Model save

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,719 @@
+---
+base_model: intfloat/multilingual-e5-base
+datasets:
+- rztk/rozetka_positive_pairs
+language: []
+library_name: sentence-transformers
+metrics:
+- dot_accuracy@1
+- dot_accuracy@3
+- dot_accuracy@5
+- dot_accuracy@10
+- dot_precision@1
+- dot_precision@3
+- dot_precision@5
+- dot_precision@10
+- dot_recall@1
+- dot_recall@3
+- dot_recall@5
+- dot_recall@10
+- dot_ndcg@10
+- dot_mrr@10
+- dot_map@100
+- dot_ndcg@1
+- dot_mrr@1
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:44800
+- loss:RZTKMatryoshka2dLoss
+widget:
+- source_sentence: папка планшет
+  sentences:
+  - <category>Сифони</category><brand>Alcaplast</brand><options><option_title>Гарантія</option_title><option_value>24
+    місяці офіційної гарантії від виробника</option_value><option_title>Кількість
+    вантажних місць</option_title><option_value>1</option_value><option_title>Країна-виробник
+    товару</option_title><option_value>Чехія</option_value><option_title>Призначення</option_title><option_value>Для
+    душових піддонів</option_value><option_title>Матеріал</option_title><option_value>Пластик</option_value><option_title>Вид</option_title><option_value>Пляшковий</option_value><option_title>Під'єднані
+    до пральної машини</option_title><option_value>Немає</option_value><option_title>Колір</option_title><option_value>Білий
+    + Хром</option_value><option_title>Тип</option_title><option_value>Сифон</option_value><option_title>Теги</option_title><option_value>недорогий
+    сифон</option_value><option_title>відкривання/перекриття зливних отворів</option_title><option_value>Неперекривний</option_value><option_title>Різновид
+    гідрозатвора</option_title><option_value>Мокрий (без мембрани)</option_value><option_title>Діаметр
+    під'єднання</option_title><option_value>90 мм</option_value><option_title>Діаметр
+    патрубка в каналізацію</option_title><option_value>40 мм</option_value><option_title>Переливання</option_title><option_value>Без
+    функції переливу</option_value><option_title>Тип гарантійного талона</option_title><option_value>Гарантія
+    по чеку</option_value><option_title>Доставка Premium</option_title><option_title>Доставка</option_title><option_value>Доставка
+    в магазини ROZETKA</option_value></options>
+  - Сифон для душевого поддона ALCA PLAST A49CR (8594045930627)
+  - <category>Папки-планшеты</category><brand>iTEM</brand><options><option_title>Формат</option_title><option_value>A4</option_value><option_title>Материал</option_title><option_value>Картон</option_value><option_title>Страна
+    регистрации бренда</option_title><option_value>Украина</option_value><option_title>Страна-производитель
+    товара</option_title><option_value>Украина</option_value></options>
+- source_sentence: вино игристое
+  sentences:
+  - Женские резиновые сапоги Demar HAWAI LADY 0076V 36 (23.8 см) Черные (5901232011374)
+  - Верстак складной Ryobi RWB01
+  - Вино ігристе Adamanti біле напівсолодке 0.75 л 12.5% (4860004073259)
+- source_sentence: елка искуственная
+  sentences:
+  - <category>Підставки та столики для ноутбуків</category><brand>UFT</brand><options><option_title>Вид</option_title><option_value>Столики</option_value><option_title>Охолодження</option_title><option_value>Активне</option_value><option_title>Максимальна
+    діагональ ноутбука</option_title><option_value>16"</option_value><option_title>Колір</option_title><option_value>Синій</option_value><option_title>Матеріал</option_title><option_value>Метал</option_value><option_title>Кількість
+    вантажних місць</option_title><option_value>1</option_value></options>
+  - Декоративная елка, 90см (122-F12)
+  - Конструктор LEGO Minecraft Гарбузова ферма 257 деталей (21248)
+- source_sentence: переходник
+  sentences:
+  - Штучна ялинка «Ніка» 1.8 м
+  - Набір інструментів NEO торцевих головок 108 шт., 1, 4, 1/2 "CrV (08-666)
+  - <category>Кабели и адаптеры</category><brand>Protech</brand><options><option_title>Гарантия</option_title><option_value>6
+    месяцев</option_value><option_title>Длина</option_title><option_value>0.2 м</option_value><option_title>Тип</option_title><option_value>Адаптеры
+    (Переходники)</option_value><option_title>Количество грузовых мест</option_title><option_value>1</option_value><option_title>Страна
+    регистрации бренда</option_title><option_value>Китай</option_value><option_title>Страна-производитель
+    товара</option_title><option_value>Китай</option_value><option_title>Цвет</option_title><option_value>Серебристый</option_value><option_title>Тип
+    гарантийного талона</option_title><option_value>Гарантия по чеку</option_value><option_title>Доставка
+    Premium</option_title><option_title>Тип коннектора 1</option_title><option_value>USB
+    Type-C</option_value><option_title>Тип коннектора 2</option_title><option_value>USB</option_value></options>
+- source_sentence: поилка для детей
+  sentences:
