README.md

---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:13304
- loss:MultipleNegativesRankingLoss
base_model: sentence-transformers/LaBSE
widget:
- source_sentence: それは彼女のアリバイになるはずだ。
  sentences:
  - Важко сказати.
  - Це мало правити їй за алібі.
  - — Ні.
- source_sentence: 声が上機嫌になった。
  sentences:
  - Фукаері кивнула.
  - 'Його голос став веселішим:'
  - Бо карлики більше полюбляли природну дощову воду, ніж річкову.
- source_sentence: 天吾は前夜、長い時間をかけて知恵を絞り、それを作成したのだ。
  sentences:
  - Повернути назад куплений товар і взяти новий не випадає.
  - «Погратися з наручниками?» — подумала вона.
  - Минулого вечора він довго сушив собі голову над ними.
- source_sentence: 「その人たちにどんなことをされたの？」
  sentences:
  - — Правду кажучи, я до двадцяти років залишалася незайманою.
  - Та все одно я кохала його.
  - — І до чого вони вас примушували?
- source_sentence: 微かな、しかし打ち消しがたい違和感がそこにはある。
  sentences:
  - Якась легка, але незаперечна відмінність.
  - Кожна людина вільна обирати, як їй жити.
  - Дуже дякую!
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---

# SentenceTransformer based on sentence-transformers/LaBSE

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) on the csv 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:** [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) <!-- at revision b7f947194ceae0ddf90bafe213722569e274ad28 -->
- **Maximum Sequence Length:** 256 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
    - csv
<!-- - **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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): Normalize()
)
```

## 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("bicolino34/LaBSE-ja-uk")
# Run inference
sentences = [
    '微かな、しかし打ち消しがたい違和感がそこにはある。',
    'Якась легка, але незаперечна відмінність.',
    'Кожна людина вільна обирати, як їй жити.',
]
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.*
-->

<!--
## 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

#### csv

* Dataset: csv
* Size: 13,304 training samples
* Columns: <code>Source</code> and <code>Target</code>
* Approximate statistics based on the first 1000 samples:
  |         | Source                                                                             | Target                                                                            |
  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                             | string                                                                            |
  | details | <ul><li>min: 4 tokens</li><li>mean: 22.68 tokens</li><li>max: 118 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 19.39 tokens</li><li>max: 93 tokens</li></ul> |
* Samples:
  | Source                                            | Target                                                                         |
  |:--------------------------------------------------|:-------------------------------------------------------------------------------|
  | <code>あたりはまだ暗い。</code>                            | <code>Навколо все ще було темно.</code>                                        |
  | <code>しかし受話器をとるものはいない。</code>                     | <code>Однак ніхто не підніме слухавки.</code>                                  |
  | <code>前にも言ったように、深田は宗教的な傾向など露ほども持ちあわせない人物だ。</code> | <code>Як я казав раніше, Фукада не мав найменшої схильності до релігії.</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"
  }
  ```

### Evaluation Dataset

#### csv

* Dataset: csv
* Size: 13,304 evaluation samples
* Columns: <code>Source</code> and <code>Target</code>
* Approximate statistics based on the first 1000 samples:
  |         | Source                                                                            | Target                                                                            |
  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
  | type    | string                                                                            | string                                                                            |
  | details | <ul><li>min: 4 tokens</li><li>mean: 21.78 tokens</li><li>max: 96 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 19.04 tokens</li><li>max: 72 tokens</li></ul> |
* Samples:
  | Source                          | Target                                |
  |:--------------------------------|:--------------------------------------|
  | <code>そうすれば彼女は天吾をほめてくれた。</code> | <code>За це вона його хвалила.</code> |
  | <code>「警察官一家」</code>            | <code>— Поліцейська родина.</code>    |
  | <code>ある、とバーテンダーは言った。</code>    | <code>Бармен відповів, що є.</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"
  }
  ```

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

- `eval_strategy`: steps
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `num_train_epochs`: 4
- `warmup_ratio`: 0.1
- `fp16`: True
- `batch_sampler`: no_duplicates

#### 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`: 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
- `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`: 4
- `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`: None
- `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`: proportional

</details>

### Training Logs
| Epoch  | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.1502 | 100  | 0.0884        | 0.0619          |
| 0.3003 | 200  | 0.0677        | 0.0591          |
| 0.4505 | 300  | 0.091         | 0.0778          |
| 0.6006 | 400  | 0.0612        | 0.0630          |
| 0.7508 | 500  | 0.0993        | 0.0740          |
| 0.9009 | 600  | 0.082         | 0.0757          |
| 1.0511 | 700  | 0.0898        | 0.0722          |
| 1.2012 | 800  | 0.0342        | 0.0605          |
| 1.3514 | 900  | 0.0168        | 0.0595          |
| 1.5015 | 1000 | 0.0158        | 0.0599          |
| 1.6517 | 1100 | 0.0096        | 0.0613          |
| 1.8018 | 1200 | 0.0107        | 0.0614          |
| 1.9520 | 1300 | 0.0113        | 0.0639          |
| 2.1021 | 1400 | 0.0112        | 0.0572          |
| 2.2523 | 1500 | 0.0074        | 0.0534          |
| 2.4024 | 1600 | 0.0039        | 0.0553          |
| 2.5526 | 1700 | 0.0019        | 0.0532          |
| 2.7027 | 1800 | 0.0019        | 0.0555          |
| 2.8529 | 1900 | 0.0026        | 0.0527          |
| 3.0030 | 2000 | 0.0013        | 0.0525          |
| 3.1532 | 2100 | 0.0008        | 0.0520          |
| 3.3033 | 2200 | 0.001         | 0.0516          |
| 3.4535 | 2300 | 0.0006        | 0.0519          |
| 3.6036 | 2400 | 0.0006        | 0.0515          |
| 3.7538 | 2500 | 0.0005        | 0.0514          |
| 3.9039 | 2600 | 0.0005        | 0.0516          |


### Framework Versions
- Python: 3.10.12
- Sentence Transformers: 3.3.1
- Transformers: 4.47.1
- PyTorch: 2.5.1+cu121
- Accelerate: 1.2.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## 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.*
-->