e5-gesn / README.md

e5-base, дообученная на синтетических парах запрос↔норма ГЭСН

280d2d8 verified about 1 month ago

18.5 kB

---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:10134
- loss:CachedMultipleNegativesRankingLoss
- loss:MultipleNegativesRankingLoss
base_model: intfloat/multilingual-e5-base
widget:
- source_sentence: 'query: грунтовка стен квартиры'
  sentences:
  - 'passage: Отделочные работы. Окраска фасадов с люлек по подготовленной поверхности:
    силикатная. Ед. изм.: 100 м2'
  - 'passage: Отделочные работы. Покрытие поверхностей грунтовкой глубокого проникновения:
    за 1 раз стен. Ед. изм.: 100 м2'
  - 'passage: Отделочные работы. Покрытие поверхностей грунтовкой глубокого проникновения:
    за 2 раза стен. Ед. изм.: 100 м2'
- source_sentence: 'query: установ шкафных дверей'
  sentences:
  - 'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий
    по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность'
  - 'passage: Деревянные конструкции. Установка дверных блоков: антресольных. Ед.
    изм.: 10 шт. Установка и крепление блоков антресольных'
  - 'passage: Деревянные конструкции. Установка дверных блоков: шкафных. Ед. изм.:
    10 шт. Установка и крепление блоков дверных шкафных'
- source_sentence: 'query: пергаминовая обшивка стены 100м2'
  sentences:
  - 'passage: Деревянные конструкции. Обшивка каркасных стен: досками обшивки. Ед.
    изм.: 100 м2. Обшивка стен пергамином, досками. Обшивка углов и пересечений'
  - 'passage: Деревянные конструкции. Обшивка каркасных стен: пергамином. Ед. изм.:
    100 м2. Обшивка стен пергамином'
  - 'passage: Отделочные работы. Огнезащитная пропитка текстильных (тканевых) покрытий.
    Ед. изм.: 100 м2. Огнезащитная пропитка текстильных покрытий'
- source_sentence: 'query: окраска решеток для дачи'
  sentences:
  - 'passage: Отделочные работы. Окраска фасадов с люлек с подготовкой поверхности:
    силикатная. Ед. изм.: 100 м2'
  - 'passage: Отделочные работы. Масляная окраска металлических поверхностей: решеток,
    переплетов, труб диаметром менее 50 мм и т.п., количество окрасок 2. Ед. изм.:
    100 м2'
  - 'passage: Отделочные работы. Окраска масляными составами трубопроводов по изоляции.
    Ед. изм.: 100 м2'
- source_sentence: 'query: покрытие водными растворами'
  sentences:
  - 'passage: Деревянные конструкции. Антисептирование водными растворами: стен. Ед.
    изм.: 100 м2. Нанесение готового состава на поверхность'
  - 'passage: Отделочные работы. Улучшенная окраска масляными составами по сборным
    конструкциям: стен, подготовленных под окраску. Ед. изм.: 100 м2'
  - 'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий
    по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность'
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on intfloat/multilingual-e5-base

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

## Model Details

### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision d128750597153bb5987e10b1c3493a34e5a4502a -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **Supported Modality:** Text
<!-- - **Training Dataset:** Unknown -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### Model Sources

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

### 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': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
  (2): 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("malma0/e5-gesn")
# Run inference
sentences = [
    'query: покрытие водными растворами',
    'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность',
    'passage: Деревянные конструкции. Антисептирование водными растворами: стен. Ед. изм.: 100 м2. Нанесение готового состава на поверхность',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5590, 0.3800],
#         [0.5590, 1.0000, 0.7719],
#         [0.3800, 0.7719, 1.0000]])
```
<!--
### 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

#### Unnamed Dataset

* Size: 10,134 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: 8 tokens</li><li>mean: 12.45 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 27 tokens</li><li>mean: 34.68 tokens</li><li>max: 40 tokens</li></ul> | <ul><li>min: 30 tokens</li><li>mean: 47.42 tokens</li><li>max: 107 tokens</li></ul> |
* Samples:
  | anchor                                       | positive                                                                           | negative                                                                                                                                       |
  |:---------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------|
  | <code>query: обои на потолок</code>          | <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> | <code>passage: Отделочные работы. Обивка дверей облицовочными материалами по войлоку. Ед. изм.: 100 м2</code>                                  |
  | <code>query: поменять обои в квартире</code> | <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> | <code>passage: Отделочные работы. Обивка дверей облицовочными материалами по войлоку. Ед. изм.: 100 м2</code>                                  |
  | <code>query: прораб обои потолки</code>      | <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> | <code>passage: Отделочные работы. Оклейка обоями стен по монолитной штукатурке и бетону: простыми и средней плотности. Ед. изм.: 100 м2</code> |
* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
  ```json
  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "mini_batch_size": 32,
      "mini_batch_num_tokens": null,
      "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`: 128
- `num_train_epochs`: 1
- `learning_rate`: 2e-05
- `warmup_steps`: 0.1
- `fp16`: True
- `seed`: 0
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `per_device_train_batch_size`: 128
- `num_train_epochs`: 1
- `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`: 0
- `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`: False
- `dataloader_num_workers`: 0
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `dataloader_prefetch_factor`: None
- `dataloader_multiprocessing_context`: None
- `dataloader_in_order`: True
- `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
- `local_rank`: -1
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
- `warmup_ratio`: None

