Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,1256 @@
+---
+language:
+- en
+- multilingual
+- ar
+- bg
+- ca
+- cs
+- da
+- de
+- el
+- es
+- et
+- fa
+- fi
+- fr
+- gl
+- gu
+- he
+- hi
+- hr
+- hu
+- hy
+- id
+- it
+- ja
+- ka
+- ko
+- ku
+- lt
+- lv
+- mk
+- mn
+- mr
+- ms
+- my
+- nb
+- nl
+- pl
+- pt
+- ro
+- ru
+- sk
+- sl
+- sq
+- sr
+- sv
+- th
+- tr
+- uk
+- ur
+- vi
+- zh
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- loss:MSELoss
+base_model: FacebookAI/xlm-roberta-base
+metrics:
+- negative_mse
+- src2trg_accuracy
+- trg2src_accuracy
+- mean_accuracy
+- pearson_cosine
+- spearman_cosine
+- pearson_manhattan
+- spearman_manhattan
+- pearson_euclidean
+- spearman_euclidean
+- pearson_dot
+- spearman_dot
+- pearson_max
+- spearman_max
+widget:
+- source_sentence: Grazie tante.
+  sentences:
+  - Grazie infinite.
+  - Non c'è un solo architetto diplomato in tutta la Contea.
+  - Le aziende non credevano che fosse loro responsabilità.
+- source_sentence: Avance rapide.
+  sentences:
+  - Très bien.
+  - Donc, je voulais faire quelque chose de spécial aujourd'hui.
+  - Et ils ne tiennent pas non plus compte des civils qui souffrent de façon plus
+    générale.
+- source_sentence: E' importante.
+  sentences:
+  - E' una materia fondamentale.
+  - Sono qui oggi per mostrare le mie fotografie dei Lakota.
+  - Non ero seguito da un corteo di macchine.
+- source_sentence: Müfettişler…
+  sentences:
+  - İşçi sınıfına dair birşey.
+  - Antlaşmaya göre, o topraklar bağımsız bir ulustur.
+  - Son derece düz ve bataklık bir coğrafya.
+- source_sentence: Wir sind eins.
+  sentences:
+  - Das versuchen wir zu bieten.
+  - Ihre Gehirne sind ungefähr 100 Millionen Mal komplizierter.
+  - Hinter mir war gar keine Autokolonne.
+pipeline_tag: sentence-similarity
+co2_eq_emissions:
+  emissions: 23.27766676567869
+  energy_consumed: 0.05988563672345058
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.179
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: SentenceTransformer based on FacebookAI/xlm-roberta-base
+  results:
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en ar
+      type: en-ar
+    metrics:
+    - type: negative_mse
+      value: -20.395545661449432
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en ar
+      type: en-ar
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.7603222557905337
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.7824773413897281
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.7713997985901309
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 en ar test
+      type: sts17-en-ar-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.40984231242712876
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.4425400227662121
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.4068582195810505
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.4194184278683204
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.38014538983821944
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.38651157412220366
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4077636003696869
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.37682818098716137
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.40984231242712876
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.4425400227662121
+      name: Spearman Max
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en fr
+      type: en-fr
+    metrics:
+    - type: negative_mse
+      value: -19.62321847677231
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en fr
+      type: en-fr
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.8981854838709677
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.8901209677419355
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.8941532258064516
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 fr en test
+      type: sts17-fr-en-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.5017606394120642
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5333594401322842
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.4461108010622129
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.45470883061015244
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.44313058261278737
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.44806261424208443
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.40165874540768454
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.41339619568003433
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.5017606394120642
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.5333594401322842
+      name: Spearman Max
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en de
+      type: en-de
+    metrics:
+    - type: negative_mse
+      value: -19.727922976017
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en de
+      type: en-de
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.8920282542885973
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.8910191725529768
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.8915237134207871
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 en de test
+      type: sts17-en-de-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.5262798164154752
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5618005565496922
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5084907192868734
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.5218456102379673
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.5055278909013912
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.5206420646365548