+  - Шафа розпашній Fenster Оксфорд Лагуна
+  - <category>Аксессуары для наушников</category><brand>ArmorStandart</brand><options><option_title>Гарантия</option_title><option_value>14
+    дней</option_value><option_title>Тип наушников</option_title><option_value>Вкладыши</option_value><option_title>Вид</option_title><option_value>Чехлы</option_value><option_title>Цвет</option_title><option_value>Dark
+    Green</option_value><option_title>Количество грузовых мест</option_title><option_value>1</option_value><option_title>Страна
+    регистрации бренда</option_title><option_value>Украина</option_value><option_title>Страна-производитель
+    товара</option_title><option_value>Китай</option_value><option_title>Тип гарантийного
+    талона</option_title><option_value>Гарантия по чеку</option_value><option_title>Материал</option_title><option_value>Силикон</option_value><option_title>Доставка
+    Premium</option_title><option_title>Совместимая серия</option_title><option_value>Apple
+    AirPods</option_value><option_title>Доставка</option_title><option_value>Доставка
+    в магазины ROZETKA</option_value></options>
+  - <category>Поїльники та непроливайки</category><brand>Nuk</brand><options><option_title>Стать
+    дитини</option_title><option_value>Хлопчик</option_value><option_title>Стать дитини</option_title><option_value>Дівчинка</option_value><option_title>Кількість
+    вантажних місць</option_title><option_value>1</option_value><option_title>Країна
+    реєстрації бренда</option_title><option_value>Німеччина</option_value><option_title>Країна-виробник
+    товару</option_title><option_value>Німеччина</option_value><option_title>Об'єм,
+    мл</option_title><option_value>300</option_value><option_title>Матеріал</option_title><option_value>Пластик</option_value><option_title>Колір</option_title><option_value>Блакитний</option_value><option_title>Тип</option_title><option_value>Поїльник</option_value><option_title>Тип
+    гарантійного талона</option_title><option_value>Гарантія по чеку</option_value><option_title>Доставка
+    Premium</option_title></options>
+model-index:
+- name: SentenceTransformer based on intfloat/multilingual-e5-base
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: rusisms uk title
+      type: rusisms-uk-title
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.5428571428571428
+      name: Dot Accuracy@1
+    - type: dot_accuracy@3
+      value: 0.6888888888888889
+      name: Dot Accuracy@3
+    - type: dot_accuracy@5
+      value: 0.7492063492063492
+      name: Dot Accuracy@5
+    - type: dot_accuracy@10
+      value: 0.8
+      name: Dot Accuracy@10
+    - type: dot_precision@1
+      value: 0.5428571428571428
+      name: Dot Precision@1
+    - type: dot_precision@3
+      value: 0.5216931216931217
+      name: Dot Precision@3
+    - type: dot_precision@5
+      value: 0.5034920634920634
+      name: Dot Precision@5
+    - type: dot_precision@10
+      value: 0.47682539682539676
+      name: Dot Precision@10
+    - type: dot_recall@1
+      value: 0.009248137199056617
+      name: Dot Recall@1
+    - type: dot_recall@3
+      value: 0.023803562659985587
+      name: Dot Recall@3
+    - type: dot_recall@5
+      value: 0.03509680885707945
+      name: Dot Recall@5
+    - type: dot_recall@10
+      value: 0.05987127144737185
+      name: Dot Recall@10
+    - type: dot_ndcg@10
+      value: 0.4936504584984999
+      name: Dot Ndcg@10
+    - type: dot_mrr@10
+      value: 0.6286608717561099
+      name: Dot Mrr@10
+    - type: dot_map@100
+      value: 0.14035920755466383
+      name: Dot Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: 'rusisms uk title  matryoshka dim 768  '
+      type: rusisms-uk-title--matryoshka_dim-768--
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.1619047619047619
+      name: Dot Accuracy@1
+    - type: dot_precision@1
+      value: 0.1619047619047619
+      name: Dot Precision@1
+    - type: dot_recall@1
+      value: 0.0020219082190057404
+      name: Dot Recall@1
+    - type: dot_ndcg@1
+      value: 0.1619047619047619
+      name: Dot Ndcg@1
+    - type: dot_mrr@1
+      value: 0.1619047619047619
+      name: Dot Mrr@1
+    - type: dot_map@100
+      value: 0.02128340409566104
+      name: Dot Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: 'rusisms uk title  matryoshka dim 512  '
+      type: rusisms-uk-title--matryoshka_dim-512--
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.14603174603174604
+      name: Dot Accuracy@1
+    - type: dot_precision@1
+      value: 0.14603174603174604
+      name: Dot Precision@1
+    - type: dot_recall@1
+      value: 0.0016964404522008209
+      name: Dot Recall@1
+    - type: dot_ndcg@1
+      value: 0.14603174603174604
+      name: Dot Ndcg@1
+    - type: dot_mrr@1
+      value: 0.14603174603174604
+      name: Dot Mrr@1
+    - type: dot_map@100
+      value: 0.015212846443877073
