---
base_model: klue/roberta-base
datasets: []
language: []
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
- pearson_manhattan
- spearman_manhattan
- pearson_euclidean
- spearman_euclidean
- pearson_dot
- spearman_dot
- pearson_max
- spearman_max
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:574408
- loss:MultipleNegativesRankingLoss
- loss:CosineSimilarityLoss
widget:
- source_sentence: 한 여성이 뜨거운 물 냄비에 음식을 넣고 있다.
  sentences:
  - 한 여성이 고기를 튀기고 있다.
  - '세계 브리핑 아시아 : 미얀마 : 치명적인 반 무슬림 폭력 사태가 폭발했다.'
  - 아기가 잠들고 있다.
- source_sentence: 러시아 비행기 추락 사고로 사망자 수 증가
  sentences:
  - 이탈리아 코치 추락으로 사망자 수가 39명으로 증가
  - 헬리콥터 펍 추락 후 사망 두려워하는 세 명
  - 흑백 개는 입에 갈색 물체를 물고 헤엄친다.
- source_sentence: 거울에 비친 한 여자가 옆에 있는 다른 여자와 함께 카메라를 외면하고 앉아 있었다.
  sentences:
  - 보도 위를 걷는 여자와 함께 길을 건너는 흑인 여성의 뒷모습.
  - 여자가 거울을 응시하고 있다
  - 한 여성이 햄버거를 응시하고 있다
- source_sentence: 스키를 탄 사람이 공중으로 뛰어오른다.
  sentences:
  - 밖에 한 남자가 있다.
  - 그는 눈 위를 달리고 있다.
  - 그는 스키를 타고 공중으로 뛰어올랐다.
- source_sentence: 내 옆이나 내 뒤에, 경외심을 느끼며 언더톤으로 말했다.
  sentences:
  - 그는 나와는 거리가 멀었다.
  - FSIS는 접수된 의견과 기관의 요구 사항 재평가를 고려하여 연간 부담을 8,053,319시간으로 줄였습니다.
  - 그는 나와 가까웠다.
model-index:
- name: SentenceTransformer based on klue/roberta-base
  results:
  - task:
      type: semantic-similarity
      name: Semantic Similarity
    dataset:
      name: sts dev
      type: sts-dev
    metrics:
    - type: pearson_cosine
      value: 0.8657393669442817
      name: Pearson Cosine
    - type: spearman_cosine
      value: 0.866343037897214
      name: Spearman Cosine
    - type: pearson_manhattan
      value: 0.8568809906017532
      name: Pearson Manhattan
    - type: spearman_manhattan
      value: 0.8621129068016818
      name: Spearman Manhattan
    - type: pearson_euclidean
      value: 0.8569880055215549
      name: Pearson Euclidean
    - type: spearman_euclidean
      value: 0.8620159980137003
      name: Spearman Euclidean
    - type: pearson_dot
      value: 0.8382433069709427
      name: Pearson Dot
    - type: spearman_dot
      value: 0.8359003576467027
      name: Spearman Dot
    - type: pearson_max
      value: 0.8657393669442817
      name: Pearson Max
    - type: spearman_max
      value: 0.866343037897214
      name: Spearman Max
---

