: 6.17 tokens max: 150 tokens	min: 3 tokens mean: 9.79 tokens max: 41 tokens	min: 3 tokens mean: 3.88 tokens max: 10 tokens

• Samples:

  anchor	positive	negative	itemCategory
  pilot mechanical pencil progrex h-127 - 0.7 mm	0.7 mm pencil	tracing sketch a3 70 gr 50 sheets	pencil
  superior drawing marker -pen - set of 12 colors - 2 nib	marker pen set	wunder chocolate strawberry ganache & coulis	marker
  first person singular author: haruki murakami	haruki murakami book	dark hot chocolate sugar free	literature and fiction

• 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: 128
• per_device_eval_batch_size: 128
• weight_decay: 0.001
• num_train_epochs: 5
• warmup_ratio: 0.2
• fp16: True
• dataloader_num_workers: 1
• dataloader_prefetch_factor: 2
• dataloader_persistent_workers: True
• push_to_hub: True
• hub_model_id: LamaDiab/NewMiniLM-V15Data-128BATCH-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: 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: 5e-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: 0.2
• 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/NewMiniLM-V15Data-128BATCH-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
0.0002	1	3.1229	-	-
0.1817	1000	2.6857	1.6310	0.9441
0.3634	2000	2.0541	1.5448	0.9472
0.5452	3000	1.7335	1.5236	0.9485
0.7269	4000	1.2495	1.5552	0.9433
0.9086	5000	0.813	1.5794	0.9472
1.0903	6000	1.0512	1.4544	0.9567
1.2720	7000	1.2912	1.4492	0.9563
1.4538	8000	1.1994	1.4519	0.9568
1.6355	9000	1.0662	1.4635	0.9545
1.8172	10000	0.6724	1.5717	0.9454
1.9989	11000	0.4761	1.5509	0.9503
2.1806	12000	1.0468	1.4510	0.9591
2.3623	13000	0.9871	1.4625	0.9608
2.5441	14000	0.9596	1.4531	0.9606
2.7258	15000	0.7272	1.4685	0.9589
2.9075	16000	0.4716	1.5063	0.9549
3.0892	17000	0.6495	1.4401	0.9626
3.2709	18000	0.8911	1.4418	0.9642
3.4527	19000	0.871	1.4658	0.9635
3.6344	20000	0.8008	1.4879	0.9594
3.8161	21000	0.5084	1.4949	0.9579
3.9978	22000	0.3552	1.5567	0.9568
4.1795	23000	0.8254	1.4609	0.9651
4.3613	24000	0.8164	1.4704	0.9641
4.5430	25000	0.8078	1.4598	0.9635
4.7247	26000	0.6181	1.4891	0.9602
4.9064	27000	0.3932	1.4990	0.9601

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",
}