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.3742195121194434
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.3691237073066472
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.5262798164154752
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.5618005565496922
+      name: Spearman Max
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en es
+      type: en-es
+    metrics:
+    - type: negative_mse
+      value: -19.472387433052063
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en es
+      type: en-es
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.9434343434343434
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.9464646464646465
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.944949494949495
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 es en test
+      type: sts17-es-en-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.4944989376773328
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.502096516024397
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.44447965250345656
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.428444032581959
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.43569887867301704
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.4169602915053127
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.3751122541083453
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.37961391381473436
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.4944989376773328
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.502096516024397
+      name: Spearman Max
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en tr
+      type: en-tr
+    metrics:
+    - type: negative_mse
+      value: -20.754697918891907
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en tr
+      type: en-tr
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.743202416918429
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.743202416918429
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.743202416918429
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 en tr test
+      type: sts17-en-tr-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.5544917743538167
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.581923120433332
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.5103770986779784
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.5087986920849596
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.5045523005860614
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.5053157708914061
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.47262046401401747
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.4297595645819756
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.5544917743538167
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.581923120433332
+      name: Spearman Max
+  - task:
+      type: knowledge-distillation
+      name: Knowledge Distillation
+    dataset:
+      name: en it
+      type: en-it
+    metrics:
+    - type: negative_mse
+      value: -19.76993829011917
+      name: Negative Mse
+  - task:
+      type: translation
+      name: Translation
+    dataset:
+      name: en it
+      type: en-it
+    metrics:
+    - type: src2trg_accuracy
+      value: 0.878147029204431
+      name: Src2Trg Accuracy
+    - type: trg2src_accuracy
+      value: 0.8831822759315207
+      name: Trg2Src Accuracy
+    - type: mean_accuracy
+      value: 0.8806646525679758
+      name: Mean Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts17 it en test
+      type: sts17-it-en-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.506365733914274
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5250284136808592
+      name: Spearman Cosine
+    - type: pearson_manhattan
+      value: 0.45167598168533407
+      name: Pearson Manhattan
+    - type: spearman_manhattan
+      value: 0.46227952068355316
+      name: Spearman Manhattan
+    - type: pearson_euclidean
+      value: 0.4423426674780287
+      name: Pearson Euclidean
+    - type: spearman_euclidean
+      value: 0.45072801992723094
+      name: Spearman Euclidean
+    - type: pearson_dot
+      value: 0.4201989776020174
+      name: Pearson Dot
+    - type: spearman_dot
+      value: 0.42253906764732746
+      name: Spearman Dot
+    - type: pearson_max
+      value: 0.506365733914274
+      name: Pearson Max
+    - type: spearman_max
+      value: 0.5250284136808592
+      name: Spearman Max
+---
+
+# SentenceTransformer based on FacebookAI/xlm-roberta-base
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the [en-ar](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks), [en-fr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks), [en-de](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks), [en-es](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks), [en-tr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) and [en-it](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) datasets. 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:** [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) <!-- at revision e73636d4f797dec63c3081bb6ed5c7b0bb3f2089 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Datasets:**
+    - [en-ar](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+    - [en-fr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+    - [en-de](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+    - [en-es](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+    - [en-tr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+    - [en-it](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks)
