diff --git a/1_Pooling/config.json b/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/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-1386/1_Pooling/config.json b/checkpoint-1386/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-1386/1_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-1386/README.md b/checkpoint-1386/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e7fce08a6b26f72fadc423535cf0154e5f8e63ed
--- /dev/null
+++ b/checkpoint-1386/README.md
@@ -0,0 +1,460 @@
+---
+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: 0.9846242227629088
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.6801187992095947
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9765449140552956
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.6780189275741577
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9721848413657824
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9809442711989229
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9955904030209028
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9651303277408154
+      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           | 0.9846     |
+| cosine_accuracy_threshold | 0.6801     |
+| cosine_f1                 | 0.9765     |
+| cosine_f1_threshold       | 0.678      |
+| cosine_precision          | 0.9722     |
+| cosine_recall             | 0.9809     |
+| **cosine_ap**             | **0.9956** |
+| cosine_mcc                | 0.9651     |
+
+<!--
+## 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`: epoch
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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                                                                |
+| 0.7207 | 500  | 0.038         | -               | -                                                                     |
+| 0.9989 | 693  | -             | 0.0028          | 0.9911                                                                |
+| 1.4425 | 1000 | 0.0128        | -               | -                                                                     |
+| 1.9989 | 1386 | -             | 0.0021          | 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-1386/config.json b/checkpoint-1386/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-1386/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-1386/config_sentence_transformers.json b/checkpoint-1386/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-1386/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-1386/model.safetensors b/checkpoint-1386/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d2e01043a8ccef7aa373f5618ce0d01e869e7597
--- /dev/null
+++ b/checkpoint-1386/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63c4102bbc807f6f65e6dfc340ebdf81b6d809419616e5c686dc0ae4ee24c69
+size 470637416
diff --git a/checkpoint-1386/modules.json b/checkpoint-1386/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-1386/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-1386/optimizer.pt b/checkpoint-1386/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1ceb3da28e6e09293766035251914eaaccc068d3
--- /dev/null
+++ b/checkpoint-1386/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23860257dbcfd9b5b597ed0f71ec9d1d0888d586ddccbe366e3c4cea28a49c54
+size 1715019
diff --git a/checkpoint-1386/rng_state.pth b/checkpoint-1386/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e1d2cea903a56a37e239bf6617ac96d038c2e40
--- /dev/null
+++ b/checkpoint-1386/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafafda98c3eee33da2fc3dc512fb690207c63cd6c23669bf103b6115333673f
+size 14645
diff --git a/checkpoint-1386/scaler.pt b/checkpoint-1386/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..79a79c76ea8e0c8590655d5cc9f51a2c46c1d391
--- /dev/null
+++ b/checkpoint-1386/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cf4f866900877d5a70b5a4212850bd6349868cb41fa3deed374b2e1ff32fd1
+size 1383
diff --git a/checkpoint-1386/scheduler.pt b/checkpoint-1386/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4c4bea9017104956e6b3d74d66f8d3a7a8684d75
--- /dev/null
+++ b/checkpoint-1386/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0f4146f2cb078d3608133188b68bec6910432c8f56446c257e96b3d46d2b17
+size 1465
diff --git a/checkpoint-1386/sentence_bert_config.json b/checkpoint-1386/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-1386/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-1386/special_tokens_map.json b/checkpoint-1386/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-1386/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-1386/tokenizer.json b/checkpoint-1386/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-1386/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-1386/tokenizer_config.json b/checkpoint-1386/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-1386/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-1386/trainer_state.json b/checkpoint-1386/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d8192d5fa18329c51ecf875c1ab151aab43a8f87
--- /dev/null
+++ b/checkpoint-1386/trainer_state.json
@@ -0,0 +1,89 @@
+{
+  "best_global_step": 1386,
+  "best_metric": 0.002118302509188652,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-1386",
+  "epoch": 1.998918918918919,
+  "eval_steps": 100,
+  "global_step": 1386,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.15965162217617035,
+      "learning_rate": 2.7341619887730554e-05,
+      "loss": 0.038,
+      "step": 500
+    },
+    {
+      "epoch": 0.9989189189189189,
+      "eval_loss": 0.002777691464871168,
+      "eval_runtime": 792.7494,
