SentenceTransformer

This is a sentence-transformers model trained on the pairs and hard_negatives datasets. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer

• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text
• Training Datasets:
  • pairs
  • hard_negatives

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'mean', '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("CHEONINJEONG/bge-m3-address-v2")
# Run inference
sentences = [
    '여기 구로 새말로 31',
    '서울특별시 구로구 새말로 31',
    '서울특별시 서초구 서초중앙로 206',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9368, 0.0050],
#         [0.9368, 1.0000, 0.0949],
#         [0.0050, 0.0949, 1.0000]])

Training Details

Training Datasets

pairs

• Dataset: pairs
• Size: 7,902 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 100 samples:

  	anchor	positive
  type	string	string
  modality	text	text
  details	min: 11 tokensmean: 23.45 tokensmax: 38 tokens	min: 9 tokensmean: 19.75 tokensmax: 32 tokens

• Samples:

  anchor	positive
  주소가 충청북도 청주시 청원구 오창읍 양청길 85호 106호 거든요	충청북도 청주시 청원구 오창읍 양청길 85 106호
  여기 경남고성군개천면나선길99번-3 입니다	경남 고성군 개천면 나선길 99-3
  네 충청북도음성군원남면하당길14자연빌라가동401번호	충청북도 음성군 원남면 하당길 14 자연빌라 가동 401호

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

hard_negatives

• Dataset: hard_negatives
• Size: 388 training samples
• Columns: anchor, positive, and negative
• Approximate statistics based on the first 100 samples:

  	anchor	positive	negative
  type	string	string	string
  modality	text	text	text
  details	min: 12 tokensmean: 25.28 tokensmax: 45 tokens	min: 10 tokensmean: 14.89 tokensmax: 23 tokens	min: 10 tokensmean: 14.82 tokensmax: 22 tokens

• Samples:

  anchor	positive	negative
  부산시 부산진구 가야대로 칠공삼번길 삼십 당감동서면 수지빌 시지시즌빌 천사백사 호	부산광역시 부산진구 가야대로703번길 30	부산광역시 부산진구 가야대로703번길 31
  서울시 구로구 개봉로 십칠가길 오육다시 칠 호반아트빌 이백일호요	서울특별시 구로구 개봉로17다길 56-7	서울특별시 구로구 개봉로17다길 55
  화성시 수노을 일 로 일공공팔	경기도 화성시 만세구 수노을1로 108	경기도 화성시 만세구 수노을1로 107

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Evaluation Dataset

pairs

• Dataset: pairs
• Size: 1,975 evaluation samples
• Columns: anchor and positive
• Approximate statistics based on the first 100 samples:

  	anchor	positive
  type	string	string
  modality	text	text
  details	min: 12 tokensmean: 22.61 tokensmax: 36 tokens	min: 10 tokensmean: 19.32 tokensmax: 34 tokens

• Samples:

  anchor	positive
  네 경기도광명시광명로770401호 맞아요	경기도 광명시 광명로 770 401호
  네 경남 창원시 성산구 원이대로 663호 (신월동, 은아아파트) 이에요	경상남도 창원시 성산구 원이대로 663 (신월동, 은아아파트)
  지금 경남 거제시 상동3길 15호 요	경상남도 거제시 상동3길 15

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• num_train_epochs: 5
• learning_rate: 2e-05
• warmup_steps: 0.1
• bf16: True
• load_best_model_at_end: True

All Hyperparameters

• per_device_train_batch_size: 8
• num_train_epochs: 5
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: True
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 8
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: True
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: False
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs