diff --git a/README.md b/README.md
index 54c615fd6bb393fe759eba4ade5f5ab69bd6ef41..0f0c317557daf8ae7e801d01a6d86cb7a1fd0d62 100644
--- a/README.md
+++ b/README.md
@@ -7,34 +7,35 @@ tags:
 - sentence-similarity
 - feature-extraction
 - generated_from_trainer
-- dataset_size:2130620
+- dataset_size:2130621
 - loss:ContrastiveLoss
 base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
 widget:
-- source_sentence: Russell Jurney
+- source_sentence: Kim Chol-sam
   sentences:
-  - Russell H. Jurney
-  - Russ Jurney
-  - Русс Джерни
-- source_sentence: Ben Lorica
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
   sentences:
-  - Benjamin Lorica
-  - 罗瑞卡
-  - 罗睿姬
-- source_sentence: Yevgeny Prigozhin
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
   sentences:
-  - Евге́ний Ви́кторович Приго́жин
-  - Y. Prighozhin
-- source_sentence: M.R. James
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
   sentences:
-  - Montague Rhodes James
-  - J.R. James
-  - Mr. James
-- source_sentence: Muhammad Ali
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
   sentences:
-  - مُحَمَّد عَلِيّ
-  - Mohammed Ali
-  - Sonny Liston
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 metrics:
@@ -57,38 +58,81 @@ model-index:
       type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
     metrics:
     - type: cosine_accuracy
-      value: 0.9905380542935456
+      value: 0.9843050674356433
       name: Cosine Accuracy
     - type: cosine_accuracy_threshold
-      value: 0.6790644526481628
+      value: 0.742120623588562
       name: Cosine Accuracy Threshold
     - type: cosine_f1
-      value: 0.9856131536880567
+      value: 0.9760932477723254
       name: Cosine F1
     - type: cosine_f1_threshold
-      value: 0.6790644526481628
+      value: 0.742120623588562
       name: Cosine F1 Threshold
     - type: cosine_precision
-      value: 0.9816899806664392
+      value: 0.9703216856372878
       name: Cosine Precision
     - type: cosine_recall
-      value: 0.9895678092399404
+      value: 0.9819338803033267
       name: Cosine Recall
     - type: cosine_ap
-      value: 0.9977983578816215
+      value: 0.9955554741842152
       name: Cosine Ap
     - type: cosine_mcc
-      value: 0.9785817179348335
+      value: 0.964449493634366
       name: Cosine Mcc
 ---
 
 # Graphlet-AI/eridu
 
+Deep fuzzy matching people and company names for multilingual entity resolution using representation learning... that incorporates a deep understanding of people and company names and works _much better_ than string distance methods.
+
 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) for person and company name matching using the [Open Sanctions matcher training data](https://www.opensanctions.org/docs/pairs/). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used as part of a deep, fuzzy entity resolution process.
 
 ## Model Details
 
+### TLDR: 5 Lines of Code
+
+```python
+from sentence_transformers import SentenceTransformer
+
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("Graphlet-AI/eridu")
+
+names = [
+    "Russell Jurney",
+    "Russ Jurney",
+    "Русс Джерни",
+]
+
+embeddings = model.encode(names)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+
+print(similarities.numpy())
+# [[0.9999999  0.99406826 0.99406105]
+#  [0.9940683  1.         0.9969202 ]
+#  [0.99406105 0.9969202  1.        ]]
+```
+
+### Project Eridu Overview
+
+This project is a deep fuzzy matching system for person and company names for entity resolution using representation learning. It is designed to match people and company names across languages and character sets, using a pre-trained text embedding model from HuggingFace that we fine-tune using contrastive learning on 2 million labeled pairs of person and company names from the [Open Sanctions Matcher training data](https://www.opensanctions.org/docs/pairs/). The project includes a command-line interface (CLI) utility for training the model and comparing pairs of names using cosine similarity.
+
+Matching people and company names is an intractable problem using traditional parsing based methods: there is too much variation across cultures and jurisdictions to solve the problem by humans programming. This results in complex, cost prohibitive enterprise solutions for name matching like [IBM InfoSphere Global Name Management](https://www.ibm.com/products/ibm-infosphere-global-name-management). Machine learning is used on problems like this one of cultural relevance, where the time to manually programming a solution appproaches infinity, to automatically write a program. Since 2008 there has been an explosion of deep learning methods that automate feature engineering via representation learning methods including such as text embeddings.
+
+This project loads the pre-trained [paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) paraphrase model from HuggingFace and fine-tunes it for the name matching task using contrastive learning on more than 2 million labeled pairs of matching and non-matching (just as important) person and company names from the [Open Sanctions Matcher training data](https://www.opensanctions.org/docs/pairs/) to create a deep fuzzy matching system for entity resolution.
+
+This model is available on HuggingFace Hub as [Graphlet-AI/eridu](https://huggingface.co/Graphlet-AI/eridu) and can be used in any Python project using the [Sentence Transformers](https://sbert.net/) library in five lines of code. The model is designed to be used for entity resolution tasks, such as matching people and company names across different languages and character sets when matching records.
+
 ### Model Description
+
 - **Model Type:** Sentence Transformer
 - **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
 - **Maximum Sequence Length:** 128 tokens
@@ -103,6 +147,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 - **Documentation:** [Graphlet-AI/eridu Documentation](https://github.com/Graphlet-AI/eridu)
 - **Repository:** [Graphlet-AI/eridu on GitHub](https://github.com/Graphlet-AI/eridu)
 - **Hugging Face:** [Graphlet-AI/eridu on Hugging Face](https://huggingface.co/Graphlet-AI/eridu)
+- **PyPi Package:** [Graphlet-AI/eridu on PyPi](https://pypi.org/project/eridu/)
 
 ### Full Model Architecture
 
@@ -124,19 +169,20 @@ 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("Graphlet-AI/eridu")
-
-names = [
-    "Russell Jurney",
-    "Russ Jurney",
-    "Русс Джерни",
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
 ]
-
-embeddings = model.encode(names)
+embeddings = model.encode(sentences)
 print(embeddings.shape)
 # [3, 384]
 
@@ -144,11 +190,6 @@ print(embeddings.shape)
 similarities = model.similarity(embeddings, embeddings)
 print(similarities.shape)
 # [3, 3]
-
-print(similarities.numpy())
-# [[0.9999999  0.99406826 0.99406105]
-#  [0.9940683  1.         0.9969202 ]
-#  [0.99406105 0.9969202  1.        ]]
 ```
 
 <!--
@@ -162,7 +203,7 @@ print(similarities.numpy())
 <!--
 ### Downstream Usage (Sentence Transformers)
 
-You can fine-tune this model on your own dataset.
+You can finetune this model on your own dataset.
 
 <details><summary>Click to expand</summary>
 
@@ -181,19 +222,19 @@ You can fine-tune this model on your own dataset.
 
 #### Binary Classification
 
-* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
-* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+- Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+- Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
 
 | Metric                    | Value      |
 |:--------------------------|:-----------|
-| cosine_accuracy           | 0.9905     |
-| cosine_accuracy_threshold | 0.6791     |
-| cosine_f1                 | 0.9856     |
-| cosine_f1_threshold       | 0.6791     |
-| cosine_precision          | 0.9817     |
-| cosine_recall             | 0.9896     |
-| **cosine_ap**             | **0.9978** |
-| cosine_mcc                | 0.9786     |
+| cosine_accuracy           | 0.9843     |
+| cosine_accuracy_threshold | 0.7421     |
+| cosine_f1                 | 0.9761     |
+| cosine_f1_threshold       | 0.7421     |
+| cosine_precision          | 0.9703     |
+| cosine_recall             | 0.9819     |
+| **cosine_ap**             | **0.9956** |
+| cosine_mcc                | 0.9644     |
 
 <!--
 ## Bias, Risks and Limitations
@@ -213,20 +254,25 @@ You can fine-tune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 2,130,620 training samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
+- Size: 2,130,621 training samples
+- Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+- Approximate statistics based on the first 1000 samples:
+
   |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
   |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
   | type    | string                                                                           | string                                                                           | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.28 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.11 tokens</li><li>max: 65 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                   | sentence2                      | label            |
-  |:----------------------------|:-------------------------------|:-----------------|
-  | <code>ג'ק וייט</code>       | <code>Jack White</code>        | <code>1.0</code> |
-  | <code>Абдуллоҳ Гул</code>   | <code>Савицкая Светлана</code> | <code>0.0</code> |
-  | <code>ショーン・ジャスティン・ペン</code> | <code>شان پن</code>            | <code>1.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+
+- Samples:
+
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+
+- Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+
   ```json
   {
       "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
@@ -239,20 +285,25 @@ You can fine-tune this model on your own dataset.
 