+- **Languages:** en, multilingual, ar, bg, ca, cs, da, de, el, es, et, fa, fi, fr, gl, gu, he, hi, hr, hu, hy, id, it, ja, ka, ko, ku, lt, lv, mk, mn, mr, ms, my, nb, nl, pl, pt, ro, ru, sk, sl, sq, sr, sv, th, tr, uk, ur, vi, 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: 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})
+)
+```
+
+## 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("tomaarsen/xlm-roberta-base-multilingual-en-ar-fr-de-es-tr-it")
+# Run inference
+sentences = [
+    'Wir sind eins.',
+    'Das versuchen wir zu bieten.',
+    'Ihre Gehirne sind ungefähr 100 Millionen Mal komplizierter.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(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
+
+#### Knowledge Distillation
+* Dataset: `en-ar`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-20.3955** |
+
+#### Translation
+* Dataset: `en-ar`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.7603     |
+| trg2src_accuracy  | 0.7825     |
+| **mean_accuracy** | **0.7714** |
+
+#### Semantic Similarity
+* Dataset: `sts17-en-ar-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.4098     |
+| spearman_cosine    | 0.4425     |
+| pearson_manhattan  | 0.4069     |
+| spearman_manhattan | 0.4194     |
+| pearson_euclidean  | 0.3801     |
+| spearman_euclidean | 0.3865     |
+| pearson_dot        | 0.4078     |
+| spearman_dot       | 0.3768     |
+| pearson_max        | 0.4098     |
+| **spearman_max**   | **0.4425** |
+
+#### Knowledge Distillation
+* Dataset: `en-fr`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-19.6232** |
+
+#### Translation
+* Dataset: `en-fr`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.8982     |
+| trg2src_accuracy  | 0.8901     |
+| **mean_accuracy** | **0.8942** |
+
+#### Semantic Similarity
+* Dataset: `sts17-fr-en-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.5018     |
+| spearman_cosine    | 0.5334     |
+| pearson_manhattan  | 0.4461     |
+| spearman_manhattan | 0.4547     |
+| pearson_euclidean  | 0.4431     |
+| spearman_euclidean | 0.4481     |
+| pearson_dot        | 0.4017     |
+| spearman_dot       | 0.4134     |
+| pearson_max        | 0.5018     |
+| **spearman_max**   | **0.5334** |
+
+#### Knowledge Distillation
+* Dataset: `en-de`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-19.7279** |
+
+#### Translation
+* Dataset: `en-de`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.892      |
+| trg2src_accuracy  | 0.891      |
+| **mean_accuracy** | **0.8915** |
+
+#### Semantic Similarity
+* Dataset: `sts17-en-de-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.5263     |
+| spearman_cosine    | 0.5618     |
+| pearson_manhattan  | 0.5085     |
+| spearman_manhattan | 0.5218     |
+| pearson_euclidean  | 0.5055     |
+| spearman_euclidean | 0.5206     |
+| pearson_dot        | 0.3742     |
+| spearman_dot       | 0.3691     |
+| pearson_max        | 0.5263     |
+| **spearman_max**   | **0.5618** |
+
+#### Knowledge Distillation
+* Dataset: `en-es`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-19.4724** |
+
+#### Translation
+* Dataset: `en-es`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.9434     |
+| trg2src_accuracy  | 0.9465     |
+| **mean_accuracy** | **0.9449** |
+
+#### Semantic Similarity
+* Dataset: `sts17-es-en-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.4945     |
+| spearman_cosine    | 0.5021     |
+| pearson_manhattan  | 0.4445     |
+| spearman_manhattan | 0.4284     |
+| pearson_euclidean  | 0.4357     |
+| spearman_euclidean | 0.417      |
+| pearson_dot        | 0.3751     |
+| spearman_dot       | 0.3796     |
+| pearson_max        | 0.4945     |
+| **spearman_max**   | **0.5021** |
+
+#### Knowledge Distillation
+* Dataset: `en-tr`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-20.7547** |
+
+#### Translation
+* Dataset: `en-tr`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.7432     |
+| trg2src_accuracy  | 0.7432     |
+| **mean_accuracy** | **0.7432** |
+
+#### Semantic Similarity
+* Dataset: `sts17-en-tr-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value      |
+|:-------------------|:-----------|
+| pearson_cosine     | 0.5545     |
+| spearman_cosine    | 0.5819     |
+| pearson_manhattan  | 0.5104     |
+| spearman_manhattan | 0.5088     |
+| pearson_euclidean  | 0.5046     |
+| spearman_euclidean | 0.5053     |
+| pearson_dot        | 0.4726     |
+| spearman_dot       | 0.4298     |
+| pearson_max        | 0.5545     |
+| **spearman_max**   | **0.5819** |
+
+#### Knowledge Distillation
+* Dataset: `en-it`
+* Evaluated with [<code>MSEEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.MSEEvaluator)
+
+| Metric           | Value        |
+|:-----------------|:-------------|
+| **negative_mse** | **-19.7699** |
+
+#### Translation
+* Dataset: `en-it`
+* Evaluated with [<code>TranslationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.TranslationEvaluator)
+
+| Metric            | Value      |
+|:------------------|:-----------|
+| src2trg_accuracy  | 0.8781     |
+| trg2src_accuracy  | 0.8832     |
+| **mean_accuracy** | **0.8807** |
+
+#### Semantic Similarity
+* Dataset: `sts17-it-en-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric             | Value     |
+|:-------------------|:----------|
+| pearson_cosine     | 0.5064    |
+| spearman_cosine    | 0.525     |
+| pearson_manhattan  | 0.4517    |
+| spearman_manhattan | 0.4623    |
+| pearson_euclidean  | 0.4423    |
+| spearman_euclidean | 0.4507    |
+| pearson_dot        | 0.4202    |