# SentenceTransformer based on klue/roberta-base

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [klue/roberta-base](https://huggingface.co/klue/roberta-base). 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:** [klue/roberta-base](https://huggingface.co/klue/roberta-base) <!-- at revision 02f94ba5e3fcb7e2a58a390b8639b0fac974a8da -->
- **Maximum Sequence Length:** 128 tokens
- **Output Dimensionality:** 768 tokens
- **Similarity Function:** Cosine Similarity
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **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': 128, '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:

```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("sentence_transformers_model_id")
# Run inference
sentences = [
    '내 옆이나 내 뒤에, 경외심을 느끼며 언더톤으로 말했다.',
    '그는 나와 가까웠다.',
    '그는 나와는 거리가 멀었다.',
]
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     | 0.8657     |
| spearman_cosine    | 0.8663     |
| pearson_manhattan  | 0.8569     |
| spearman_manhattan | 0.8621     |
| pearson_euclidean  | 0.857      |
| spearman_euclidean | 0.862      |
| pearson_dot        | 0.8382     |
| spearman_dot       | 0.8359     |
| pearson_max        | 0.8657     |
| **spearman_max**   | **0.8663** |

<!--
## 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 Datasets

#### Unnamed Dataset


* Size: 568,640 training samples
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
* Approximate statistics based on the first 1000 samples:
  |         | sentence_0                                                                        | sentence_1                                                                       | sentence_2                                                                        |
  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                            | string                                                                           | string                                                                            |
  | details | <ul><li>min: 4 tokens</li><li>mean: 19.2 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 18.3 tokens</li><li>max: 93 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.64 tokens</li><li>max: 54 tokens</li></ul> |
* Samples:
  | sentence_0                              | sentence_1                                       | sentence_2                            |
  |:----------------------------------------|:-------------------------------------------------|:--------------------------------------|
  | <code>발생 부하가 함께 5% 적습니다.</code>         | <code>발생 부하의 5% 감소와 함께 11.</code>                | <code>발생 부하가 5% 증가합니다.</code>         |
  | <code>어떤 행사를 위해 음식과 옷을 배급하는 여성들.</code> | <code>여성들은 음식과 옷을 나눠줌으로써 난민들을 돕고 있다.</code>      | <code>여자들이 사막에서 오토바이를 운전하고 있다.</code> |
  | <code>어린 아이들은 그 지식을 얻을 필요가 있다.</code>   | <code>응, 우리 젊은이들 중 많은 사람들이 그걸 배워야 할 것 같아.</code> | <code>젊은 사람들은 배울 필요가 없다.</code>       |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
  ```json
  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  ```

#### Unnamed Dataset


* Size: 5,768 training samples
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
* Approximate statistics based on the first 1000 samples:
  |         | sentence_0                                                                        | sentence_1                                                                        | label                                                          |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
  | type    | string                                                                            | string                                                                            | float                                                          |
  | details | <ul><li>min: 4 tokens</li><li>mean: 17.14 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 17.21 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.54</li><li>max: 1.0</li></ul> |
* Samples:
  | sentence_0                                                            | sentence_1                                                                | label                           |
  |:----------------------------------------------------------------------|:--------------------------------------------------------------------------|:--------------------------------|
  | <code>식품의약품관리국은 셔디 리서치를 인용하여 2001년 IMClone의 에르비턱스 판매 신청을 거절했다.</code> | <code>미국 식품의약국은 2001년 12월 이 재판이 부실하게 진행되었다고 말하면서 이클론의 원래 신청을 거부했다.</code> | <code>0.5599999999999999</code> |
  | <code>이슬람 주도의 이집트 , 콥트 교회 이름은 새로운 교황이다</code>                         | <code>이집트 기독교인들은 새로운 교황을 선택한다</code>                                      | <code>0.64</code>               |
  | <code>시리아 주지사는 공격을 중단하지 않는다</code>                                    | <code>시리아 야당, '학살' 보고</code>                                              | <code>0.2</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
- `num_train_epochs`: 5
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin

#### 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`: 8
- `per_device_eval_batch_size`: 8
- `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`: 5
- `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`: 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, '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`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin

</details>

### Training Logs
| Epoch  | Step | Training Loss | sts-dev_spearman_max |
|:------:|:----:|:-------------:|:--------------------:|
| 0.3467 | 500  | 0.419         | -                    |
| 0.6935 | 1000 | 0.3032        | 0.8516               |
| 1.0007 | 1443 | -             | 0.8605               |
| 1.0395 | 1500 | 0.2705        | -                    |
| 1.3863 | 2000 | 0.1368        | 0.8509               |
| 1.7330 | 2500 | 0.0906        | -                    |
| 2.0007 | 2886 | -             | 0.8663               |


### Framework Versions
- Python: 3.11.9
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.2.2+cu121
- Accelerate: 0.31.0
- Datasets: 2.20.0
- 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",
}
```

#### MultipleNegativesRankingLoss
```bibtex
@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}
}
```

<!--
## 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.*
-->