 #### Unnamed Dataset
 
-* Size: 266,328 evaluation samples
-* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
-* Approximate statistics based on the first 1000 samples:
-  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
-  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
-  | type    | string                                                                           | string                                                                           | float                                                          |
-  | details | <ul><li>min: 3 tokens</li><li>mean: 9.27 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.99 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.32</li><li>max: 1.0</li></ul> |
-* Samples:
-  | sentence1                                    | sentence2                                      | label            |
-  |:---------------------------------------------|:-----------------------------------------------|:-----------------|
-  | <code>Анатолий Николаевич Герасимов</code>   | <code>Anatoli Nikolajewitsch Gerassimow</code> | <code>1.0</code> |
-  | <code>Igor Stanislavovitsj Prokopenko</code> | <code>Angelo Lauricella</code>                 | <code>0.0</code> |
-  | <code>Кофе, Линда</code>                     | <code>Святлана Яўгенаўна Савіцкая</code>       | <code>0.0</code> |
-* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+- Size: 2,663,276 evaluation samples
+- Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+- Approximate statistics based on the first 1000 samples:
+
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+
+- Samples:
+
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+
+- Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+
   ```json
   {
       "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
@@ -262,41 +313,43 @@ You can fine-tune this model on your own dataset.
   ```
 
 ### Training Hyperparameters
+
 #### Non-Default Hyperparameters
 
 - `eval_strategy`: steps
-- `per_device_train_batch_size`: 5000
-- `per_device_eval_batch_size`: 5000
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
 - `gradient_accumulation_steps`: 4
-- `weight_decay`: 0.02
-- `num_train_epochs`: 10
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
 - `warmup_ratio`: 0.1
-- `fp16`: True
+- `fp16_opt_level`: O0
 - `load_best_model_at_end`: True
 - `optim`: adafactor
-- `gradient_checkpointing`: True
 
 #### All Hyperparameters
+
 <details><summary>Click to expand</summary>
 
 - `overwrite_output_dir`: False
 - `do_predict`: False
 - `eval_strategy`: steps
 - `prediction_loss_only`: True
-- `per_device_train_batch_size`: 5000
-- `per_device_eval_batch_size`: 5000
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
 - `per_gpu_train_batch_size`: None
 - `per_gpu_eval_batch_size`: None
 - `gradient_accumulation_steps`: 4
 - `eval_accumulation_steps`: None
 - `torch_empty_cache_steps`: None
-- `learning_rate`: 5e-05
-- `weight_decay`: 0.02
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
 - `adam_beta1`: 0.9
 - `adam_beta2`: 0.999
 - `adam_epsilon`: 1e-08
 - `max_grad_norm`: 1.0
-- `num_train_epochs`: 10
+- `num_train_epochs`: 8
 - `max_steps`: -1
 - `lr_scheduler_type`: linear
 - `lr_scheduler_kwargs`: {}
@@ -318,8 +371,8 @@ You can fine-tune this model on your own dataset.
 - `jit_mode_eval`: False
 - `use_ipex`: False
 - `bf16`: False
-- `fp16`: True
-- `fp16_opt_level`: O1
+- `fp16`: False
+- `fp16_opt_level`: O0
 - `half_precision_backend`: auto
 - `bf16_full_eval`: False
 - `fp16_full_eval`: False
@@ -364,7 +417,7 @@ You can fine-tune this model on your own dataset.
 - `hub_strategy`: every_save
 - `hub_private_repo`: None
 - `hub_always_push`: False
-- `gradient_checkpointing`: True
+- `gradient_checkpointing`: False
 - `gradient_checkpointing_kwargs`: None
 - `include_inputs_for_metrics`: False
 - `include_for_metrics`: []
@@ -372,7 +425,7 @@ You can fine-tune this model on your own dataset.
 - `fp16_backend`: auto
 - `push_to_hub_model_id`: None
 - `push_to_hub_organization`: None
-- `mp_parameters`: 
+- `mp_parameters`:
 - `auto_find_batch_size`: False
 - `full_determinism`: False
 - `torchdynamo`: None
@@ -397,24 +450,25 @@ You can fine-tune this model on your own dataset.
 </details>
 
 ### Training Logs
-| Epoch      | Step     | Training Loss | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
-|:----------:|:--------:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
-| -1         | -1       | -             | -               | 0.7195                                                                |
-| 0.9368     | 100      | -             | 0.0083          | 0.9597                                                                |
-| 1.8712     | 200      | -             | 0.0043          | 0.9877                                                                |
-| 2.8056     | 300      | -             | 0.0028          | 0.9936                                                                |
-| 3.7400     | 400      | -             | 0.0021          | 0.9954                                                                |
-| 4.6745     | 500      | 0.0224        | 0.0016          | 0.9964                                                                |
-| 5.6089     | 600      | -             | 0.0015          | 0.9970                                                                |
-| 6.5433     | 700      | -             | 0.0014          | 0.9974                                                                |
-| 7.4778     | 800      | -             | 0.0013          | 0.9975                                                                |
-| 8.4122     | 900      | -             | 0.0013          | 0.9977                                                                |
-| **9.3466** | **1000** | **0.0052**    | **0.0012**      | **0.9978**                                                            |
-| 9.9087     | 1060     | -             | 0.0012          | 0.9978                                                                |
-
-* The bold row denotes the saved checkpoint.
+
+| Epoch  | Step | Training Loss | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
+| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
+| 2.2553 | 1200 | -             | 0.0017          | 0.9956                                                                |
 
 ### Framework Versions
+
 - Python: 3.12.9
 - Sentence Transformers: 3.4.1
 - Transformers: 4.51.3
@@ -428,6 +482,7 @@ You can fine-tune this model on your own dataset.
 ### BibTeX
 
 #### Sentence Transformers
+
 ```bibtex
 @inproceedings{reimers-2019-sentence-bert,
     title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
@@ -441,6 +496,7 @@ You can fine-tune this model on your own dataset.
 ```
 
