.ipynb_checkpoints/README-checkpoint.md

---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:574325
- loss:MultipleNegativesRankingLoss
- loss:CosineSimilarityLoss
base_model: upskyy/gte-base-korean
widget:
- source_sentence: 그것은 도덕적으로 강요하지 않는다.
  sentences:
  - 그것은 법을 제정하고 있다.
  - 시리아 야당은 회담에 참석할 것을 촉구했다.
  - 한 젊은이가 기타를 연주하면서 노래를 부르고 있다.
- source_sentence: 한 여성이 무대에서 플루트를 연주하고 있다.
  sentences:
  - 여자가 플루트를 연주하고 있다.
  - 인도, 사이클론 파일린에 대한 적색 경보 발령
  - 반 데르 메르웨는 가이게스의 형을 5년 징역형으로 중지했다.
- source_sentence: 적어도 나는 이 남자가 자신의 범죄를 이해한다고 확신할 수 있었다.
  sentences:
  - 티셔츠와 반바지를 입고 티에서 축구를 걷어차는 남자
  - 나는 그가 무엇을 잘못했는지 전혀 모른다고 생각하기 시작했다.
  - 남자는 자신이 한 일을 알고 있었다.
- source_sentence: 사람은 다리로 올라갑니다.
  sentences:
  - 한 남자가 땅에 누워 있다.
  - 자전거를 타는 한 무리의 사람들이 거리에서 돌아선다.
  - 공중으로 뛰어드는 남자
- source_sentence: 모자를 쓴 남자와 여자가 거리에서 악기를 연주하고 있다.
  sentences:
  - 사람은 수직 물체에 받쳐진다.
  - 두 남자가 길가에 서 있다.
  - 두 사람이 모자를 쓰고 있다.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
- pearson_cosine
- spearman_cosine
model-index:
- name: SentenceTransformer based on upskyy/gte-base-korean
  results:
  - task:
      type: semantic-similarity
      name: Semantic Similarity
    dataset:
      name: sts dev
      type: sts-dev
    metrics:
    - type: pearson_cosine
      value: 0.868140244252358
      name: Pearson Cosine
    - type: spearman_cosine
      value: 0.8689161244129222
      name: Spearman Cosine
---

# SentenceTransformer based on upskyy/gte-base-korean

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [upskyy/gte-base-korean](https://huggingface.co/upskyy/gte-base-korean). 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:** [upskyy/gte-base-korean](https://huggingface.co/upskyy/gte-base-korean) <!-- at revision c1a18ef8326962b57c63e2d306a724a925913dfe -->
- **Maximum Sequence Length:** 8192 tokens
- **Output Dimensionality:** 768 dimensions
- **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': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
  (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 = [
    '모자를 쓴 남자와 여자가 거리에서 악기를 연주하고 있다.',
    '두 사람이 모자를 쓰고 있다.',
    '두 남자가 길가에 서 있다.',
]
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      | 0.8681     |
| **spearman_cosine** | **0.8689** |

<!--
## 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: 568,576 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: 5 tokens</li><li>mean: 19.18 tokens</li><li>max: 111 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 20.1 tokens</li><li>max: 129 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.51 tokens</li><li>max: 42 tokens</li></ul> |
* Samples:
  | sentence_0                                                | sentence_1                                                  | sentence_2                                      |
  |:----------------------------------------------------------|:------------------------------------------------------------|:------------------------------------------------|
  | <code>나는 솔직히 말해서 가게에서 그것을 산 사람은 그 남자가 아니라고 말할 것이다.</code> | <code>화학자 가게에서 스트리크닌을 산 사람은 그가 아니었다는 것을 인정하겠다.</code>       | <code>난 아무것도 인정하지 않을 거야, 이 모든 대화는 무의미해!</code>  |
  | <code>네 명의 여성이 있다.</code>                                 | <code>검은색과 노란색 드레스를 입은 세 명의 여성과 오렌지색 머리를 가진 한 명의 여성.</code> | <code>신부 들러리 세 명이 모두 어울리지 않는 드레스를 입고 있다.</code> |
  | <code>드류는 빤히 쳐다보면서 다른 사람을 생각하고 있었다.</code>                | <code>하지만 다른 하나는...... 드류가 빤히 쳐다보았다.</code>                 | <code>드류는 다른 사람을 걱정하지 않았다.</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: 5,749 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: 19.1 tokens</li><li>max: 74 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.15 tokens</li><li>max: 83 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.53</li><li>max: 1.0</li></ul> |
* Samples:
  | sentence_0                             | sentence_1                            | label            |
  |:---------------------------------------|:--------------------------------------|:-----------------|
  | <code>한 남자가 바이올린을 연주하고 있다.</code>      | <code>아기가 웃고 기어가고 있다.</code>          | <code>0.0</code> |
  | <code>구스마오는 동티모르 선거에서 권력을 강화한다.</code> | <code>롬니가 선거에서 승리할 경우 대법원의 가능성</code> | <code>0.0</code> |
  | <code>그게 아니었다는 것만 빼면.</code>           | <code>그들이 할 수 없다는 것 빼고는...</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`: 1
- `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
- `torch_empty_cache_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`: 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
- `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
- `include_for_metrics`: []
- `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
- `eval_on_start`: False
- `use_liger_kernel`: False
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: round_robin

</details>

### Training Logs
| Epoch  | Step | Training Loss | sts-dev_spearman_cosine |
|:------:|:----:|:-------------:|:-----------------------:|
| 0.3477 | 500  | 0.1296        | -                       |
| 0.6954 | 1000 | 0.1192        | 0.8689                  |


### Framework Versions
- Python: 3.11.10
- Sentence Transformers: 3.3.0
- Transformers: 4.46.2
- PyTorch: 2.4.0+cu121
- Accelerate: 1.1.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3

## 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.*
-->