+| spearman_dot       | 0.4225    |
+| pearson_max        | 0.5064    |
+| **spearman_max**   | **0.525** |
+
+<!--
+## 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
+
+#### en-ar
+
+* Dataset: [en-ar](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                       | label                                |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                            | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.3 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                             | label                                                                                                                       |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|
+  | <code>حسناً ان ما نقوم به اليوم .. هو ان نجبر الطلاب لتعلم الرياضيات</code>                                                                                             | <code>[0.3943225145339966, 0.18910610675811768, -0.3788299858570099, 0.4386662542819977, 0.2727023661136627, ...]</code>    |
+  | <code>انها المادة الاهم ..</code>                                                                                                                                       | <code>[0.6257511377334595, -0.1750679910182953, -0.5734405517578125, 0.11480475962162018, 1.1682192087173462, ...]</code>   |
+  | <code>انا لا انفي لدقيقة واحدة ان الذين يهتمون بالحسابات اليدوية والذين هوايتهم القيام بذلك .. او القيام بالطرق التقليدية في اي مجال ان يقوموا بذلك كما يريدون .</code> | <code>[-0.04564047232270241, 0.4971524775028229, 0.28066301345825195, -0.726702094078064, -0.17846377193927765, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-fr
+
+* Dataset: [en-fr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 30.18 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                                                                         | label                                                                                                                        |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Je ne crois pas que ce soit justifié.</code>                                                                                                                                                                  | <code>[-0.361753910779953, 0.7323777079582214, 0.6518164277076721, -0.8461216688156128, -0.007496988866478205, ...]</code>   |
+  | <code>Je fais cette distinction entre ce qu'on force les gens à faire et les matières générales, et la matière que quelqu'un va apprendre parce que ça lui plait et peut-être même exceller dans ce domaine.</code> | <code>[0.3047865629196167, 0.5270194411277771, 0.26616284251213074, 0.2612147927284241, 0.1950961947441101, ...]</code>      |
+  | <code>Quels sont les problèmes en relation avec ça?</code>                                                                                                                                                          | <code>[0.2123892903327942, -0.09616081416606903, -0.41965243220329285, -0.5469444394111633, -0.6056491136550903, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-de
+
+* Dataset: [en-de](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.04 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                         | label                                                                                                                        |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Ich denke, dass es sich aus diesem Grund lohnt, den Leuten das Rechnen von Hand beizubringen.</code>                                          | <code>[0.0960279330611229, 0.7833179831504822, -0.09527698159217834, 0.8104371428489685, 0.7545774579048157, ...]</code>     |
+  | <code>Außerdem gibt es ein paar bestimmte konzeptionelle Dinge, die das Rechnen per Hand rechtfertigen, aber ich glaube es sind sehr wenige.</code> | <code>[-0.5939837098121643, 0.9714100956916809, 0.6800686717033386, -0.21585524082183838, -0.7509503364562988, ...]</code>   |
+  | <code>Eine Sache, die ich mich oft frage, ist Altgriechisch, und wie das zusammengehört.</code>                                                     | <code>[-0.09777048230171204, 0.07093209028244019, -0.42989012598991394, -0.1457514613866806, 1.4382753372192383, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-es
+
+* Dataset: [en-es](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 25.42 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                              | label                                                                                                                        |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Y luego hay ciertas aspectos conceptuales que pueden beneficiarse del cálculo a mano pero creo que son relativamente pocos.</code> | <code>[-0.5939835906028748, 0.9714106917381287, 0.6800685524940491, -0.2158554196357727, -0.7509507536888123, ...]</code>    |
+  | <code>Algo que pregunto a menudo es sobre el griego antiguo y cómo se relaciona.</code>                                                  | <code>[-0.09777048230171204, 0.07093209028244019, -0.42989012598991394, -0.1457514613866806, 1.4382753372192383, ...]</code> |
+  | <code>Vean, lo que estamos haciendo ahora es forzar a la gente a aprender matemáticas.</code>                                            | <code>[0.3943225145339966, 0.18910610675811768, -0.3788299858570099, 0.4386662542819977, 0.2727023661136627, ...]</code>     |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-tr
+