+      name: Dot Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: 'rusisms uk title  matryoshka dim 256  '
+      type: rusisms-uk-title--matryoshka_dim-256--
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.10158730158730159
+      name: Dot Accuracy@1
+    - type: dot_precision@1
+      value: 0.10158730158730159
+      name: Dot Precision@1
+    - type: dot_recall@1
+      value: 0.0012653450153450154
+      name: Dot Recall@1
+    - type: dot_ndcg@1
+      value: 0.10158730158730159
+      name: Dot Ndcg@1
+    - type: dot_mrr@1
+      value: 0.10158730158730159
+      name: Dot Mrr@1
+    - type: dot_map@100
+      value: 0.011952854173853285
+      name: Dot Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: 'rusisms uk title  matryoshka dim 128  '
+      type: rusisms-uk-title--matryoshka_dim-128--
+    metrics:
+    - type: dot_accuracy@1
+      value: 0.05396825396825397
+      name: Dot Accuracy@1
+    - type: dot_precision@1
+      value: 0.05396825396825397
+      name: Dot Precision@1
+    - type: dot_recall@1
+      value: 0.0007494719994719994
+      name: Dot Recall@1
+    - type: dot_ndcg@1
+      value: 0.05396825396825397
+      name: Dot Ndcg@1
+    - type: dot_mrr@1
+      value: 0.05396825396825397
+      name: Dot Mrr@1
+    - type: dot_map@100
+      value: 0.0053781586003166125
+      name: Dot Map@100
+---
+
+# 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) on the [rztk/rozetka_positive_pairs](https://huggingface.co/datasets/rztk/rozetka_positive_pairs) 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:** [intfloat/multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) <!-- at revision d13f1b27baf31030b7fd040960d60d909913633f -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [rztk/rozetka_positive_pairs](https://huggingface.co/datasets/rztk/rozetka_positive_pairs)
+<!-- - **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': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (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})
+  (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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'поилка для детей',
+    "<category>Поїльники та непроливайки</category><brand>Nuk</brand><options><option_title>Стать дитини</option_title><option_value>Хлопчик</option_value><option_title>Стать дитини</option_title><option_value>Дівчинка</option_value><option_title>Кількість вантажних місць</option_title><option_value>1</option_value><option_title>Країна реєстрації бренда</option_title><option_value>Німеччина</option_value><option_title>Країна-виробник товару</option_title><option_value>Німеччина</option_value><option_title>Об'єм, мл</option_title><option_value>300</option_value><option_title>Матеріал</option_title><option_value>Пластик</option_value><option_title>Колір</option_title><option_value>Блакитний</option_value><option_title>Тип</option_title><option_value>Поїльник</option_value><option_title>Тип гарантійного талона</option_title><option_value>Гарантія по чеку</option_value><option_title>Доставка Premium</option_title></options>",
+    'Шафа розпашній Fenster Оксфорд Лагуна',
+]
+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
+
+#### Information Retrieval
+* Dataset: `rusisms-uk-title`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric           | Value      |
+|:-----------------|:-----------|
+| dot_accuracy@1   | 0.5429     |
+| dot_accuracy@3   | 0.6889     |
+| dot_accuracy@5   | 0.7492     |
+| dot_accuracy@10  | 0.8        |
+| dot_precision@1  | 0.5429     |
+| dot_precision@3  | 0.5217     |
+| dot_precision@5  | 0.5035     |
+| dot_precision@10 | 0.4768     |
+| dot_recall@1     | 0.0092     |
+| dot_recall@3     | 0.0238     |
+| dot_recall@5     | 0.0351     |
+| dot_recall@10    | 0.0599     |
+| dot_ndcg@10      | 0.4937     |
+| dot_mrr@10       | 0.6287     |
+| **dot_map@100**  | **0.1404** |
+
+#### Information Retrieval
+* Dataset: `rusisms-uk-title--matryoshka_dim-768--`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric          | Value      |
+|:----------------|:-----------|
+| dot_accuracy@1  | 0.1619     |
+| dot_precision@1 | 0.1619     |
+| dot_recall@1    | 0.002      |
+| dot_ndcg@1      | 0.1619     |
+| dot_mrr@1       | 0.1619     |
+| **dot_map@100** | **0.0213** |
+
+#### Information Retrieval
+* Dataset: `rusisms-uk-title--matryoshka_dim-512--`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric          | Value      |
+|:----------------|:-----------|
+| dot_accuracy@1  | 0.146      |
+| dot_precision@1 | 0.146      |
+| dot_recall@1    | 0.0017     |
+| dot_ndcg@1      | 0.146      |
+| dot_mrr@1       | 0.146      |
+| **dot_map@100** | **0.0152** |
+
+#### Information Retrieval
+* Dataset: `rusisms-uk-title--matryoshka_dim-256--`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric          | Value     |
+|:----------------|:----------|
+| dot_accuracy@1  | 0.1016    |
+| dot_precision@1 | 0.1016    |
+| dot_recall@1    | 0.0013    |
+| dot_ndcg@1      | 0.1016    |
+| dot_mrr@1       | 0.1016    |
+| **dot_map@100** | **0.012** |
+
+#### Information Retrieval
+* Dataset: `rusisms-uk-title--matryoshka_dim-128--`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric          | Value      |
+|:----------------|:-----------|
+| dot_accuracy@1  | 0.054      |
+| dot_precision@1 | 0.054      |
+| dot_recall@1    | 0.0007     |
+| dot_ndcg@1      | 0.054      |
+| dot_mrr@1       | 0.054      |
+| **dot_map@100** | **0.0054** |
+
+<!--
+## 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
+
+#### rztk/rozetka_positive_pairs
+
+* Dataset: [rztk/rozetka_positive_pairs](https://huggingface.co/datasets/rztk/rozetka_positive_pairs)
+* Size: 44,800 training samples
+* Columns: <code>query</code> and <code>text</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                            | text                                                                                |
+  |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                              |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 7.18 tokens</li><li>max: 16 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 158.88 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                  | text                                                                                                                                                                                                                                                                                                                   |
+  |:-----------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>p smart z</code> | <code>TPU чехол Ultrathin Series 0,33 mm для Huawei P Smart Z Безбарвний (прозорий)</code>                                                                                                                                                                                                                             |
+  | <code>p smart z</code> | <code><category>Чохли для мобільних телефонів</category><options><option_title>Матеріал</option_title><option_value>Силікон</option_value><option_title>Колір</option_title><option_value>Transparent</option_value><option_title>Сумісна модель</option_title><option_value>P Smart Z</option_value></options></code> |
+  | <code>p smart z</code> | <code>TPU чехол Ultrathin Series 0,33mm для Huawei P Smart Z Бесцветный (прозрачный)</code>                                                                                                                                                                                                                            |
+* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
+  ```json
+  {
+      "loss": "RZTKMultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.0,
+      "prior_layers_weight": 1.0,
+      "kl_div_weight": 1.0,
+      "kl_temperature": 0.3,
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": 1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### rztk/rozetka_positive_pairs
+
+* Dataset: [rztk/rozetka_positive_pairs](https://huggingface.co/datasets/rztk/rozetka_positive_pairs)
+* Size: 4,480 evaluation samples
+* Columns: <code>query</code> and <code>text</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                            | text                                                                                 |
+  |:--------|:---------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                               |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 6.29 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 12 tokens</li><li>mean: 161.36 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                         | text                                                                                                                                                                                                                                                                                                                                                                                                    |
+  |:------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>кошелек женский</code> | <code>Портмоне BAELLERRY Forever N2345 Черный (020354)</code>                                                                                                                                                                                                                                                                                                                                           |
+  | <code>кошелек женский</code> | <code><category>Гаманці</category><brand>Baellerry</brand><options><option_title>Для кого</option_title><option_value>Для жінок</option_value><option_title>Вид</option_title><option_value>Портмоне</option_value><option_title>Матеріал</option_title><option_value>Штучна шкіра</option_value><option_title>Країна-виробник товару</option_title><option_value>Китай</option_value></options></code> |