</details>

### Training Logs
| Epoch | Step | Training Loss |
|:-----:|:----:|:-------------:|
| 0.125 | 10   | 4.3797        |
| 0.25  | 20   | 2.6564        |
| 0.375 | 30   | 1.9438        |
| 0.5   | 40   | 1.7043        |
| 0.625 | 50   | 1.5870        |
| 0.75  | 60   | 1.5707        |
| 0.875 | 70   | 1.4605        |
| 1.0   | 80   | 1.5043        |


### Training Time
- **Training**: 6.4 minutes

### Framework Versions
- Python: 3.13.15
- Sentence Transformers: 5.7.0
- Transformers: 5.16.1
- PyTorch: 2.11.0+cu128
- Accelerate: 1.14.0
- Datasets: 4.8.5
- Tokenizers: 0.23.1

## Additional Resources

- [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models.
- [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss.
- [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors.
- [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API.
- [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough.

## 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",
}
```

#### CachedMultipleNegativesRankingLoss
```bibtex
@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}
```

#### MultipleNegativesRankingLoss
```bibtex
@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.*
-->

	---
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- dense
	- generated_from_trainer
	- dataset_size:10134
	- loss:CachedMultipleNegativesRankingLoss
	- loss:MultipleNegativesRankingLoss
	base_model: intfloat/multilingual-e5-base
	widget:
	- source_sentence: 'query: грунтовка стен квартиры'
	sentences:
	- 'passage: Отделочные работы. Окраска фасадов с люлек по подготовленной поверхности:
	силикатная. Ед. изм.: 100 м2'
	- 'passage: Отделочные работы. Покрытие поверхностей грунтовкой глубокого проникновения:
	за 1 раз стен. Ед. изм.: 100 м2'
	- 'passage: Отделочные работы. Покрытие поверхностей грунтовкой глубокого проникновения:
	за 2 раза стен. Ед. изм.: 100 м2'
	- source_sentence: 'query: установ шкафных дверей'
	sentences:
	- 'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий
	по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность'
	- 'passage: Деревянные конструкции. Установка дверных блоков: антресольных. Ед.
	изм.: 10 шт. Установка и крепление блоков антресольных'
	- 'passage: Деревянные конструкции. Установка дверных блоков: шкафных. Ед. изм.:
	10 шт. Установка и крепление блоков дверных шкафных'
	- source_sentence: 'query: пергаминовая обшивка стены 100м2'
	sentences:
	- 'passage: Деревянные конструкции. Обшивка каркасных стен: досками обшивки. Ед.
	изм.: 100 м2. Обшивка стен пергамином, досками. Обшивка углов и пересечений'
	- 'passage: Деревянные конструкции. Обшивка каркасных стен: пергамином. Ед. изм.:
	100 м2. Обшивка стен пергамином'
	- 'passage: Отделочные работы. Огнезащитная пропитка текстильных (тканевых) покрытий.
	Ед. изм.: 100 м2. Огнезащитная пропитка текстильных покрытий'
	- source_sentence: 'query: окраска решеток для дачи'
	sentences:
	- 'passage: Отделочные работы. Окраска фасадов с люлек с подготовкой поверхности:
	силикатная. Ед. изм.: 100 м2'
	- 'passage: Отделочные работы. Масляная окраска металлических поверхностей: решеток,
	переплетов, труб диаметром менее 50 мм и т.п., количество окрасок 2. Ед. изм.:
	100 м2'
	- 'passage: Отделочные работы. Окраска масляными составами трубопроводов по изоляции.
	Ед. изм.: 100 м2'
	- source_sentence: 'query: покрытие водными растворами'
	sentences:
	- 'passage: Деревянные конструкции. Антисептирование водными растворами: стен. Ед.
	изм.: 100 м2. Нанесение готового состава на поверхность'
	- 'passage: Отделочные работы. Улучшенная окраска масляными составами по сборным
	конструкциям: стен, подготовленных под окраску. Ед. изм.: 100 м2'
	- 'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий
	по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность'
	pipeline_tag: sentence-similarity
	library_name: sentence-transformers
	---

	# SentenceTransformer based on intfloat/multilingual-e5-base

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision d128750597153bb5987e10b1c3493a34e5a4502a -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 dimensions
	- Similarity Function: Cosine Similarity
	- Supported Modality: Text
	<!-- - Training Dataset: Unknown -->
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### Model Sources

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

	### 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': 'XLMRobertaModel'})
	(1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', 'include_prompt': True})
	(2): 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("malma0/e5-gesn")
	# Run inference
	sentences = [
	'query: покрытие водными растворами',
	'passage: Деревянные конструкции. Антисептирование водными растворами: покрытий по фермам. Ед. изм.: 100 м2. Нанесение готового состава на поверхность',
	'passage: Деревянные конструкции. Антисептирование водными растворами: стен. Ед. изм.: 100 м2. Нанесение готового состава на поверхность',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities)
	# tensor([[1.0000, 0.5590, 0.3800],
	# [0.5590, 1.0000, 0.7719],
	# [0.3800, 0.7719, 1.0000]])
	```
	<!--
	### 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

	#### Unnamed Dataset

	* Size: 10,134 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: 8 tokens</li><li>mean: 12.45 tokens</li><li>max: 21 tokens</li></ul> \| <ul><li>min: 27 tokens</li><li>mean: 34.68 tokens</li><li>max: 40 tokens</li></ul> \| <ul><li>min: 30 tokens</li><li>mean: 47.42 tokens</li><li>max: 107 tokens</li></ul> \|
	* Samples:
	\| anchor \| positive \| negative \|
	\|:---------------------------------------------\|:-----------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>query: обои на потолок</code> \| <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> \| <code>passage: Отделочные работы. Обивка дверей облицовочными материалами по войлоку. Ед. изм.: 100 м2</code> \|
	\| <code>query: поменять обои в квартире</code> \| <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> \| <code>passage: Отделочные работы. Обивка дверей облицовочными материалами по войлоку. Ед. изм.: 100 м2</code> \|
	\| <code>query: прораб обои потолки</code> \| <code>passage: Отделочные работы. Оклейка обоями потолков. Ед. изм.: 100 м2</code> \| <code>passage: Отделочные работы. Оклейка обоями стен по монолитной штукатурке и бетону: простыми и средней плотности. Ед. изм.: 100 м2</code> \|
	* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
	```json
	{
	"scale": 20.0,
	"similarity_fct": "cos_sim",
	"mini_batch_size": 32,
	"mini_batch_num_tokens": null,
	"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`: 128
	- `num_train_epochs`: 1
	- `learning_rate`: 2e-05
	- `warmup_steps`: 0.1
	- `fp16`: True
	- `seed`: 0
	- `batch_sampler`: no_duplicates

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

	- `per_device_train_batch_size`: 128
	- `num_train_epochs`: 1
	- `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`: 0
	- `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`: False
	- `dataloader_num_workers`: 0
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `dataloader_prefetch_factor`: None
	- `dataloader_multiprocessing_context`: None
	- `dataloader_in_order`: True
	- `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
	- `local_rank`: -1
	- `prompts`: None
	- `batch_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional
	- `router_mapping`: {}
	- `learning_rate_mapping`: {}
	- `warmup_ratio`: None

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \|
	\|:-----:\|:----:\|:-------------:\|
	\| 0.125 \| 10 \| 4.3797 \|
	\| 0.25 \| 20 \| 2.6564 \|
	\| 0.375 \| 30 \| 1.9438 \|
	\| 0.5 \| 40 \| 1.7043 \|
	\| 0.625 \| 50 \| 1.5870 \|
	\| 0.75 \| 60 \| 1.5707 \|
	\| 0.875 \| 70 \| 1.4605 \|
	\| 1.0 \| 80 \| 1.5043 \|


	### Training Time
	- Training: 6.4 minutes

	### Framework Versions
	- Python: 3.13.15
	- Sentence Transformers: 5.7.0
	- Transformers: 5.16.1
	- PyTorch: 2.11.0+cu128
	- Accelerate: 1.14.0
	- Datasets: 4.8.5
	- Tokenizers: 0.23.1

	## Additional Resources

	- [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models.
	- [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss.
	- [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors.
	- [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API.
	- [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough.

	## 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",
	}
	```

	#### CachedMultipleNegativesRankingLoss
	```bibtex
	@misc{gao2021scaling,
	title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
	author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
	year={2021},
	eprint={2101.06983},
	archivePrefix={arXiv},
	primaryClass={cs.LG}
	}
	```

	#### MultipleNegativesRankingLoss
	```bibtex
	@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.
	-->