+* Dataset: [en-tr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 24.72 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                                               | label                                                                                                                        |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Eğer insanlar elle hesaba ilgililerse ya da öğrenmek için özel amaçları varsa konu ne kadar acayip olursa olsun bunu öğrenmeliler, engellemeyi bir an için bile önermiyorum.</code> | <code>[-0.04564047232270241, 0.4971524775028229, 0.28066301345825195, -0.726702094078064, -0.17846377193927765, ...]</code>  |
+  | <code>İnsanların kendi ilgi alanlarını takip etmeleri, kesinlikle doğru bir şeydir.</code>                                                                                                | <code>[0.2061387449502945, 0.5284574031829834, 0.3577779233455658, 0.28818392753601074, 0.17228049039840698, ...]</code>     |
+  | <code>Ben bir biçimde Antik Yunan hakkında ilgiliyimdir. ancak tüm nüfusu Antik Yunan gibi bir konu hakkında bilgi edinmeye zorlamamalıyız.</code>                                        | <code>[0.12050342559814453, 0.15652479231357574, 0.48636534810066223, -0.13693244755268097, 0.42764803767204285, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-it
+
+* Dataset: [en-it](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 5,000 training samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 26.41 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                                                                                               | label                                                                                                                       |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Non credo che sia giustificato.</code>                                                                                                                                                                                              | <code>[-0.36175352334976196, 0.7323781251907349, 0.651816189289093, -0.8461223840713501, -0.007496151141822338, ...]</code> |
+  | <code>Perciò faccio distinzione tra quello che stiamo facendo fare alle persone, le materie che si ritengono principali, e le materie che le persone potrebbero seguire per loro interesse o forse a volte anche incitate a farlo.</code> | <code>[0.3047865927219391, 0.5270194411277771, 0.26616284251213074, 0.2612147927284241, 0.1950961947441101, ...]</code>     |
+  | <code>Ma che argomenti porta la gente su questi temi?</code>                                                                                                                                                                              | <code>[0.2123885154724121, -0.09616123884916306, -0.4196523427963257, -0.5469440817832947, -0.6056501865386963, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+### Evaluation Datasets
+
+#### en-ar
+
+* Dataset: [en-ar](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 993 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 28.03 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                 | label                                                                                                                        |
+  |:------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>شكرا جزيلا كريس.</code>                                                                               | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>انه فعلا شرف عظيم لي ان أصعد المنصة للمرة الثانية. أنا في غاية الامتنان.</code>                       | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>لقد بهرت فعلا بهذا المؤتمر, وأريد أن أشكركم جميعا على تعليقاتكم الطيبة على ما قلته تلك الليلة.</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-fr
+
+* Dataset: [en-fr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 992 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 30.72 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                                      | label                                                                                                                        |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Merci beaucoup, Chris.</code>                                                                                                                                              | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>C'est vraiment un honneur de pouvoir venir sur cette scène une deuxième fois. Je suis très reconnaissant.</code>                                                           | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>J'ai été très impressionné par cette conférence, et je tiens à vous remercier tous pour vos nombreux et sympathiques commentaires sur ce que j'ai dit l'autre soir.</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-de
+
+* Dataset: [en-de](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 991 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.71 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                | label                                                                                                                        |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Vielen Dank, Chris.</code>                                                                                                                           | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>Es ist mir wirklich eine Ehre, zweimal auf dieser Bühne stehen zu dürfen. Tausend Dank dafür.</code>                                                 | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>Ich bin wirklich begeistert von dieser Konferenz, und ich danke Ihnen allen für die vielen netten Kommentare zu meiner Rede vorgestern Abend.</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-es