 #### ContrastiveLoss
+
 ```bibtex
 @inproceedings{hadsell2006dimensionality,
     author={Hadsell, R. and Chopra, S. and LeCun, Y.},
diff --git a/checkpoint-1000/1_Pooling/config.json b/checkpoint-1000/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-1000/1_Pooling/config.json
@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}
\ No newline at end of file
diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..3bc5608974f42cafdc8ed1ae922876e7c1ae90e5
--- /dev/null
+++ b/checkpoint-1000/README.md
@@ -0,0 +1,466 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2130621
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Kim Chol-sam
+  sentences:
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
+  sentences:
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
+  sentences:
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
+  sentences:
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
+  sentences:
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: sentence transformers paraphrase multilingual MiniLM L12 v2
+      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9817931272716349
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7197962999343872
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9722373310278887
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7091608047485352
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9675121928984912
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9770088489465266
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9944127523785896
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9587183163648803
+      name: Cosine Mcc
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.9818     |
+| cosine_accuracy_threshold | 0.7198     |
+| cosine_f1                 | 0.9722     |
+| cosine_f1_threshold       | 0.7092     |
+| cosine_precision          | 0.9675     |
+| cosine_recall             | 0.977      |
+| **cosine_ap**             | **0.9944** |
+| cosine_mcc                | 0.9587     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,130,621 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,663,276 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16_opt_level`: O0
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+
+#### 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`: 1000
+- `per_device_eval_batch_size`: 1000
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `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`: O0
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adafactor
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `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 | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->
\ No newline at end of file
diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-1000/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}
diff --git a/checkpoint-1000/config_sentence_transformers.json b/checkpoint-1000/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-1000/config_sentence_transformers.json
@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
\ No newline at end of file
diff --git a/checkpoint-1000/model.safetensors b/checkpoint-1000/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..73640d8f7f70e27e135807c6ab63bffc4c1cd512
--- /dev/null
+++ b/checkpoint-1000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cdf706594f9c2e35f539f5023cae863f9d5c0e8588348281d86e7ac79b4662
+size 470637416
diff --git a/checkpoint-1000/modules.json b/checkpoint-1000/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-1000/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"
+  }
+]
\ No newline at end of file
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b8c58ea739043f210901f0ab0fb962d19e7958fc
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c108fa814d36d19a8e9c702a9800909a0bdbcc7bbc32071418d14ec158efbaf5
+size 1715019
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7db666e6775b0f053ef0cbb331ebaa54f8182cd0
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31530f34a96cd557f736a4c9e2dbdab66da89f3ee40e3c858c87c688d4a1b9a1
+size 14645
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c026cbfbd78e0d251a49db6ad9188412f9899f74
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8985e0cd69062d78f38bea6c82894c697cf2eff7e9a24bf93fa0da194c1b5e7
+size 1465
diff --git a/checkpoint-1000/sentence_bert_config.json b/checkpoint-1000/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-1000/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}
\ No newline at end of file
diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1000/tokenizer.json b/checkpoint-1000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-1000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..59d5f0faee0a3010b3bfe7f0c72eebe378c700d3
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,217 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.002240537665784359,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1000",
+  "epoch": 1.8784608165180665,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.012530049309134483,
+      "eval_runtime": 812.6802,
+      "eval_samples_per_second": 3277.151,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
+      "eval_steps_per_second": 3.278,
+      "step": 100
+    },
+    {
+      "epoch": 0.37541060534960113,
+      "eval_loss": 0.009013425558805466,
+      "eval_runtime": 792.9843,
+      "eval_samples_per_second": 3358.548,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
+      "eval_steps_per_second": 3.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.5631159080244017,
+      "eval_loss": 0.006819029338657856,
+      "eval_runtime": 809.9704,
+      "eval_samples_per_second": 3288.115,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
+      "eval_steps_per_second": 3.289,
+      "step": 300
+    },
+    {
+      "epoch": 0.7508212106992023,
+      "eval_loss": 0.005150709766894579,
+      "eval_runtime": 797.9199,
+      "eval_samples_per_second": 3337.773,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
+      "eval_steps_per_second": 3.339,
+      "step": 400
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "grad_norm": 0.17396493256092072,
+      "learning_rate": 2.9428198433420364e-05,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "eval_loss": 0.003973629325628281,
+      "eval_runtime": 809.4532,
+      "eval_samples_per_second": 3290.216,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
+      "eval_steps_per_second": 3.291,
+      "step": 500
+    },
+    {
+      "epoch": 1.1276396058188645,
+      "eval_loss": 0.0032712339889258146,
+      "eval_runtime": 793.7573,
+      "eval_samples_per_second": 3355.277,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
+      "eval_steps_per_second": 3.356,
+      "step": 600
+    },
+    {
+      "epoch": 1.3153449084936648,
+      "eval_loss": 0.0028166945558041334,
+      "eval_runtime": 815.1943,
+      "eval_samples_per_second": 3267.044,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
+      "eval_steps_per_second": 3.268,
+      "step": 700
+    },
+    {
+      "epoch": 1.5030502111684654,
+      "eval_loss": 0.0026242006570100784,
+      "eval_runtime": 805.7115,
+      "eval_samples_per_second": 3305.496,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
+      "eval_steps_per_second": 3.306,
+      "step": 800
+    },
+    {
+      "epoch": 1.690755513843266,
+      "eval_loss": 0.002248650649562478,
+      "eval_runtime": 818.5338,
+      "eval_samples_per_second": 3253.715,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
+      "eval_steps_per_second": 3.255,
+      "step": 900
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "grad_norm": 0.07541557401418686,
+      "learning_rate": 2.5511749347258486e-05,
+      "loss": 0.0131,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "eval_loss": 0.002240537665784359,
+      "eval_runtime": 803.6286,
+      "eval_samples_per_second": 3314.063,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
+      "eval_steps_per_second": 3.315,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1000,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6aba0195c0abacac26202ea40cbb6012662a9ff
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
+size 6033
diff --git a/checkpoint-1000/unigram.json b/checkpoint-1000/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-1000/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-1100/1_Pooling/config.json b/checkpoint-1100/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-1100/1_Pooling/config.json
@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}
\ No newline at end of file
diff --git a/checkpoint-1100/README.md b/checkpoint-1100/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..b854316e034d2e39fdf0901261d0f057f057bd3d
--- /dev/null
+++ b/checkpoint-1100/README.md
@@ -0,0 +1,467 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2130621
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Kim Chol-sam
+  sentences:
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
+  sentences:
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
+  sentences:
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
+  sentences:
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
+  sentences:
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: sentence transformers paraphrase multilingual MiniLM L12 v2
+      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9828594815415578
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7552986741065979
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.973889221813201
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7401974201202393
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9661201195760486
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9817842882294052
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9950493119597241
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9611601510291333
+      name: Cosine Mcc
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value     |
+|:--------------------------|:----------|
+| cosine_accuracy           | 0.9829    |
+| cosine_accuracy_threshold | 0.7553    |
+| cosine_f1                 | 0.9739    |
+| cosine_f1_threshold       | 0.7402    |
+| cosine_precision          | 0.9661    |
+| cosine_recall             | 0.9818    |
+| **cosine_ap**             | **0.995** |
+| cosine_mcc                | 0.9612    |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,130,621 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,663,276 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16_opt_level`: O0
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+
+#### 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`: 1000
+- `per_device_eval_batch_size`: 1000
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `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`: O0
