Add new SentenceTransformer model

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
+}

2_Dense/config.json

@@ -0,0 +1 @@
+{"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e369ffa6cabab73d45ccfe57b15306f60df8672a95facbcaf940343382ad8719
+size 1575072

README.md

@@ -0,0 +1,1019 @@
+---
+language:
+- de
+- en
+- es
+- fr
+- it
+- nl
+- pl
+- pt
+- ru
+- zh
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:51741
+- loss:CoSENTLoss
+base_model: RomainDarous/pre_training_original_model
+widget:
+- source_sentence: Starsza para azjatycka pozuje z noworodkiem przy stole obiadowym.
+  sentences:
+  - Koszykarz ma zamiar zdobyć punkty dla swojej drużyny.
+  - Grupa starszych osób pozuje wokół stołu w jadalni.
+  - Możliwe, że układ słoneczny taki jak nasz może istnieć poza galaktyką.
+- source_sentence: Englisch arbeitet überall mit Menschen, die Dinge kaufen und verkaufen,
+    und in der Gastfreundschaft und im Tourismusgeschäft.
+  sentences:
+  - Ich bin in Maharashtra (einschließlich Mumbai) und Andhra Pradesh herumgereist,
+    und ich hatte kein Problem damit, nur mit Englisch auszukommen.
+  - 'Ein griechischsprachiger Sklave (δούλος, doulos) würde seinen Herrn, glaube ich,
+    κύριος nennen (translit: kurios; Herr, Herr, Herr, Herr; Vokativform: κύριε).'
+  - Das Paar lag auf dem Bett.
+- source_sentence: Si vous vous comprenez et comprenez votre ennemi, vous aurez beaucoup
+    plus de chances de gagner n'importe quelle bataille.
+  sentences:
+  - 'Outre les probabilités de gagner une bataille théorique, cette citation a une
+    autre signification : l''importance de connaître/comprendre les autres.'
+  - Une femme et un chien se promènent ensemble.
+  - Un homme joue de la guitare.
+- source_sentence: Un homme joue de la harpe.
+  sentences:
+  - Une femme joue de la guitare.
+  - une femme a un enfant.
+  - Un groupe de personnes est debout et assis sur le sol la nuit.
+- source_sentence: Dois cães a lutar na neve.
+  sentences:
+  - Dois cães brincam na neve.
+  - Pode sempre perguntar, então é a escolha do autor a aceitar ou não.
+  - Um gato está a caminhar sobre chão de madeira dura.
+datasets:
+- PhilipMay/stsb_multi_mt
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on RomainDarous/pre_training_original_model
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts eval
+      type: sts-eval
+    metrics:
+    - type: pearson_cosine
+      value: 0.649351613026743
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6712113629733555
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6648874938903813
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6859979455545288
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6574990404767099
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6819347305734045
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6482851200513846
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6739057551228634
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.657747388798702
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6797522820481435
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.580138787555855
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6025843591291092
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6445711160678915
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6738244742184887
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6060638359389463
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6210827296807453
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6672294139281439
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6864882079409924
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.6279093972489541
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6320355986028895
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6433522116833627
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.658000076471118
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6271929274305698
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6229896619978917
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6391062028706688
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6417698712729121
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.622947898324511
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6179788172853071
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.5903164175964553
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5887507390354803
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.640080846863563
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6391082728350455
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6172821161239198
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6180296923884917
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.6607896399210559
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.6616750284666137
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on RomainDarous/pre_training_original_model
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [RomainDarous/pre_training_original_model](https://huggingface.co/RomainDarous/pre_training_original_model) on the [multi_stsb_de](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_es](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_fr](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_it](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_nl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_pl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_pt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt), [multi_stsb_ru](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) and [multi_stsb_zh](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) datasets. It maps sentences & paragraphs to a 512-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:** [RomainDarous/pre_training_original_model](https://huggingface.co/RomainDarous/pre_training_original_model) <!-- at revision 880d5ef9d016fb1257687b6b61da19f4978b0f0c -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 512 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - [multi_stsb_de](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_es](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_fr](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_it](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_nl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_pl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_pt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_ru](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+    - [multi_stsb_zh](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt)