+
+* Dataset: [en-es](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 990 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 26.47 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                                       | label                                                                                                                        |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Muchas gracias Chris.</code>                                                                                                                                | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>Y es en verdad un gran honor tener la oportunidad de venir a este escenario por segunda vez. Estoy extremadamente agradecido.</code>                        | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>He quedado conmovido por esta conferencia, y deseo agradecer a todos ustedes sus amables comentarios acerca de lo que tenía que decir la otra noche.</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-tr
+
+* Dataset: [en-tr](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 993 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                       | label                                |
+  |:--------|:----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                            | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 25.4 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                 | label                                                                                                                        |
+  |:----------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Çok teşekkür ederim Chris.</code>                                                                                     | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>Bu sahnede ikinci kez yer alma fırsatına sahip olmak gerçekten büyük bir onur. Çok minnettarım.</code>                | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>Bu konferansta çok mutlu oldum, ve anlattıklarımla ilgili güzel yorumlarınız için sizlere çok teşekkür ederim.</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+#### en-it
+
+* Dataset: [en-it](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks) at [d366ddd](https://huggingface.co/datasets/sentence-transformers/parallel-sentences-talks/tree/d366dddc3d1ef0421a41f9e534bad4efae6d7730)
+* Size: 993 evaluation samples
+* Columns: <code>non_english</code> and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | non_english                                                                        | label                                |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------|
+  | type    | string                                                                             | list                                 |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.94 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>size: 768 elements</li></ul> |
+* Samples:
+  | non_english                                                                                                                                             | label                                                                                                                        |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------|
+  | <code>Grazie mille, Chris.</code>                                                                                                                       | <code>[-0.4331263303756714, 1.0602688789367676, -0.07791043072938919, -0.4170420169830322, 1.6768444776535034, ...]</code>   |
+  | <code>E’ veramente un grande onore venire su questo palco due volte. Vi sono estremamente grato.</code>                                                 | <code>[0.27005696296691895, 0.5391750335693359, -0.2580486238002777, -0.6613674759864807, 0.6738830804824829, ...]</code>    |
+  | <code>Sono impressionato da questa conferenza, e voglio ringraziare tutti voi per i tanti, lusinghieri commenti, anche perché... Ne ho bisogno!!</code> | <code>[-0.25320106744766235, 0.04791366308927536, -0.13174884021282196, -0.7357578277587891, 0.2366354614496231, ...]</code> |
+* Loss: [<code>MSELoss</code>](https://sbert.net/docs/package_reference/losses.html#mseloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: False
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `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`: 5
+- `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
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: None
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `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_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | en-ar loss | en-it loss | en-de loss | en-fr loss | en-es loss | en-tr loss | en-ar_mean_accuracy | en-ar_negative_mse | en-de_mean_accuracy | en-de_negative_mse | en-es_mean_accuracy | en-es_negative_mse | en-fr_mean_accuracy | en-fr_negative_mse | en-it_mean_accuracy | en-it_negative_mse | en-tr_mean_accuracy | en-tr_negative_mse | sts17-en-ar-test_spearman_max | sts17-en-de-test_spearman_max | sts17-en-tr-test_spearman_max | sts17-es-en-test_spearman_max | sts17-fr-en-test_spearman_max | sts17-it-en-test_spearman_max |