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adafactor
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `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 | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
+| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->
\ No newline at end of file
diff --git a/checkpoint-1100/config.json b/checkpoint-1100/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-1100/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}
diff --git a/checkpoint-1100/config_sentence_transformers.json b/checkpoint-1100/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-1100/config_sentence_transformers.json
@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
\ No newline at end of file
diff --git a/checkpoint-1100/model.safetensors b/checkpoint-1100/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b873dde2ea0dcd9a4564f3ed6586ee6cf87d4af4
--- /dev/null
+++ b/checkpoint-1100/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763540a5075ed486170f85323b5ee9b40182439ea8f51d889e8674424cce13c2
+size 470637416
diff --git a/checkpoint-1100/modules.json b/checkpoint-1100/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-1100/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"
+  }
+]
\ No newline at end of file
diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..03ef458f7ffb9345dd2acfe855ed8260ddc45d46
--- /dev/null
+++ b/checkpoint-1100/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0711e7f2b2b4728583424781a68346e4cb105f82c5b3e33e835ff6603b1b546
+size 1715019
diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..daf3e104f28697a178a58c60d9ce3a52fcceacaa
--- /dev/null
+++ b/checkpoint-1100/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d533d8579fdbb2634c2232f32ae13c2e79a071512c8f417a9f5453a5c0587c27
+size 14645
diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..df1b0fb5337749ce5e08702b420610e645c9e08f
--- /dev/null
+++ b/checkpoint-1100/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3efc25b9c32ace074d8642ed698ba4f27854c75c4022587a44f288f2399a9b
+size 1465
diff --git a/checkpoint-1100/sentence_bert_config.json b/checkpoint-1100/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-1100/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}
\ No newline at end of file
diff --git a/checkpoint-1100/special_tokens_map.json b/checkpoint-1100/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-1100/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1100/tokenizer.json b/checkpoint-1100/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-1100/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-1100/tokenizer_config.json b/checkpoint-1100/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-1100/tokenizer_config.json
@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c1ec352f7a38fdedbedf50fefef94348e203cdd4
--- /dev/null
+++ b/checkpoint-1100/trainer_state.json
@@ -0,0 +1,233 @@
+{
+  "best_global_step": 1100,
+  "best_metric": 0.0018734760815277696,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1100",
+  "epoch": 2.0675739089629284,
+  "eval_steps": 100,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.012530049309134483,
+      "eval_runtime": 812.6802,
+      "eval_samples_per_second": 3277.151,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
+      "eval_steps_per_second": 3.278,
+      "step": 100
+    },
+    {
+      "epoch": 0.37541060534960113,
+      "eval_loss": 0.009013425558805466,
+      "eval_runtime": 792.9843,
+      "eval_samples_per_second": 3358.548,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
+      "eval_steps_per_second": 3.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.5631159080244017,
+      "eval_loss": 0.006819029338657856,
+      "eval_runtime": 809.9704,
+      "eval_samples_per_second": 3288.115,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
+      "eval_steps_per_second": 3.289,
+      "step": 300
+    },
+    {
+      "epoch": 0.7508212106992023,
+      "eval_loss": 0.005150709766894579,
+      "eval_runtime": 797.9199,
+      "eval_samples_per_second": 3337.773,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
+      "eval_steps_per_second": 3.339,
+      "step": 400
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "grad_norm": 0.17396493256092072,
+      "learning_rate": 2.9428198433420364e-05,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "eval_loss": 0.003973629325628281,
+      "eval_runtime": 809.4532,
+      "eval_samples_per_second": 3290.216,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
+      "eval_steps_per_second": 3.291,
+      "step": 500
+    },
+    {
+      "epoch": 1.1276396058188645,
+      "eval_loss": 0.0032712339889258146,
+      "eval_runtime": 793.7573,
+      "eval_samples_per_second": 3355.277,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
+      "eval_steps_per_second": 3.356,
+      "step": 600
+    },
+    {
+      "epoch": 1.3153449084936648,
+      "eval_loss": 0.0028166945558041334,
+      "eval_runtime": 815.1943,
+      "eval_samples_per_second": 3267.044,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
+      "eval_steps_per_second": 3.268,
+      "step": 700
+    },
+    {
+      "epoch": 1.5030502111684654,
+      "eval_loss": 0.0026242006570100784,
+      "eval_runtime": 805.7115,
+      "eval_samples_per_second": 3305.496,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
+      "eval_steps_per_second": 3.306,
+      "step": 800
+    },
+    {
+      "epoch": 1.690755513843266,
+      "eval_loss": 0.002248650649562478,
+      "eval_runtime": 818.5338,
+      "eval_samples_per_second": 3253.715,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
+      "eval_steps_per_second": 3.255,
+      "step": 900
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "grad_norm": 0.07541557401418686,
+      "learning_rate": 2.5511749347258486e-05,
+      "loss": 0.0131,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "eval_loss": 0.002240537665784359,
+      "eval_runtime": 803.6286,
+      "eval_samples_per_second": 3314.063,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
+      "eval_steps_per_second": 3.315,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0675739089629284,
+      "eval_loss": 0.0018734760815277696,
+      "eval_runtime": 807.0812,
+      "eval_samples_per_second": 3299.886,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9828594815415578,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7552986741065979,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9950493119597241,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.973889221813201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7401974201202393,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9611601510291333,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9661201195760486,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9817842882294052,
+      "eval_steps_per_second": 3.301,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1000,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6aba0195c0abacac26202ea40cbb6012662a9ff
--- /dev/null
+++ b/checkpoint-1100/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
+size 6033
diff --git a/checkpoint-1100/unigram.json b/checkpoint-1100/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-1100/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-1200/1_Pooling/config.json b/checkpoint-1200/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-1200/1_Pooling/config.json
@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}
\ No newline at end of file
diff --git a/checkpoint-1200/README.md b/checkpoint-1200/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..242cb95f5c93fd570dc1df42c4d441e6d9b8df43
--- /dev/null
+++ b/checkpoint-1200/README.md
@@ -0,0 +1,468 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2130621
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Kim Chol-sam
+  sentences:
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
+  sentences:
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
+  sentences:
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
+  sentences:
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
+  sentences:
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: sentence transformers paraphrase multilingual MiniLM L12 v2
+      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9843050674356433
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.742120623588562
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9760932477723254
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.742120623588562
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9703216856372878
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9819338803033267
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9955554741842152
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.964449493634366
+      name: Cosine Mcc
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.9843     |
+| cosine_accuracy_threshold | 0.7421     |
+| cosine_f1                 | 0.9761     |
+| cosine_f1_threshold       | 0.7421     |
+| cosine_precision          | 0.9703     |
+| cosine_recall             | 0.9819     |
+| **cosine_ap**             | **0.9956** |
+| cosine_mcc                | 0.9644     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,130,621 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,663,276 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16_opt_level`: O0
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+
+#### 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`: 1000
+- `per_device_eval_batch_size`: 1000
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `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`: O0
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adafactor
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `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 | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
+| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
+| 2.2553 | 1200 | -             | 0.0017          | 0.9956                                                                |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->
\ No newline at end of file
diff --git a/checkpoint-1200/config.json b/checkpoint-1200/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-1200/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}
diff --git a/checkpoint-1200/config_sentence_transformers.json b/checkpoint-1200/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-1200/config_sentence_transformers.json
@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
\ No newline at end of file
diff --git a/checkpoint-1200/model.safetensors b/checkpoint-1200/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..758df5d10ff7af9db5b1be5837fa1db20cc72d2f