+- **Languages:** de, en, es, fr, it, nl, pl, pt, ru, zh
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
+  (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): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+)
+```
+
+## 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("RomainDarous/multists_finetuned_original_model")
+# Run inference
+sentences = [
+    'Dois cães a lutar na neve.',
+    'Dois cães brincam na neve.',
+    'Pode sempre perguntar, então é a escolha do autor a aceitar ou não.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 512]
+
+# 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
+
+* Datasets: `sts-eval`, `sts-test`, `sts-test`, `sts-test`, `sts-test`, `sts-test`, `sts-test`, `sts-test`, `sts-test` and `sts-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-eval   | sts-test   |
+|:--------------------|:-----------|:-----------|
+| pearson_cosine      | 0.6494     | 0.6608     |
+| **spearman_cosine** | **0.6712** | **0.6617** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.6649    |
+| **spearman_cosine** | **0.686** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6575     |
+| **spearman_cosine** | **0.6819** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6483     |
+| **spearman_cosine** | **0.6739** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6577     |
+| **spearman_cosine** | **0.6798** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.5801     |
+| **spearman_cosine** | **0.6026** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6446     |
+| **spearman_cosine** | **0.6738** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6061     |
+| **spearman_cosine** | **0.6211** |
+
+#### Semantic Similarity
+
+* Dataset: `sts-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.6672     |
+| **spearman_cosine** | **0.6865** |
+
+<!--
+## 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
+
+#### multi_stsb_de
+
+* Dataset: [multi_stsb_de](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 12.05 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.01 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                      | sentence2                                                                 | score                           |
+  |:---------------------------------------------------------------|:--------------------------------------------------------------------------|:--------------------------------|
+  | <code>Ein Flugzeug hebt gerade ab.</code>                      | <code>Ein Flugzeug hebt gerade ab.</code>                                 | <code>1.0</code>                |
+  | <code>Ein Mann spielt eine große Flöte.</code>                 | <code>Ein Mann spielt eine Flöte.</code>                                  | <code>0.7599999904632568</code> |
+  | <code>Ein Mann streicht geriebenen Käse auf eine Pizza.</code> | <code>Ein Mann streicht geriebenen Käse auf eine ungekochte Pizza.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_es
+
+* Dataset: [multi_stsb_es](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.28 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.14 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                       | sentence2                                                             | score                           |
+  |:----------------------------------------------------------------|:----------------------------------------------------------------------|:--------------------------------|
+  | <code>Un avión está despegando.</code>                          | <code>Un avión está despegando.</code>                                | <code>1.0</code>                |
+  | <code>Un hombre está tocando una gran flauta.</code>            | <code>Un hombre está tocando una flauta.</code>                       | <code>0.7599999904632568</code> |
+  | <code>Un hombre está untando queso rallado en una pizza.</code> | <code>Un hombre está untando queso rallado en una pizza cruda.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_fr
+
+* Dataset: [multi_stsb_fr](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 12.47 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.37 tokens</li><li>max: 31 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                            | score                           |
+  |:-----------------------------------------------------------|:---------------------------------------------------------------------|:--------------------------------|
+  | <code>Un avion est en train de décoller.</code>            | <code>Un avion est en train de décoller.</code>                      | <code>1.0</code>                |
+  | <code>Un homme joue d'une grande flûte.</code>             | <code>Un homme joue de la flûte.</code>                              | <code>0.7599999904632568</code> |
+  | <code>Un homme étale du fromage râpé sur une pizza.</code> | <code>Un homme étale du fromage râpé sur une pizza non cuite.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_it
+
