e5-word-meta-ko

SentenceTransformer based on dragonkue/multilingual-e5-small-ko-v2

This is a sentence-transformers model finetuned from dragonkue/multilingual-e5-small-ko-v2 on the json dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: dragonkue/multilingual-e5-small-ko-v2 <!-- at revision fcfc26bf355882620c48df58be112275bd756f50 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text
• Training Dataset:
  • json

<!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', '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("sentence_transformers_model_id")
# Run inference
queries = [
    'query: 병과명',
]
documents = [
    'passage: 한글명: 병과명\n영문약어명: BR_NM\n단어조합: 병과 + 명\n단어영문약어조합: BR + NM\n단어도메인분류조합: 명\n마지막단어: 명\n마지막단어도메인분류명: 명\n설명: 군사조직에서 군인이 능력에 따라 수행하는 주요 임무를 분류한 것의 이름',
    'passage: 한글명: 변환파일명\n영문약어명: TRSF_FILE_NM\n단어조합: 변환 + 파일 + 명\n단어영문약어조합: TRSF + FILE + NM\n단어도메인분류조합: 명\n마지막단어: 명\n마지막단어도메인분류명: 명\n설명: 다르게 하여 바꾼 파일의 이름',
    'passage: 한글명: 국가명\n영문약어명: NTN_NM\n단어조합: 국가 + 명\n단어영문약어조합: NTN + NM\n단어도메인분류조합: 명\n마지막단어: 명\n마지막단어도메인분류명: 명\n설명: 일정한 영토와 거기에 사는 사람들로 구성되고, 주권(主權)에 따른 하나의 통치 조직을 가지고 있는 사회 집단의 이름\n이음동의어: 나라명, 국가명칭, 국가이름, 나라명칭, 나라이름',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.9488, 0.0378, 0.2989]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* -->

Evaluation

Metrics

Information Retrieval

• Dataset: meta-assistant-terms
• Evaluated with <code>InformationRetrievalEvaluator</code>

<!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

json

• Dataset: json
• Size: 25,358 training samples
• Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
• Approximate statistics based on the first 100 samples:

  	anchor	positive	negative
  type	string	string	string
  modality	text	text	text
  details	<ul><li>min: 6 tokens</li><li>mean: 7.65 tokens</li><li>max: 10 tokens</li></ul>	<ul><li>min: 64 tokens</li><li>mean: 84.45 tokens</li><li>max: 105 tokens</li></ul>	<ul><li>min: 73 tokens</li><li>mean: 102.46 tokens</li><li>max: 150 tokens</li></ul>

• Samples:

  anchor	positive	negative
  <code>query: 고도</code>	<code>passage: 한글명: 고도<br>영문약어명: ALTD<br>단어조합: 고도<br>단어영문약어조합: ALTD<br>단어도메인분류조합: 수<br>마지막단어: 고도<br>마지막단어도메인분류명: 수<br>설명: 평균 해수면 따위를 0으로 하여 측정한 대상 물체의 높이</code>	<code>passage: 한글명: 해발고도<br>영문약어명: ELVT_ALTD<br>단어조합: 해발 + 고도<br>단어영문약어조합: ELVT + ALTD<br>단어도메인분류조합: 수<br>마지막단어: 고도<br>마지막단어도메인분류명: 수<br>설명: 평균 해수면을 기준으로 하여 잰 어떤 지점의 높이</code>
  <code>query: 국비</code>	<code>passage: 한글명: 국비<br>영문약어명: GVEXP<br>단어조합: 국비<br>단어영문약어조합: GVEXP<br>단어도메인분류조합: 비용<br>마지막단어: 국비<br>마지막단어도메인분류명: 비용<br>설명: 나라의 재정으로 부담하는 비용</code>	<code>passage: 한글명: 국민주택기금금액<br>영문약어명: NHFND_AMT<br>단어조합: 국민주택기금 + 금액<br>단어영문약어조합: NHFND + AMT<br>단어도메인분류조합: 금액<br>마지막단어: 금액<br>마지막단어도메인분류명: 금액<br>설명: 한 세대당 85㎡ 이하로 규정된 국민 주택의 건설하는 것을 지원할 목적으로 마련한 기금에서 지원·융자 또는 보조하는 돈의 액수</code>
  <code>query: 군번</code>	<code>passage: 한글명: 군번<br>영문약어명: SRVNO<br>단어조합: 군번<br>단어영문약어조합: SRVNO<br>단어도메인분류조합: 번호<br>마지막단어: 군번<br>마지막단어도메인분류명: 번호<br>설명: 군인 개인마다 주어지는 고유 번호</code>	<code>passage: 한글명: 군경력개월수<br>영문약어명: MLCR_MCNT<br>단어조합: 군경력 + 개월수<br>단어영문약어조합: MLCR + MCNT<br>단어도메인분류조합: 수<br>마지막단어: 개월수<br>마지막단어도메인분류명: 수<br>설명: 군에 복무한 경력에 대한 개월의 수</code>

• Loss: <code>MultipleNegativesRankingLoss</code> 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

• per_device_train_batch_size: 32
• num_train_epochs: 2
• learning_rate: 2e-05
• warmup_steps: 0.1
• fp16: True
• dataloader_drop_last: True
• batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• per_device_train_batch_size: 32
• num_train_epochs: 2
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch_fused
• 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: False
• fp16: True
• 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: False
• 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: True
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Training Time

• Training: 7.6 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.6.0
• Transformers: 5.12.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

<!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->