--- /dev/null
+++ b/checkpoint-1200/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a16798609ad3be64f1c33cafbc6d8595006225a97722265fbba67e2dfaf916a
+size 470637416
diff --git a/checkpoint-1200/modules.json b/checkpoint-1200/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-1200/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"
+  }
+]
\ No newline at end of file
diff --git a/checkpoint-1200/optimizer.pt b/checkpoint-1200/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..688a4c38248062de6965ef846f0ce9ad3a2b236b
--- /dev/null
+++ b/checkpoint-1200/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6c0d2369b6fe2e14855dd6ee01f523f4a5901a968149aedc664f3defacc964
+size 1715019
diff --git a/checkpoint-1200/rng_state.pth b/checkpoint-1200/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f7883f1663e6f9392cc038e07a44a0505edba1b0
--- /dev/null
+++ b/checkpoint-1200/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a5e12d95d9820ac91d074df8188d98ce5f4fc76cb3ec8a63d860d96a200697
+size 14645
diff --git a/checkpoint-1200/scheduler.pt b/checkpoint-1200/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..71a8a43af78ecac02cddf7ac3bc51a2133d1a52d
--- /dev/null
+++ b/checkpoint-1200/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdbea4967733a900bbe36cb7fab0e417825ab1560e9b509550180a0f55ecc51
+size 1465
diff --git a/checkpoint-1200/sentence_bert_config.json b/checkpoint-1200/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-1200/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}
\ No newline at end of file
diff --git a/checkpoint-1200/special_tokens_map.json b/checkpoint-1200/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-1200/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1200/tokenizer.json b/checkpoint-1200/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-1200/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-1200/tokenizer_config.json b/checkpoint-1200/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-1200/tokenizer_config.json
@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1200/trainer_state.json b/checkpoint-1200/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b35e26591e541dc6afd36c4085cc569cbc91bc99
--- /dev/null
+++ b/checkpoint-1200/trainer_state.json
@@ -0,0 +1,249 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 0.0017435119953006506,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1200",
+  "epoch": 2.255279211637729,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.012530049309134483,
+      "eval_runtime": 812.6802,
+      "eval_samples_per_second": 3277.151,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
+      "eval_steps_per_second": 3.278,
+      "step": 100
+    },
+    {
+      "epoch": 0.37541060534960113,
+      "eval_loss": 0.009013425558805466,
+      "eval_runtime": 792.9843,
+      "eval_samples_per_second": 3358.548,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
+      "eval_steps_per_second": 3.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.5631159080244017,
+      "eval_loss": 0.006819029338657856,
+      "eval_runtime": 809.9704,
+      "eval_samples_per_second": 3288.115,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
+      "eval_steps_per_second": 3.289,
+      "step": 300
+    },
+    {
+      "epoch": 0.7508212106992023,
+      "eval_loss": 0.005150709766894579,
+      "eval_runtime": 797.9199,
+      "eval_samples_per_second": 3337.773,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
+      "eval_steps_per_second": 3.339,
+      "step": 400
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "grad_norm": 0.17396493256092072,
+      "learning_rate": 2.9428198433420364e-05,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "eval_loss": 0.003973629325628281,
+      "eval_runtime": 809.4532,
+      "eval_samples_per_second": 3290.216,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
+      "eval_steps_per_second": 3.291,
+      "step": 500
+    },
+    {
+      "epoch": 1.1276396058188645,
+      "eval_loss": 0.0032712339889258146,
+      "eval_runtime": 793.7573,
+      "eval_samples_per_second": 3355.277,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
+      "eval_steps_per_second": 3.356,
+      "step": 600
+    },
+    {
+      "epoch": 1.3153449084936648,
+      "eval_loss": 0.0028166945558041334,
+      "eval_runtime": 815.1943,
+      "eval_samples_per_second": 3267.044,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
+      "eval_steps_per_second": 3.268,
+      "step": 700
+    },
+    {
+      "epoch": 1.5030502111684654,
+      "eval_loss": 0.0026242006570100784,
+      "eval_runtime": 805.7115,
+      "eval_samples_per_second": 3305.496,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
+      "eval_steps_per_second": 3.306,
+      "step": 800
+    },
+    {
+      "epoch": 1.690755513843266,
+      "eval_loss": 0.002248650649562478,
+      "eval_runtime": 818.5338,
+      "eval_samples_per_second": 3253.715,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
+      "eval_steps_per_second": 3.255,
+      "step": 900
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "grad_norm": 0.07541557401418686,
+      "learning_rate": 2.5511749347258486e-05,
+      "loss": 0.0131,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "eval_loss": 0.002240537665784359,
+      "eval_runtime": 803.6286,
+      "eval_samples_per_second": 3314.063,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
+      "eval_steps_per_second": 3.315,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0675739089629284,
+      "eval_loss": 0.0018734760815277696,
+      "eval_runtime": 807.0812,
+      "eval_samples_per_second": 3299.886,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9828594815415578,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7552986741065979,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9950493119597241,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.973889221813201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7401974201202393,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9611601510291333,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9661201195760486,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9817842882294052,
+      "eval_steps_per_second": 3.301,
+      "step": 1100
+    },
+    {
+      "epoch": 2.255279211637729,
+      "eval_loss": 0.0017435119953006506,
+      "eval_runtime": 802.6162,
+      "eval_samples_per_second": 3318.244,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9843050674356433,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.742120623588562,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955554741842152,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9760932477723254,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.742120623588562,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.964449493634366,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9703216856372878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9819338803033267,
+      "eval_steps_per_second": 3.319,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1000,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1200/training_args.bin b/checkpoint-1200/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6aba0195c0abacac26202ea40cbb6012662a9ff
--- /dev/null
+++ b/checkpoint-1200/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
+size 6033
diff --git a/checkpoint-1200/unigram.json b/checkpoint-1200/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-1200/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-1300/1_Pooling/config.json b/checkpoint-1300/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-1300/1_Pooling/config.json
@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}
\ No newline at end of file
diff --git a/checkpoint-1300/README.md b/checkpoint-1300/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..5fd2a478fc5e1e56ffeef38e9c5b0835aa37ad72
--- /dev/null
+++ b/checkpoint-1300/README.md
@@ -0,0 +1,469 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2130621
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Kim Chol-sam
+  sentences:
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
+  sentences:
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
+  sentences:
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
+  sentences:
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
+  sentences:
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: sentence transformers paraphrase multilingual MiniLM L12 v2
+      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9853564026313418
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.6976222991943359
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9776227541137591
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.6851664781570435
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9732136748238192
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9820719652946388
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9958172202316342
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9667334329094465
+      name: Cosine Mcc
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.9854     |
+| cosine_accuracy_threshold | 0.6976     |
+| cosine_f1                 | 0.9776     |
+| cosine_f1_threshold       | 0.6852     |
+| cosine_precision          | 0.9732     |
+| cosine_recall             | 0.9821     |
+| **cosine_ap**             | **0.9958** |
+| cosine_mcc                | 0.9667     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,130,621 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,663,276 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16_opt_level`: O0
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+
+#### 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`: 1000
+- `per_device_eval_batch_size`: 1000
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `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`: O0
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adafactor
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `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 | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+| 1.8785 | 1000 | 0.0131        | 0.0022          | 0.9944                                                                |
+| 2.0676 | 1100 | -             | 0.0019          | 0.9950                                                                |
+| 2.2553 | 1200 | -             | 0.0017          | 0.9956                                                                |
+| 2.4430 | 1300 | -             | 0.0019          | 0.9958                                                                |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->
\ No newline at end of file
