Add new SentenceTransformer model.

8e96d52 verified 7 months ago

18.8 kB

	---
	language:
	- ko
	library_name: sentence-transformers
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:11668
	- loss:CosineSimilarityLoss
	datasets:
	- klue/klue
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	widget:
	- source_sentence: 이는 지난 15일 개최된 제1차 주요국 외교장관간 협의에 뒤이은 것이다.
	sentences:
	- 100일간의 유럽 여행 중 단연 최고의 숙소였습니다!
	- 이것은 7월 15일에 열린 주요 국가의 외무 장관들 간의 첫 번째 회담에 이은 것입니다.
	- 거실옆 작은 방에도 싱글 침대가 두개 있습니다.
	- source_sentence: 3000만원 이하 소액대출은 지역신용보증재단 심사를 기업은행에 위탁하기로 했다.
	sentences:
	- 그 집은 두 사람이 살기에 충분히 크고 깨끗했습니다.
	- 3,000만원 미만의 소규모 대출은 기업은행에 의해 국내 신용보증재단을 검토하도록 의뢰될 것입니다.
	- 지하철, 버스, 기차 모두 편리했습니다.
	- source_sentence: 공간은 4명의 성인 가족이 사용하기에 부족함이 없었고.
	sentences:
	- 특히 모든 부처 장관들이 책상이 아닌 현장에서 직접 방역과 민생 경제의 중심에 서 주시기 바랍니다.
	- 구시가까지 걸어서 15분 정도 걸립니다.
	- 그 공간은 4인 가족에게는 충분하지 않았습니다.
	- source_sentence: 클락키까지 걸어서 10분 정도 걸려요.
	sentences:
	- 가족 여행이나 4명정도 같이 가는 일행은 정말 좋은 곳 같아요
	- 외출 시 방범 모드는 어떻게 바꿔?
	- 타이페이 메인 역까지 걸어서 10분 정도 걸립니다.
	- source_sentence: SR은 동대구·김천구미·신경주역에서 승하차하는 모든 국민에게 운임 10%를 할인해 준다.
	sentences:
	- 그 방은 두 사람이 쓰기에는 조금 좁아요.
	- 수강신청 하는 날짜가 어느 날짜인지 아시는지요?
	- SR은 동대구역, 김천구미역, 신주역을 오가는 모든 승객을 대상으로 요금을 10% 할인해 드립니다.
	pipeline_tag: sentence-similarity
	model-index:
	- name: SentenceTransformer
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: sts dev
	type: sts-dev
	metrics:
	- type: pearson_cosine
	value: 0.8702835444344084
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.8689602780969523
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.8348899972988737
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.8326814383995406
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.8344792299115973
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.8328448090313935
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.8254531870117598
	name: Pearson Dot
	- type: spearman_dot
	value: 0.8304427971585958
	name: Spearman Dot
	- type: pearson_max
	value: 0.8702835444344084
	name: Pearson Max
	- type: spearman_max
	value: 0.8689602780969523
	name: Spearman Max
	---

	# SentenceTransformer

	This is a [sentence-transformers](https://www.SBERT.net) model trained on the [klue/klue](https://huggingface.co/datasets/klue/klue) 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: [Unknown](https://huggingface.co/unknown) -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- [klue/klue](https://huggingface.co/datasets/klue/klue)
	- Language: ko
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

	### Full Model Architecture

	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
	(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:

	```bash
	pip install -U sentence-transformers
	```

	Then you can load this model and run inference.
	```python
	from sentence_transformers import SentenceTransformer

	# Download from the 🤗 Hub
	model = SentenceTransformer("snunlp/KR-SBERT-Medium-klueNLItriplet_PARpair-klueSTS")
	# Run inference
	sentences = [
	'SR은 동대구·김천구미·신경주역에서 승하차하는 모든 국민에게 운임 10%를 할인해 준다.',
	'SR은 동대구역, 김천구미역, 신주역을 오가는 모든 승객을 대상으로 요금을 10% 할인해 드립니다.',
	'수강신청 하는 날짜가 어느 날짜인지 아시는지요?',
	]
	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]
	```

	<!--
	### 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

	#### Semantic Similarity
	* Dataset: `sts-dev`
	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:----------\|
	\| pearson_cosine \| 0.8703 \|
	\| spearman_cosine \| 0.869 \|
	\| pearson_manhattan \| 0.8349 \|
	\| spearman_manhattan \| 0.8327 \|
	\| pearson_euclidean \| 0.8345 \|
	\| spearman_euclidean \| 0.8328 \|
	\| pearson_dot \| 0.8255 \|
	\| spearman_dot \| 0.8304 \|
	\| pearson_max \| 0.8703 \|
	\| spearman_max \| 0.869 \|

