NghiBuine/ecommerce-product-search-model

SentenceTransformer based on keepitreal/vietnamese-sbert

This is a sentence-transformers model finetuned from keepitreal/vietnamese-sbert on the json dataset. It maps sentences & paragraphs to a 768-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: keepitreal/vietnamese-sbert
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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}) with Transformer model: RobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, '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})
)

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("NghiBuine/ecommerce-product-search-model")
# Run inference
sentences = [
    'LEGO City Police Station',
    'mô hình đẹp mắt để trưng bày',
    'dễ dàng phối đồ từ áo thun, sơ mi đến blazer',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 768
  }
  

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.0
cosine_accuracy@5	0.027
cosine_accuracy@10	0.5676
cosine_precision@1	0.0
cosine_precision@3	0.0
cosine_precision@5	0.0054
cosine_precision@10	0.0568
cosine_recall@1	0.0
cosine_recall@3	0.0
cosine_recall@5	0.027
cosine_recall@10	0.5676
cosine_ndcg@10	0.1784
cosine_mrr@10	0.0706
cosine_map@100	0.0797

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 512
  }
  

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.0
cosine_accuracy@5	0.0
cosine_accuracy@10	0.5405
cosine_precision@1	0.0
cosine_precision@3	0.0
cosine_precision@5	0.0
cosine_precision@10	0.0541
cosine_recall@1	0.0
cosine_recall@3	0.0
cosine_recall@5	0.0
cosine_recall@10	0.5405
cosine_ndcg@10	0.1702
cosine_mrr@10	0.0675
cosine_map@100	0.0782

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 256
  }
  

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.0
cosine_accuracy@5	0.0
cosine_accuracy@10	0.5405
cosine_precision@1	0.0
cosine_precision@3	0.0
cosine_precision@5	0.0
cosine_precision@10	0.0541
cosine_recall@1	0.0
cosine_recall@3	0.0
cosine_recall@5	0.0
cosine_recall@10	0.5405
cosine_ndcg@10	0.1722
cosine_mrr@10	0.0695
cosine_map@100	0.0794

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 128
  }
  

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.0
cosine_accuracy@5	0.0
cosine_accuracy@10	0.5405
cosine_precision@1	0.0
cosine_precision@3	0.0
cosine_precision@5	0.0
cosine_precision@10	0.0541
cosine_recall@1	0.0
cosine_recall@3	0.0
cosine_recall@5	0.0
cosine_recall@10	0.5405
cosine_ndcg@10	0.1706
cosine_mrr@10	0.0679
cosine_map@100	0.0761

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 64
  }
  

Metric	Value
cosine_accuracy@1	0.0
cosine_accuracy@3	0.0
cosine_accuracy@5	0.027
cosine_accuracy@10	0.5135
cosine_precision@1	0.0
cosine_precision@3	0.0
cosine_precision@5	0.0054
cosine_precision@10	0.0514
cosine_recall@1	0.0
cosine_recall@3	0.0
cosine_recall@5	0.027
cosine_recall@10	0.5135
cosine_ndcg@10	0.1648
cosine_mrr@10	0.0673
cosine_map@100	0.0779

Training Details

Training Dataset

json

• Dataset: json
• Size: 333 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 333 samples:

  	positive	anchor
  type	string	string
  details	min: 4 tokens mean: 9.73 tokens max: 37 tokens	min: 6 tokens mean: 13.71 tokens max: 41 tokens

• Samples:

  positive	anchor
  Giày Chạy Bộ Adidas Ultraboost	Ultraboost đế continental chống trượt
  Cà Phê Cùng Tony	Cà Phê Cùng Tony chia sẻ bài học phát triển bản thân và sống tích cực
  Đắc Nhân Tâm	phát triển kỹ năng thuyết phục và giao tiếp tự nhiên

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• gradient_accumulation_steps: 16
• learning_rate: 2e-05
• num_train_epochs: 4
• bf16: True
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 16
• eval_accumulation_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: 4
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: True
• fp16: False
• 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: True
• 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: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• dispatch_batches: None
• split_batches: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
1.0	1	0.1716	0.1897	0.1450	0.1699	0.1542
2.0	3	0.179	0.171	0.1722	0.1719	0.1644
2.9091	4	0.1784	0.1702	0.1722	0.1706	0.1648

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 4.1.0
• Transformers: 4.41.2
• PyTorch: 2.6.0+cu124
• Accelerate: 1.7.0
• Datasets: 2.19.1
• Tokenizers: 0.19.1

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}