diff --git a/checkpoint-1300/config.json b/checkpoint-1300/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-1300/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}
diff --git a/checkpoint-1300/config_sentence_transformers.json b/checkpoint-1300/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-1300/config_sentence_transformers.json
@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
\ No newline at end of file
diff --git a/checkpoint-1300/model.safetensors b/checkpoint-1300/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a8aa559c334c3fc66e03a9ddd27372987d07c981
--- /dev/null
+++ b/checkpoint-1300/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea639f895e7708a55ae3e3cfe23138278e63e6378e5bf609d6db6d629b9b438
+size 470637416
diff --git a/checkpoint-1300/modules.json b/checkpoint-1300/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-1300/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"
+  }
+]
\ No newline at end of file
diff --git a/checkpoint-1300/optimizer.pt b/checkpoint-1300/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..84fa920bf7210db539d9da0c26ab38415d0baa31
--- /dev/null
+++ b/checkpoint-1300/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1aa28c8815cf88ba694f02b5e15468bbaea3ce5e26506bd5c5ecd2c992ce7ce
+size 1715019
diff --git a/checkpoint-1300/rng_state.pth b/checkpoint-1300/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..312caed491c1e3e115c4dce10fd326d5b3636499
--- /dev/null
+++ b/checkpoint-1300/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05feb30fd5220f89a53d409e9778994ba1c22d885cba182f441469ca0d0b6f67
+size 14645
diff --git a/checkpoint-1300/scheduler.pt b/checkpoint-1300/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..799bc40dae8447a987d82cf80ca6b9dba41b96b1
--- /dev/null
+++ b/checkpoint-1300/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d567b69e284ba581e3f8e7237823c230a46309045fc28a621b856fd794bfd8
+size 1465
diff --git a/checkpoint-1300/sentence_bert_config.json b/checkpoint-1300/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-1300/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}
\ No newline at end of file
diff --git a/checkpoint-1300/special_tokens_map.json b/checkpoint-1300/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-1300/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1300/tokenizer.json b/checkpoint-1300/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-1300/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-1300/tokenizer_config.json b/checkpoint-1300/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-1300/tokenizer_config.json
@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1300/trainer_state.json b/checkpoint-1300/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ce6499d979c81a036c1c5a39c2575fc32c9f615d
--- /dev/null
+++ b/checkpoint-1300/trainer_state.json
@@ -0,0 +1,265 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 0.0017435119953006506,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1200",
+  "epoch": 2.4429845143125295,
+  "eval_steps": 100,
+  "global_step": 1300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.012530049309134483,
+      "eval_runtime": 812.6802,
+      "eval_samples_per_second": 3277.151,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
+      "eval_steps_per_second": 3.278,
+      "step": 100
+    },
+    {
+      "epoch": 0.37541060534960113,
+      "eval_loss": 0.009013425558805466,
+      "eval_runtime": 792.9843,
+      "eval_samples_per_second": 3358.548,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
+      "eval_steps_per_second": 3.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.5631159080244017,
+      "eval_loss": 0.006819029338657856,
+      "eval_runtime": 809.9704,
+      "eval_samples_per_second": 3288.115,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
+      "eval_steps_per_second": 3.289,
+      "step": 300
+    },
+    {
+      "epoch": 0.7508212106992023,
+      "eval_loss": 0.005150709766894579,
+      "eval_runtime": 797.9199,
+      "eval_samples_per_second": 3337.773,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
+      "eval_steps_per_second": 3.339,
+      "step": 400
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "grad_norm": 0.17396493256092072,
+      "learning_rate": 2.9428198433420364e-05,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "eval_loss": 0.003973629325628281,
+      "eval_runtime": 809.4532,
+      "eval_samples_per_second": 3290.216,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
+      "eval_steps_per_second": 3.291,
+      "step": 500
+    },
+    {
+      "epoch": 1.1276396058188645,
+      "eval_loss": 0.0032712339889258146,
+      "eval_runtime": 793.7573,
+      "eval_samples_per_second": 3355.277,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
+      "eval_steps_per_second": 3.356,
+      "step": 600
+    },
+    {
+      "epoch": 1.3153449084936648,
+      "eval_loss": 0.0028166945558041334,
+      "eval_runtime": 815.1943,
+      "eval_samples_per_second": 3267.044,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
+      "eval_steps_per_second": 3.268,
+      "step": 700
+    },
+    {
+      "epoch": 1.5030502111684654,
+      "eval_loss": 0.0026242006570100784,
+      "eval_runtime": 805.7115,
+      "eval_samples_per_second": 3305.496,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
+      "eval_steps_per_second": 3.306,
+      "step": 800
+    },
+    {
+      "epoch": 1.690755513843266,
+      "eval_loss": 0.002248650649562478,
+      "eval_runtime": 818.5338,
+      "eval_samples_per_second": 3253.715,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
+      "eval_steps_per_second": 3.255,
+      "step": 900
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "grad_norm": 0.07541557401418686,
+      "learning_rate": 2.5511749347258486e-05,
+      "loss": 0.0131,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8784608165180665,
+      "eval_loss": 0.002240537665784359,
+      "eval_runtime": 803.6286,
+      "eval_samples_per_second": 3314.063,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9817931272716349,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7197962999343872,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9944127523785896,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9722373310278887,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7091608047485352,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9587183163648803,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9675121928984912,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9770088489465266,
+      "eval_steps_per_second": 3.315,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0675739089629284,
+      "eval_loss": 0.0018734760815277696,
+      "eval_runtime": 807.0812,
+      "eval_samples_per_second": 3299.886,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9828594815415578,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7552986741065979,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9950493119597241,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.973889221813201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7401974201202393,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9611601510291333,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9661201195760486,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9817842882294052,
+      "eval_steps_per_second": 3.301,
+      "step": 1100
+    },
+    {
+      "epoch": 2.255279211637729,
+      "eval_loss": 0.0017435119953006506,
+      "eval_runtime": 802.6162,
+      "eval_samples_per_second": 3318.244,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9843050674356433,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.742120623588562,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955554741842152,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9760932477723254,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.742120623588562,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.964449493634366,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9703216856372878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9819338803033267,
+      "eval_steps_per_second": 3.319,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4429845143125295,
+      "eval_loss": 0.001928201992996037,
+      "eval_runtime": 818.5215,
+      "eval_samples_per_second": 3253.764,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9853564026313418,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.6976222991943359,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9958172202316342,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9776227541137591,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6851664781570435,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9667334329094465,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9732136748238192,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9820719652946388,
+      "eval_steps_per_second": 3.255,
+      "step": 1300
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1000,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1300/training_args.bin b/checkpoint-1300/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6aba0195c0abacac26202ea40cbb6012662a9ff
--- /dev/null
+++ b/checkpoint-1300/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
+size 6033
diff --git a/checkpoint-1300/unigram.json b/checkpoint-1300/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-1300/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-900/1_Pooling/config.json b/checkpoint-900/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-900/1_Pooling/config.json
@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}
\ No newline at end of file
diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..683350c1ce91442d3fa01de820e3af30b94b218f
--- /dev/null
+++ b/checkpoint-900/README.md
@@ -0,0 +1,465 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2130621
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+widget:
+- source_sentence: Kim Chol-sam
+  sentences:
+  - Stankevich Sergey Nikolayevich
+  - Kim Chin-So’k
+  - Julen Lopetegui Agote
+- source_sentence: دينا بنت عبد الحميد
+  sentences:
+  - Alexia van Amsberg
+  - Anthony Nicholas Colin Maitland Biddulph, 5th Baron Biddulph
+  - Dina bint Abdul-Hamíd
+- source_sentence: Մուհամեդ բեն Նաիֆ Ալ Սաուդ
+  sentences:
+  - Karpov Anatoly Evgenyevich
+  - GNPower Mariveles Coal Plant [former]
+  - Muhammed bin Nayef bin Abdul Aziz Al Saud
+- source_sentence: Edward Gnehm
+  sentences:
+  - Шауэрте, Хартмут
+  - Ханзада Филипп, Эдинбург герцогі
+  - AFX
+- source_sentence: Schori i Lidingö
+  sentences:
+  - Yordan Canev
+  - ကားပေါ့ အန်နာတိုလီ
+  - BYSTROV, Mikhail Ivanovich
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+model-index:
+- name: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: sentence transformers paraphrase multilingual MiniLM L12 v2
