LamaDiab/FinetunningMiniLM-V18Data-256ConstantBATCH-SemanticEngine

SentenceTransformer based on LamaDiab/v4MiniLM-V18Data-256ConstantBATCH-SemanticEngine

This is a sentence-transformers model finetuned from LamaDiab/v4MiniLM-V18Data-256ConstantBATCH-SemanticEngine. 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: LamaDiab/v4MiniLM-V18Data-256ConstantBATCH-SemanticEngine
• 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/FinetunningMiniLM-V18Data-256ConstantBATCH-SemanticEngine")
# Run inference
sentences = [
    'italian dolce provolone',
    'experience the authentic taste of italy with our italian dolce provolone. indulge in its creamy texture, delicate flavors, and versatility in both simple and sophisticated culinary creations.',
    'trident - gum strawberry flavor - 5 per pack',
]
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, 0.8072, 0.1772],
#         [0.8072, 1.0000, 0.2218],
#         [0.1772, 0.2218, 1.0000]])

Evaluation

Metrics

Triplet

• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9706

Training Details

Training Dataset

Unnamed Dataset

• Size: 705,905 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: 13.19 tokens max: 51 tokens	min: 3 tokens mean: 4.46 tokens max: 93 tokens	min: 3 tokens mean: 3.91 tokens max: 11 tokens

• Samples:

  anchor	positive	itemCategory
  mango nos nos small	milk chocolate ganache cake	sweet
  lux soap creamy perfection 165 gm	soap	hand soap
  grey deo original	classic deodrant	women's deodorant

• 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: 2 tokens mean: 6.53 tokens max: 150 tokens	min: 3 tokens mean: 9.52 tokens max: 50 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	office supplies	scary halloween skull mask	pencil
  superior drawing marker -pen - set of 12 colors - 2 nib	superior	coloring and writing book 21 x 29.7 cm 100 gsm 18 pages number subtraction ma4014	marker
  first person singular author: haruki murakami	haruki murakami book	buried secrets	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: 256
• per_device_eval_batch_size: 256
• learning_rate: 2e-05
• weight_decay: 0.001
• num_train_epochs: 4
• 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/FinetunningMiniLM-V18Data-256ConstantBATCH-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: 2e-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: 4
• 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/FinetunningMiniLM-V18Data-256ConstantBATCH-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
0.0004	1	1.2042	-	-
0.3626	1000	1.1885	0.3903	0.9712
0.7252	2000	0.8207	0.3788	0.9699
1.0877	3000	0.7257	0.3854	0.9716
1.45	4000	0.9126	0.3814	0.9709
1.8123	5000	0.8911	0.3810	0.9711
2.1746	6000	0.8678	0.3830	0.9716
2.5370	7000	0.8551	0.3813	0.9721
2.8993	8000	0.8576	0.3842	0.9715
3.2616	9000	0.8325	0.3848	0.9713
3.6239	10000	0.8453	0.3842	0.9710
3.9862	11000	0.817	0.3848	0.9706

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",
}