+  | <code>кошелек женский</code> | <code>Портмоне BAELLERRY Forever N2345 Черный (020354)</code>                                                                                                                                                                                                                                                                                                                                           |
+* Loss: <code>sentence_transformers_training.model.matryoshka2d_loss.RZTKMatryoshka2dLoss</code> with these parameters:
+  ```json
+  {
+      "loss": "RZTKMultipleNegativesRankingLoss",
+      "n_layers_per_step": 1,
+      "last_layer_weight": 1.0,
+      "prior_layers_weight": 1.0,
+      "kl_div_weight": 1.0,
+      "kl_temperature": 0.3,
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": 1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 112
+- `per_device_eval_batch_size`: 112
+- `torch_empty_cache_steps`: 30
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1.0
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `bf16_full_eval`: True
+- `tf32`: True
+- `dataloader_num_workers`: 2
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+- `push_to_hub`: 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`: 112
+- `per_device_eval_batch_size`: 112
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: 30
+- `learning_rate`: 2e-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`: 1.0
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: True
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: True
+- `dataloader_num_workers`: 2
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `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`: adafactor
+- `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`: True
+- `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
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `ddp_static_graph`: False
+- `ddp_comm_hook`: bf16
+- `gradient_as_bucket_view`: False
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | loss       | rusisms-uk-title--matryoshka_dim-128--_dot_map@100 | rusisms-uk-title--matryoshka_dim-256--_dot_map@100 | rusisms-uk-title--matryoshka_dim-512--_dot_map@100 | rusisms-uk-title--matryoshka_dim-768--_dot_map@100 | rusisms-uk-title_dot_map@100 |
+|:-------:|:------:|:-------------:|:----------:|:--------------------------------------------------:|:--------------------------------------------------:|:--------------------------------------------------:|:--------------------------------------------------:|:----------------------------:|
+| 0.1     | 10     | 6.6103        | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.2     | 20     | 5.524         | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.3     | 30     | 4.759         | 3.6444     | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.4     | 40     | 4.5195        | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.5     | 50     | 3.6598        | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.6     | 60     | 3.7912        | 2.8962     | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.7     | 70     | 3.9935        | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| 0.8     | 80     | 3.3929        | -          | -                                                  | -                                                  | -                                                  | -                                                  | -                            |
+| **0.9** | **90** | **3.6101**    | **2.6889** | **-**                                              | **-**                                              | **-**                                              | **-**                                              | **-**                        |
+| 1.0     | 100    | 3.8753        | -          | 0.0054                                             | 0.0120                                             | 0.0152                                             | 0.0213                                             | 0.1404                       |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.6
+- Sentence Transformers: 3.0.1
+- Transformers: 4.45.1
+- PyTorch: 2.4.1
+- Accelerate: 0.34.2
+- Datasets: 3.0.0
+- Tokenizers: 0.20.0
+
+## 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",
+}
+```
+
+<!--
+## 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.*
+-->

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.45.1",
+    "pytorch": "2.4.1"
+  },
+  "prompts": {
+    "query": "query: ",
+    "passage": "passage: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce0c1d3dfc935e339f6522529d559b07ece28ba9ab8130bac45439ac5e6fb4c
+oid sha256:48b0bc6d823b415718596e69b55f4a07d986360bb1bbec1b008e0f665ba8dbd7
 size 556109872

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}