+* Dataset: [multi_stsb_it](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.92 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.81 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                 | sentence2                                                                           | score                           |
+  |:--------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:--------------------------------|
+  | <code>Un aereo sta decollando.</code>                                     | <code>Un aereo sta decollando.</code>                                               | <code>1.0</code>                |
+  | <code>Un uomo sta suonando un grande flauto.</code>                       | <code>Un uomo sta suonando un flauto.</code>                                        | <code>0.7599999904632568</code> |
+  | <code>Un uomo sta spalmando del formaggio a pezzetti su una pizza.</code> | <code>Un uomo sta spalmando del formaggio a pezzetti su una pizza non cotta.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_nl
+
+* Dataset: [multi_stsb_nl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 12.12 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.04 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                               | sentence2                                                           | score                           |
+  |:--------------------------------------------------------|:--------------------------------------------------------------------|:--------------------------------|
+  | <code>Er gaat een vliegtuig opstijgen.</code>           | <code>Er gaat een vliegtuig opstijgen.</code>                       | <code>1.0</code>                |
+  | <code>Een man speelt een grote fluit.</code>            | <code>Een man speelt fluit.</code>                                  | <code>0.7599999904632568</code> |
+  | <code>Een man smeert geraspte kaas op een pizza.</code> | <code>Een man strooit geraspte kaas op een ongekookte pizza.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_pl
+
+* Dataset: [multi_stsb_pl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 13.24 tokens</li><li>max: 46 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.08 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                  | sentence2                                                               | score                           |
+  |:-----------------------------------------------------------|:------------------------------------------------------------------------|:--------------------------------|
+  | <code>Samolot wystartował.</code>                          | <code>Samolot wystartował.</code>                                       | <code>1.0</code>                |
+  | <code>Człowiek gra na dużym flecie.</code>                 | <code>Człowiek gra na flecie.</code>                                    | <code>0.7599999904632568</code> |
+  | <code>Mężczyzna rozsiewa na pizzy rozdrobniony ser.</code> | <code>Mężczyzna rozsiewa rozdrobniony ser na niegotowanej pizzy.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_pt
+
+* Dataset: [multi_stsb_pt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 13.0 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 12.99 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                         | sentence2                                                                         | score                           |
+  |:------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------|
+  | <code>Um avião está a descolar.</code>                            | <code>Um avião aéreo está a descolar.</code>                                      | <code>1.0</code>                |
+  | <code>Um homem está a tocar uma grande flauta.</code>             | <code>Um homem está a tocar uma flauta.</code>                                    | <code>0.7599999904632568</code> |
+  | <code>Um homem está a espalhar queijo desfiado numa pizza.</code> | <code>Um homem está a espalhar queijo desfiado sobre uma pizza não cozida.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_ru
+
+* Dataset: [multi_stsb_ru](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 12.66 tokens</li><li>max: 47 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 12.67 tokens</li><li>max: 36 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                       | sentence2                                                            | score                           |
+  |:------------------------------------------------|:---------------------------------------------------------------------|:--------------------------------|
+  | <code>Самолет взлетает.</code>                  | <code>Взлетает самолет.</code>                                       | <code>1.0</code>                |
+  | <code>Человек играет на большой флейте.</code>  | <code>Человек играет на флейте.</code>                               | <code>0.7599999904632568</code> |
+  | <code>Мужчина разбрасывает сыр на пиццу.</code> | <code>Мужчина разбрасывает измельченный сыр на вареную пиццу.</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_zh
+
+* Dataset: [multi_stsb_zh](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 12.55 tokens</li><li>max: 37 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.73 tokens</li><li>max: 28 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.45</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                     | sentence2                         | score                           |
+  |:------------------------------|:----------------------------------|:--------------------------------|
+  | <code>一架飞机正在起飞。</code>        | <code>一架飞机正在起飞。</code>            | <code>1.0</code>                |
+  | <code>一个男人正在吹一支大笛子。</code>    | <code>一个人在吹笛子。</code>             | <code>0.7599999904632568</code> |