+      type: sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9801973506353069
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7349117994308472
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9698356230196407
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7348856329917908
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9641228578901284
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9756164919507957
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9938133122786723
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9551340483533577
+      name: Cosine Mcc
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2-name-matcher-original
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision 86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### 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: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Schori i Lidingö',
+    'Yordan Canev',
+    'ကားပေါ့ အန်နာတိုလီ',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+#### Binary Classification
+
+* Dataset: `sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.9802     |
+| cosine_accuracy_threshold | 0.7349     |
+| cosine_f1                 | 0.9698     |
+| cosine_f1_threshold       | 0.7349     |
+| cosine_precision          | 0.9641     |
+| cosine_recall             | 0.9756     |
+| **cosine_ap**             | **0.9938** |
+| cosine_mcc                | 0.9551     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,130,621 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                        | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.32 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.16 tokens</li><li>max: 54 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.34</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                         | sentence2                           | label            |
+  |:----------------------------------|:------------------------------------|:-----------------|
+  | <code>캐스린 설리번</code>              | <code>Kathryn D. Sullivanová</code> | <code>1.0</code> |
+  | <code>ଶିବରାଜ ଅଧାଲରାଓ ପାଟିଲ</code> | <code>Aleksander Lubocki</code>     | <code>0.0</code> |
+  | <code>Пырванов, Георги</code>     | <code>アナトーリー・セルジュコフ</code>          | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 2,663,276 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.34 tokens</li><li>max: 102 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 9.11 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.33</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                             | sentence2                              | label            |
+  |:--------------------------------------|:---------------------------------------|:-----------------|
+  | <code>Ева Херман</code>               | <code>I Xuan Karlos</code>             | <code>0.0</code> |
+  | <code>Кличков Андрій Євгенович</code> | <code>Андрэй Яўгенавіч Клычкоў</code>  | <code>1.0</code> |
+  | <code>Кинах А.</code>                 | <code>Senator John Hickenlooper</code> | <code>0.0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 1000
+- `per_device_eval_batch_size`: 1000
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 8
+- `warmup_ratio`: 0.1
+- `fp16_opt_level`: O0
+- `load_best_model_at_end`: True
+- `optim`: adafactor
+
+#### 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`: 1000
+- `per_device_eval_batch_size`: 1000
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 4
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 8
+- `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`: O0
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adafactor
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: 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
+- `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 | Validation Loss | sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------------------------------------------------:|
+| -1     | -1   | -             | -               | 0.7140                                                                |
+| 0.1877 | 100  | -             | 0.0125          | 0.8849                                                                |
+| 0.3754 | 200  | -             | 0.0090          | 0.9369                                                                |
+| 0.5631 | 300  | -             | 0.0068          | 0.9630                                                                |
+| 0.7508 | 400  | -             | 0.0052          | 0.9774                                                                |
+| 0.9385 | 500  | 0.0409        | 0.0040          | 0.9845                                                                |
+| 1.1276 | 600  | -             | 0.0033          | 0.9887                                                                |
+| 1.3153 | 700  | -             | 0.0028          | 0.9911                                                                |
+| 1.5031 | 800  | -             | 0.0026          | 0.9927                                                                |
+| 1.6908 | 900  | -             | 0.0022          | 0.9938                                                                |
+
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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.*
+-->
\ No newline at end of file
diff --git a/checkpoint-900/config.json b/checkpoint-900/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-900/config.json
@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}
diff --git a/checkpoint-900/config_sentence_transformers.json b/checkpoint-900/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-900/config_sentence_transformers.json
@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
\ No newline at end of file
diff --git a/checkpoint-900/model.safetensors b/checkpoint-900/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..795e6aaa670415820ca709514edbe530bdea1aaa
--- /dev/null
+++ b/checkpoint-900/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd22f29179cb59eb49ab1e22762c421371c4a0057f02dd94030fc6b968320a5
+size 470637416
diff --git a/checkpoint-900/modules.json b/checkpoint-900/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-900/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"
+  }
+]
\ No newline at end of file
diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1977f7f965df8dcac656820a8f691ac8ff03ec37
--- /dev/null
+++ b/checkpoint-900/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8991a774d54025a5dcc46dbfaa413ba269663f199753722d2a3b79cefa8b292
+size 1715019
diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c6a5ab15ecd4a2fef9af49c645654df65ebde454
--- /dev/null
+++ b/checkpoint-900/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b85d95a42799e9a94a2b86a10328a7da2fb159a0243740b6c87e8c3319eabf
+size 14645
diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1efe206ea47391412c8839ac9f5454484a614dcb
--- /dev/null
+++ b/checkpoint-900/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c98de6545907d56f9ea5ea2c9583eab89319b7449506f9ce652f5af5699468d
+size 1465
diff --git a/checkpoint-900/sentence_bert_config.json b/checkpoint-900/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-900/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}
\ No newline at end of file
diff --git a/checkpoint-900/special_tokens_map.json b/checkpoint-900/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-900/special_tokens_map.json
@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-900/tokenizer.json b/checkpoint-900/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-900/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-900/tokenizer_config.json b/checkpoint-900/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-900/tokenizer_config.json
@@ -0,0 +1,65 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c7cdd0b7791a686e5a68fa0cb88f11e29aff85b4
--- /dev/null
+++ b/checkpoint-900/trainer_state.json
@@ -0,0 +1,194 @@
+{
+  "best_global_step": 900,
+  "best_metric": 0.002248650649562478,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-900",
+  "epoch": 1.690755513843266,
+  "eval_steps": 100,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18770530267480057,
+      "eval_loss": 0.012530049309134483,
+      "eval_runtime": 812.6802,
+      "eval_samples_per_second": 3277.151,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.8778235859541618,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7128396034240723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.8848748516159781,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.812583495899967,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6880456209182739,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.7185793630359445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.7900823930955021,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8364038065429271,
+      "eval_steps_per_second": 3.278,
+      "step": 100
+    },
+    {
+      "epoch": 0.37541060534960113,
+      "eval_loss": 0.009013425558805466,
+      "eval_runtime": 792.9843,
+      "eval_samples_per_second": 3358.548,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9164113424048541,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7378441095352173,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9368603114664952,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.8729798695775446,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7272344827651978,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.8103205315460159,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8605654745268148,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.8857576838544123,
+      "eval_steps_per_second": 3.359,
+      "step": 200
+    },
+    {
+      "epoch": 0.5631159080244017,
+      "eval_loss": 0.006819029338657856,
+      "eval_runtime": 809.9704,
+      "eval_samples_per_second": 3288.115,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9398298338890391,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9629957356284182,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9088032597499417,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449667453765869,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.864029341509194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.8990159430733201,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9188060251084542,
+      "eval_steps_per_second": 3.289,
+      "step": 300
+    },
+    {
+      "epoch": 0.7508212106992023,
+      "eval_loss": 0.005150709766894579,
+      "eval_runtime": 797.9199,
