README.md

metadata

library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10501
  - loss:CosineSimilarityLoss
base_model: BAAI/bge-m3
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: 숙소가 기대했던 것 이상으로 좋았습니다.
    sentences:
      - 숙소가 생각보다 좋았어요.
      - 어떻게 해야 환풍기를 작동시킬 수 있어?
      - 우리 집 바로 옆에 슈퍼마켓이 있는데, 무엇보다도 조용해요.
  - source_sentence: 위치, 청결 상태, 주변 편의시설 모든게 좋았어요.
    sentences:
      - 집주인이 있기에 이 나라에서 잊을 수 없는 추억을 남겼습니다.
      - 두 개 방 모두에서 누우면 에펠탑이 보입니다!
      - 위치와 청결도 편의시설 크기 등등 모든게 좋습니다.
  - source_sentence: 인내심을 가지고 결실을 맺는다는 자세가 필요합니다.
    sentences:
      - >-
        같은 날, 바이오 산업은 정부에게 바이오 전문가 공급 시설, 새로운 시장 창출을 위한 규제 완화, 세금과 같은 인센티브 확대 등을
        제안했습니다.
      - 그런 점에서 매우 힘든 기간을 보내고 계십니다.
      - 접속 가능한 계정 네이트나 네이버 메일 중 하나만 알려줘
  - source_sentence: 비가 올지 맑을지 오늘 날씨를 찾아봐줄래?
    sentences:
      - 이번 태풍 진행 방향은?
      - 제가 지메일을 몇 번 가입했는지 알려주실 수 있나요?
      - 할부지 덕분에 산타모니카에 있는 내내 행복했어요.
  - source_sentence: 티비 켜고 싶은데 말로 어떻게 명령해야하는 지 알려줘
    sentences:
      - 가습기 어떻게 써?
      - 친절한 설명으로 많은 도움이 되었습니다.
      - 에어컨과 뜨거운 물 모두 좋았습니다.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on BAAI/bge-m3
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: pearson_cosine
            value: 0.9599773741282561
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9215829115320294
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.9448530221078223
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.9182945172058137
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.9451692315193281
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.9184981231098932
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.9576506770371606
            name: Pearson Dot
          - type: spearman_dot
            value: 0.9159848293826075
            name: Spearman Dot
          - type: pearson_max
            value: 0.9599773741282561
            name: Pearson Max
          - type: spearman_max
            value: 0.9215829115320294
            name: Spearman Max

SentenceTransformer based on BAAI/bge-m3

This is a sentence-transformers model finetuned from BAAI/bge-m3. It maps sentences & paragraphs to a 1024-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: BAAI/bge-m3
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 1024 tokens
• 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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("jeonseonjin/embedding_BAAI-bge-m3")
# Run inference
sentences = [
    '티비 켜고 싶은데 말로 어떻게 명령해야하는 지 알려줘',
    '가습기 어떻게 써?',
    '친절한 설명으로 많은 도움이 되었습니다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

Evaluation

Metrics

Semantic Similarity

• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.96
spearman_cosine	0.9216
pearson_manhattan	0.9449
spearman_manhattan	0.9183
pearson_euclidean	0.9452
spearman_euclidean	0.9185
pearson_dot	0.9577
spearman_dot	0.916
pearson_max	0.96
spearman_max	0.9216

Training Details

Training Dataset

Unnamed Dataset

• Size: 10,501 training samples
• Columns: sentence_0, sentence_1, and label
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	label
  type	string	string	float
  details	min: 7 tokens mean: 21.15 tokens max: 97 tokens	min: 7 tokens mean: 20.2 tokens max: 61 tokens	min: 0.0 mean: 0.44 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  공원에서 열리는 시장도 구경할 수 있었어요.	공원에서 시장을 볼 수 있었어요.	0.74
  베네치아에서 2박 3일 일정으로 머물렀습니다.	저는 2박 3일 동안 베니스에 머물렀습니다.	0.74
  메일로 홍보하는 학회 리스트 불러줘	보낸메일함의 메일은 주기적으로 백업하세요. 간헐적으로 하면 안됩니다.	0.12

• Loss: CosineSimilarityLoss with these parameters:

  {
      "loss_fct": "torch.nn.modules.loss.MSELoss"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 1
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1
• num_train_epochs: 1
• 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
• 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: 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: 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, '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_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	spearman_max
0	0	-	0.9196
0.7610	500	0.024	-
1.0	657	-	0.9216

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.1.1
• Transformers: 4.40.1
• PyTorch: 2.4.1+cu121
• Accelerate: 0.34.2
• Datasets: 2.19.0
• 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",
}