+  | <code>一名男子正在比萨饼上涂抹奶酪丝。</code> | <code>一名男子正在将奶酪丝涂抹在未熟的披萨上。</code> | <code>0.7599999904632568</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Datasets
+
+#### multi_stsb_de
+
+* Dataset: [multi_stsb_de](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 18.96 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.01 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                    | sentence2                                                  | score                          |
+  |:-------------------------------------------------------------|:-----------------------------------------------------------|:-------------------------------|
+  | <code>Ein Mann mit einem Schutzhelm tanzt.</code>            | <code>Ein Mann mit einem Schutzhelm tanzt.</code>          | <code>1.0</code>               |
+  | <code>Ein kleines Kind reitet auf einem Pferd.</code>        | <code>Ein Kind reitet auf einem Pferd.</code>              | <code>0.949999988079071</code> |
+  | <code>Ein Mann verfüttert eine Maus an eine Schlange.</code> | <code>Der Mann füttert die Schlange mit einer Maus.</code> | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_es
+
+* Dataset: [multi_stsb_es](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 18.41 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 18.24 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                             | sentence2                                                            | score                          |
+  |:----------------------------------------------------------------------|:---------------------------------------------------------------------|:-------------------------------|
+  | <code>Un hombre con un casco está bailando.</code>                    | <code>Un hombre con un casco está bailando.</code>                   | <code>1.0</code>               |
+  | <code>Un niño pequeño está montando a caballo.</code>                 | <code>Un niño está montando a caballo.</code>                        | <code>0.949999988079071</code> |
+  | <code>Un hombre está alimentando a una serpiente con un ratón.</code> | <code>El hombre está alimentando a la serpiente con un ratón.</code> | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_fr
+
+* Dataset: [multi_stsb_fr](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 19.77 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 19.62 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                | sentence2                                                                   | score                          |
+  |:-------------------------------------------------------------------------|:----------------------------------------------------------------------------|:-------------------------------|
+  | <code>Un homme avec un casque de sécurité est en train de danser.</code> | <code>Un homme portant un casque de sécurité est en train de danser.</code> | <code>1.0</code>               |
+  | <code>Un jeune enfant monte à cheval.</code>                             | <code>Un enfant monte à cheval.</code>                                      | <code>0.949999988079071</code> |
+  | <code>Un homme donne une souris à un serpent.</code>                     | <code>L'homme donne une souris au serpent.</code>                           | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_it
+
+* Dataset: [multi_stsb_it](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 19.05 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 19.03 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                         | sentence2                                                      | score                          |
+  |:------------------------------------------------------------------|:---------------------------------------------------------------|:-------------------------------|
+  | <code>Un uomo con l'elmetto sta ballando.</code>                  | <code>Un uomo che indossa un elmetto sta ballando.</code>      | <code>1.0</code>               |
+  | <code>Un bambino piccolo sta cavalcando un cavallo.</code>        | <code>Un bambino sta cavalcando un cavallo.</code>             | <code>0.949999988079071</code> |
+  | <code>Un uomo sta dando da mangiare un topo a un serpente.</code> | <code>L'uomo sta dando da mangiare un topo al serpente.</code> | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_nl
+
+* Dataset: [multi_stsb_nl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 19.12 tokens</li><li>max: 49 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 18.95 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                            | sentence2                                            | score                          |
+  |:-----------------------------------------------------|:-----------------------------------------------------|:-------------------------------|
+  | <code>Een man met een helm is aan het dansen.</code> | <code>Een man met een helm is aan het dansen.</code> | <code>1.0</code>               |
+  | <code>Een jong kind rijdt op een paard.</code>       | <code>Een kind rijdt op een paard.</code>            | <code>0.949999988079071</code> |
+  | <code>Een man voedt een muis aan een slang.</code>   | <code>De man voert een muis aan de slang.</code>     | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_pl
+
+* Dataset: [multi_stsb_pl](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 21.6 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 21.47 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                          | sentence2                                          | score                          |
+  |:---------------------------------------------------|:---------------------------------------------------|:-------------------------------|
+  | <code>Tańczy mężczyzna w twardym kapeluszu.</code> | <code>Tańczy mężczyzna w twardym kapeluszu.</code> | <code>1.0</code>               |