	<!--
	## 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

	#### klue/klue

	* Dataset: [klue/klue](https://huggingface.co/datasets/klue/klue) at [349481e](https://huggingface.co/datasets/klue/klue/tree/349481ec73fff722f88e0453ca05c77a447d967c)
	* Size: 11,668 training samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 7 tokens</li><li>mean: 18.53 tokens</li><li>max: 56 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 18.02 tokens</li><li>max: 60 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.44</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:-----------------------------------------------------------\|:--------------------------------------------------------\|:---------------------------------\|
	\| <code>숙소 위치는 찾기 쉽고 일반적인 한국의 반지하 숙소입니다.</code> \| <code>숙박시설의 위치는 쉽게 찾을 수 있고 한국의 대표적인 반지하 숙박시설입니다.</code> \| <code>0.7428571428571428</code> \|
	\| <code>위반행위 조사 등을 거부·방해·기피한 자는 500만원 이하 과태료 부과 대상이다.</code> \| <code>시민들 스스로 자발적인 예방 노력을 한 것은 아산 뿐만이 아니었다.</code> \| <code>0.0</code> \|
	\| <code>회사가 보낸 메일은 이 지메일이 아니라 다른 지메일 계정으로 전달해줘.</code> \| <code>사람들이 주로 네이버 메일을 쓰는 이유를 알려줘</code> \| <code>0.06666666666666667</code> \|
	* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
	```json
	{
	"loss_fct": "torch.nn.modules.loss.MSELoss"
	}
	```

	### Evaluation Dataset

	#### klue/klue

	* Dataset: [klue/klue](https://huggingface.co/datasets/klue/klue) at [349481e](https://huggingface.co/datasets/klue/klue/tree/349481ec73fff722f88e0453ca05c77a447d967c)
	* Size: 519 evaluation samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:---------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:--------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 7 tokens</li><li>mean: 18.6 tokens</li><li>max: 61 tokens</li></ul> \| <ul><li>min: 7 tokens</li><li>mean: 18.16 tokens</li><li>max: 60 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:----------------------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------------\|:---------------------------------\|
	\| <code>무엇보다도 호스트분들이 너무 친절하셨습니다.</code> \| <code>무엇보다도, 호스트들은 매우 친절했습니다.</code> \| <code>0.9714285714285713</code> \|
	\| <code>주요 관광지 모두 걸어서 이동가능합니다.</code> \| <code>위치는 피렌체 중심가까지 걸어서 이동 가능합니다.</code> \| <code>0.2857142857142858</code> \|
	\| <code>학생들의 균형 있는 영어능력을 향상시킬 수 있는 학교 수업을 유도하기 위해 2018학년도 수능부터 도입된 영어 영역 절대평가는 올해도 유지한다.</code> \| <code>영어 영역의 경우 학생들이 한글 해석본을 암기하는 문제를 해소하기 위해 2016학년도부터 적용했던 EBS 연계 방식을 올해도 유지한다.</code> \| <code>0.25714285714285723</code> \|
	* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
	```json
	{
	"loss_fct": "torch.nn.modules.loss.MSELoss"
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 64
	- `per_device_eval_batch_size`: 64
	- `num_train_epochs`: 30
	- `warmup_ratio`: 0.1
	- `fp16`: True

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: steps
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 64
	- `per_device_eval_batch_size`: 64
	- `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`: 1.0
	- `num_train_epochs`: 30
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.1
	- `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`: 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, '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
	- `batch_sampler`: batch_sampler
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| sts-dev_spearman_cosine \|
	\|:------:\|:----:\|:-------------:\|:------:\|:-----------------------:\|
	\| 0 \| 0 \| - \| - \| 0.7244 \|
	\| 0.0109 \| 1 \| 0.0228 \| - \| - \|
	\| 0.5435 \| 50 \| 0.0212 \| 0.0335 \| 0.7952 \|
	\| 1.0870 \| 100 \| 0.0152 \| 0.0294 \| 0.8274 \|
	\| 1.6304 \| 150 \| 0.011 \| 0.0266 \| 0.8473 \|
	\| 2.1739 \| 200 \| 0.009 \| 0.0253 \| 0.8609 \|
	\| 2.7174 \| 250 \| 0.0056 \| 0.0248 \| 0.8658 \|
	\| 3.2609 \| 300 \| 0.005 \| 0.0251 \| 0.8685 \|
	\| 3.8043 \| 350 \| 0.0041 \| 0.0251 \| 0.8638 \|
	\| 4.3478 \| 400 \| 0.0044 \| 0.0278 \| 0.8600 \|
	\| 4.8913 \| 450 \| 0.0041 \| 0.0266 \| 0.8682 \|
	\| 5.4348 \| 500 \| 0.0036 \| 0.0259 \| 0.8690 \|


	### Framework Versions
	- Python: 3.11.9
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.3.1
	- Accelerate: 0.31.0
	- Datasets: 2.19.2
	- Tokenizers: 0.19.1

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@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",
	}
	```

	<!--
	## 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.
	-->