+|:------:|:----:|:-------------:|:----------:|:----------:|:----------:|:----------:|:----------:|:----------:|:-------------------:|:------------------:|:-------------------:|:------------------:|:-------------------:|:------------------:|:-------------------:|:------------------:|:-------------------:|:------------------:|:-------------------:|:------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|
+| 0.2110 | 100  | 0.5581        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 0.4219 | 200  | 0.3071        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 0.6329 | 300  | 0.2675        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 0.8439 | 400  | 0.2606        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 1.0549 | 500  | 0.2589        | 0.2519     | 0.2498     | 0.2511     | 0.2488     | 0.2503     | 0.2512     | 0.1254              | -25.1903           | 0.2523              | -25.1089           | 0.2591              | -25.0276           | 0.2409              | -24.8803           | 0.2180              | -24.9768           | 0.1158              | -25.1219           | 0.0308                        | 0.1281                        | 0.1610                        | 0.1465                        | 0.0552                        | 0.0518                        |
+| 1.2658 | 600  | 0.2504        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 1.4768 | 700  | 0.2427        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 1.6878 | 800  | 0.2337        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 1.8987 | 900  | 0.2246        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 2.1097 | 1000 | 0.2197        | 0.2202     | 0.2157     | 0.2151     | 0.2147     | 0.2139     | 0.2218     | 0.5841              | -22.0204           | 0.8012              | -21.5087           | 0.8495              | -21.3935           | 0.7959              | -21.4660           | 0.7815              | -21.5699           | 0.6007              | -22.1778           | 0.3346                        | 0.4013                        | 0.4727                        | 0.3353                        | 0.3827                        | 0.3292                        |
+| 2.3207 | 1100 | 0.2163        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 2.5316 | 1200 | 0.2123        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 2.7426 | 1300 | 0.2069        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 2.9536 | 1400 | 0.2048        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 3.1646 | 1500 | 0.2009        | 0.2086     | 0.2029     | 0.2022     | 0.2012     | 0.2002     | 0.2111     | 0.7367              | -20.8567           | 0.8739              | -20.2247           | 0.9303              | -20.0215           | 0.8755              | -20.1213           | 0.8600              | -20.2900           | 0.7165              | -21.1119           | 0.4087                        | 0.5473                        | 0.5551                        | 0.4724                        | 0.4882                        | 0.4690                        |
+| 3.3755 | 1600 | 0.2019        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 3.5865 | 1700 | 0.1989        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 3.7975 | 1800 | 0.196         | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 4.0084 | 1900 | 0.1943        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 4.2194 | 2000 | 0.194         | 0.2040     | 0.1977     | 0.1973     | 0.1962     | 0.1947     | 0.2075     | 0.7714              | -20.3955           | 0.8915              | -19.7279           | 0.9449              | -19.4724           | 0.8942              | -19.6232           | 0.8807              | -19.7699           | 0.7432              | -20.7547           | 0.4425                        | 0.5618                        | 0.5819                        | 0.5021                        | 0.5334                        | 0.5250                        |
+| 4.4304 | 2100 | 0.1951        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 4.6414 | 2200 | 0.1928        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+| 4.8523 | 2300 | 0.1909        | -          | -          | -          | -          | -          | -          | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                   | -                  | -                             | -                             | -                             | -                             | -                             | -                             |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.060 kWh
+- **Carbon Emitted**: 0.023 kg of CO2
+- **Hours Used**: 0.179 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 3.0.0.dev0
+- Transformers: 4.41.0.dev0
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.26.1
+- Datasets: 2.18.0
+- Tokenizers: 0.19.1
+
+## 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",
+}
+```
+
+#### MSELoss
+```bibtex
+@inproceedings{reimers-2020-multilingual-sentence-bert,
+    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2020",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/2004.09813",
+}
+```
+
+<!--
+## 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 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.0.dev0",
+    "transformers": "4.41.0.dev0",
+    "pytorch": "2.3.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149e16f1341357d04aa0ffc019a3dd067c6a43fd0e9c878c9b981c08c577cabd
+size 1112197096

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}