+      "eval_samples_per_second": 3337.773,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9560016220600163,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7553268671035767,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9774059659768239,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9333702119012406,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7449506521224976,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9005457325671423,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.916037892637527,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9513710688929036,
+      "eval_steps_per_second": 3.339,
+      "step": 400
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "grad_norm": 0.17396493256092072,
+      "learning_rate": 2.9428198433420364e-05,
+      "loss": 0.0409,
+      "step": 500
+    },
+    {
+      "epoch": 0.9385265133740028,
+      "eval_loss": 0.003973629325628281,
+      "eval_runtime": 809.4532,
+      "eval_samples_per_second": 3290.216,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9655950557207654,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7622435092926025,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9845099503823473,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9477742208778024,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7535413503646851,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9221773981286795,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9367750202319935,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9590347859107281,
+      "eval_steps_per_second": 3.291,
+      "step": 500
+    },
+    {
+      "epoch": 1.1276396058188645,
+      "eval_loss": 0.0032712339889258146,
+      "eval_runtime": 793.7573,
+      "eval_samples_per_second": 3355.277,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9712722657775374,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7610360383987427,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9887055977101925,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9564087809158087,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7610177993774414,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9350876149915242,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9471753898932449,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9658239646502422,
+      "eval_steps_per_second": 3.356,
+      "step": 600
+    },
+    {
+      "epoch": 1.3153449084936648,
+      "eval_loss": 0.0028166945558041334,
+      "eval_runtime": 815.1943,
+      "eval_samples_per_second": 3267.044,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9751246583160614,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7577522993087769,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911117019106511,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9621558129059113,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7424367666244507,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.943665667488554,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9536134909690983,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9708525597505264,
+      "eval_steps_per_second": 3.268,
+      "step": 700
+    },
+    {
+      "epoch": 1.5030502111684654,
+      "eval_loss": 0.0026242006570100784,
+      "eval_runtime": 805.7115,
+      "eval_samples_per_second": 3305.496,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9782673995974888,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7254683971405029,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9927214598054878,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9669240257663667,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7145971059799194,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9507846488068235,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9597660102710608,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9741896137072368,
+      "eval_steps_per_second": 3.306,
+      "step": 800
+    },
+    {
+      "epoch": 1.690755513843266,
+      "eval_loss": 0.002248650649562478,
+      "eval_runtime": 818.5338,
+      "eval_samples_per_second": 3253.715,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9801973506353069,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7349117994308472,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9938133122786723,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9698356230196407,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7348856329917908,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9551340483533577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9641228578901284,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9756164919507957,
+      "eval_steps_per_second": 3.255,
+      "step": 900
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1000,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f6aba0195c0abacac26202ea40cbb6012662a9ff
--- /dev/null
+++ b/checkpoint-900/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
+size 6033
diff --git a/checkpoint-900/unigram.json b/checkpoint-900/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-900/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/eval/binary_classification_evaluation_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_results.csv b/eval/binary_classification_evaluation_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_results.csv
index 4c5dfba18a99f41287ca9807760bdb7cd7d0e708..6ea0a1b02bf5de42c5914dcff7b9a0505585b736 100644
--- a/eval/binary_classification_evaluation_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_results.csv
+++ b/eval/binary_classification_evaluation_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_results.csv
@@ -1,12 +1,19 @@
 epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
-0.936768149882904,100,0.9330529793864755,0.66396797,0.8990018609372358,0.8846836847946726,0.913791126905881,0.65369195,0.9596591982248662,0.8488676021429209
-1.8711943793911008,200,0.9683099913640971,0.6799859,0.9520018198362147,0.9445886468795847,0.9595322710076808,0.6799859,0.987669070948898,0.9284143244509058
-2.8056206088992974,300,0.9790110013892539,0.70408267,0.9680662667809197,0.9648143930767479,0.9713401352745615,0.70297325,0.9935758649482886,0.9524469797852624
-3.740046838407494,400,0.9837419742424811,0.71141905,0.975348704810703,0.9687853426826509,0.9820016049524246,0.69665205,0.9954100421733855,0.963270232791414
-4.674473067915691,500,0.986370292494274,0.73912907,0.9792820044518008,0.975107979086156,0.9834919179181474,0.73912907,0.996439193909599,0.9691467317957321
-5.608899297423887,600,0.9884729470957083,0.7460525,0.9824360661365067,0.9805847418912745,0.9842943941304597,0.7435638,0.9969945004512654,0.9738614226726382
-6.543325526932084,700,0.9893740847820374,0.720954,0.9838035826704058,0.9822857142857143,0.9853261492605755,0.720954,0.997357375070481,0.9758996171607873
-7.477751756440281,800,0.9898246536252018,0.7261426,0.9844654628833477,0.9845218986470993,0.9844090335893615,0.72277415,0.9975494130839752,0.9769000718683564
-8.412177985948478,900,0.9902752224683663,0.68553466,0.9852413242919824,0.9794924087922049,0.9910581222056631,0.65824556,0.9977460917001926,0.9780277137066985
-9.346604215456674,1000,0.9905380542935456,0.67906445,0.9856131536880567,0.9816899806664392,0.9895678092399404,0.67906445,0.9977983578816215,0.9785817179348335
-9.908665105386417,1060,0.9905380542935456,0.67906445,0.9856131536880567,0.9816899806664392,0.9895678092399404,0.67906445,0.9977983578816215,0.9785817179348335
+1.8598130841121496,100,0.9346675177411482,0.67952216,0.9003093846682708,0.8945690538540362,0.9061238611463499,0.6791203,0.9564959700255526,0.8517640890817079
+3.710280373831776,200,0.9564450118274321,0.69247603,0.9339482974604258,0.9223934315600045,0.9457963326029293,0.6891077,0.9756899897636082,0.9016239916822852
+5.5607476635514015,300,0.9622273119813765,0.7210211,0.9425234975790372,0.9312246735704638,0.9540998731403529,0.7118325,0.9799459083669457,0.9144248443043316
+5.897196261682243,318,0.9622273119813765,0.7210211,0.9425234975790372,0.9312246735704638,0.9540998731403529,0.7118325,0.9799459083669457,0.9144248443043316
+0.18770530267480057,100,0.8778235859541618,0.7128396,0.812583495899967,0.7900823930955021,0.8364038065429271,0.6880456,0.8848748516159781,0.7185793630359445
+0.37541060534960113,200,0.9164113424048541,0.7378441,0.8729798695775446,0.8605654745268148,0.8857576838544123,0.7272345,0.9368603114664952,0.8103205315460159
+0.5631159080244017,300,0.9398298338890391,0.74496675,0.9088032597499417,0.8990159430733201,0.9188060251084542,0.74496675,0.9629957356284182,0.864029341509194
+0.7508212106992023,400,0.9560016220600163,0.75532687,0.9333702119012406,0.916037892637527,0.9513710688929036,0.74495065,0.9774059659768239,0.9005457325671423
+0.9385265133740028,500,0.9655950557207654,0.7622435,0.9477742208778024,0.9367750202319935,0.9590347859107281,0.75354135,0.9845099503823473,0.9221773981286795
+1.1276396058188645,600,0.9712722657775374,0.76103604,0.9564087809158087,0.9471753898932449,0.9658239646502422,0.7610178,0.9887055977101925,0.9350876149915242
+1.3153449084936648,700,0.9751246583160614,0.7577523,0.9621558129059113,0.9536134909690983,0.9708525597505264,0.74243677,0.9911117019106511,0.943665667488554
+1.5030502111684654,800,0.9782673995974888,0.7254684,0.9669240257663667,0.9597660102710608,0.9741896137072368,0.7145971,0.9927214598054878,0.9507846488068235
+1.690755513843266,900,0.9801973506353069,0.7349118,0.9698356230196407,0.9641228578901284,0.9756164919507957,0.73488563,0.9938133122786723,0.9551340483533577
+1.8784608165180665,1000,0.9817931272716349,0.7197963,0.9722373310278887,0.9675121928984912,0.9770088489465266,0.7091608,0.9944127523785896,0.9587183163648803
+2.0675739089629284,1100,0.9828594815415578,0.7552987,0.973889221813201,0.9661201195760486,0.9817842882294052,0.7401974,0.9950493119597241,0.9611601510291333
+2.255279211637729,1200,0.9843050674356433,0.7421206,0.9760932477723254,0.9703216856372878,0.9819338803033267,0.7421206,0.9955554741842152,0.964449493634366
+2.4429845143125295,1300,0.9853564026313418,0.6976223,0.9776227541137591,0.9732136748238192,0.9820719652946388,0.6851665,0.9958172202316342,0.9667334329094465
+2.4429845143125295,1300,0.9843050674356433,0.7421206,0.9760932477723254,0.9703216856372878,0.9819338803033267,0.7421206,0.9955554741842152,0.964449493634366
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..758df5d10ff7af9db5b1be5837fa1db20cc72d2f
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a16798609ad3be64f1c33cafbc6d8595006225a97722265fbba67e2dfaf916a
+size 470637416
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/training_args.bin b/training_args.bin
index d9dc73de16e341766a62f00cd26c21c6f69c3391..f6aba0195c0abacac26202ea40cbb6012662a9ff 100644
--- a/training_args.bin
+++ b/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319aaa354e613c6db82c6bb78290f3da04198ef2c7a75b61b314fa305ed33c45
+oid sha256:9339753774865faea550d7da93688221ca0f43171c16e3034645a2149992c8a6
 size 6033