+  | <code>Małe dziecko jedzie na koniu.</code>         | <code>Dziecko jedzie na koniu.</code>              | <code>0.949999988079071</code> |
+  | <code>Człowiek karmi węża myszką.</code>           | <code>Ten człowiek karmi węża myszką.</code>       | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_pt
+
+* Dataset: [multi_stsb_pt](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 19.26 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 19.08 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                   | sentence2                                                  | score                          |
+  |:------------------------------------------------------------|:-----------------------------------------------------------|:-------------------------------|
+  | <code>Um homem de chapéu duro está a dançar.</code>         | <code>Um homem com um capacete está a dançar.</code>       | <code>1.0</code>               |
+  | <code>Uma criança pequena está a montar a cavalo.</code>    | <code>Uma criança está a montar a cavalo.</code>           | <code>0.949999988079071</code> |
+  | <code>Um homem está a alimentar um rato a uma cobra.</code> | <code>O homem está a alimentar a cobra com um rato.</code> | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_ru
+
+* Dataset: [multi_stsb_ru](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 20.91 tokens</li><li>max: 55 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 20.95 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                             | sentence2                                     | score                          |
+  |:------------------------------------------------------|:----------------------------------------------|:-------------------------------|
+  | <code>Человек в твердой шляпе танцует.</code>         | <code>Мужчина в твердой шляпе танцует.</code> | <code>1.0</code>               |
+  | <code>Маленький ребенок едет верхом на лошади.</code> | <code>Ребенок едет на лошади.</code>          | <code>0.949999988079071</code> |
+  | <code>Мужчина кормит мышь змее.</code>                | <code>Человек кормит змею мышью.</code>       | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+#### multi_stsb_zh
+
+* Dataset: [multi_stsb_zh](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt) at [3acaa3d](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt/tree/3acaa3dd8c91649e0b8e627ffad891f059e47c8c)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | score                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 19.81 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.67 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                  | sentence2                 | score                          |
+  |:---------------------------|:--------------------------|:-------------------------------|
+  | <code>一个戴着硬帽子的人在跳舞。</code> | <code>一个戴着硬帽的人在跳舞。</code> | <code>1.0</code>               |
+  | <code>一个小孩子在骑马。</code>     | <code>一个孩子在骑马。</code>     | <code>0.949999988079071</code> |
+  | <code>一个人正在用老鼠喂蛇。</code>   | <code>那人正在给蛇喂老鼠。</code>   | <code>1.0</code>               |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_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
+
+#### 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`: 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`: 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`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch | Step  | Training Loss | multi stsb de loss | multi stsb es loss | multi stsb fr loss | multi stsb it loss | multi stsb nl loss | multi stsb pl loss | multi stsb pt loss | multi stsb ru loss | multi stsb zh loss | sts-eval_spearman_cosine | sts-test_spearman_cosine |
+|:-----:|:-----:|:-------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------:|:------------------------:|:------------------------:|
+| 1.0   | 3240  | 4.6594        | 4.6488             | 4.6520             | 4.6401             | 4.6637             | 4.6435             | 4.6943             | 4.6786             | 4.6902             | 4.6578             | 0.5620                   | -                        |
+| 2.0   | 6480  | 4.4285        | 4.6860             | 4.6755             | 4.6796             | 4.6655             | 4.6472             | 4.7655             | 4.6910             | 4.7783             | 4.6939             | 0.6592                   | -                        |
+| 3.0   | 9720  | 4.1541        | 4.9416             | 5.0391             | 4.9025             | 4.9229             | 4.9449             | 5.0618             | 5.0057             | 5.0001             | 4.9986             | 0.6764                   | -                        |
+| 4.0   | 12960 | 3.8671        | 5.3776             | 5.5136             | 5.3842             | 5.3216             | 5.3303             | 5.4847             | 5.4591             | 5.3623             | 5.4139             | 0.6865                   | 0.6617                   |
+
+
+### Framework Versions
+- Python: 3.11.10
+- Sentence Transformers: 3.3.1
+- Transformers: 4.47.1
+- PyTorch: 2.3.1+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",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## 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.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "RomainDarous/pre_training_original_model",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "vocab_size": 119547
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.47.1",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bccd9e0fdf7c5ee3abdcc5f853b428f19e7c297d0030089292d638f4dc55fd93
+size 538947416

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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "max_length": 128,
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}