+      "eval_samples_per_second": 3359.543,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.975327415818089,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7701693773269653,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911172257655966,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9624723810391563,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7597355842590332,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9441287064717891,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9527175567355498,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9724290300680068,
+      "eval_steps_per_second": 4.375,
+      "step": 693
+    },
+    {
+      "epoch": 1.4425225225225224,
+      "grad_norm": 0.11966603249311447,
+      "learning_rate": 2.1327185244587008e-05,
+      "loss": 0.0128,
+      "step": 1000
+    },
+    {
+      "epoch": 1.998918918918919,
+      "eval_loss": 0.002118302509188652,
+      "eval_runtime": 789.0568,
+      "eval_samples_per_second": 3375.265,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9846242227629088,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.6801187992095947,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955904030209028,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9765449140552956,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6780189275741577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9651303277408154,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9721848413657824,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9809442711989229,
+      "eval_steps_per_second": 4.395,
+      "step": 1386
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2772,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 768,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1386/training_args.bin b/checkpoint-1386/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65b989c1e3d30efe64e2dc0572f41454e6d26706
--- /dev/null
+++ b/checkpoint-1386/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee490aac80277022fdde76dd6763dbabee88802149f3f246e7d0572b504fcdaf
+size 6097
diff --git a/checkpoint-1386/unigram.json b/checkpoint-1386/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-1386/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-2079/1_Pooling/config.json b/checkpoint-2079/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-2079/1_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-2079/README.md b/checkpoint-2079/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..2f6f6062257574a5d84a84b819ba0067bed9bbea
--- /dev/null
+++ b/checkpoint-2079/README.md
@@ -0,0 +1,463 @@
+---
+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: 0.9879171547865789
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7181636691093445
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9815604299892273
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7181636691093445
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9775832353646149
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.98557011840788
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.996840725826042
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9725931427811844
+      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           | 0.9879     |
+| cosine_accuracy_threshold | 0.7182     |
+| cosine_f1                 | 0.9816     |
+| cosine_f1_threshold       | 0.7182     |
+| cosine_precision          | 0.9776     |
+| cosine_recall             | 0.9856     |
+| **cosine_ap**             | **0.9968** |
+| cosine_mcc                | 0.9726     |
+
+<!--
+## 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`: epoch
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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                                                                |
+| 0.7207 | 500  | 0.038         | -               | -                                                                     |
+| 0.9989 | 693  | -             | 0.0028          | 0.9911                                                                |
+| 1.4425 | 1000 | 0.0128        | -               | -                                                                     |
+| 1.9989 | 1386 | -             | 0.0021          | 0.9956                                                                |
+| 2.1643 | 1500 | 0.0084        | -               | -                                                                     |
+| 2.8850 | 2000 | 0.0065        | -               | -                                                                     |
+| 2.9989 | 2079 | -             | 0.0015          | 0.9968                                                                |
+
+
+### 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-2079/config.json b/checkpoint-2079/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-2079/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-2079/config_sentence_transformers.json b/checkpoint-2079/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-2079/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-2079/model.safetensors b/checkpoint-2079/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8cd0ac735560ce07b6eaa9920bbcbc853373fd3a
--- /dev/null
+++ b/checkpoint-2079/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4aae24e60c6b621f1ba97cb0d24aabcab5321c4240d46d5edb7e80659934ee
+size 470637416
diff --git a/checkpoint-2079/modules.json b/checkpoint-2079/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-2079/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-2079/optimizer.pt b/checkpoint-2079/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..11242a58022c29a7f4989c59bc4850b2bedaa592
--- /dev/null
+++ b/checkpoint-2079/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e098921ba43359be5ed80e5ba27c5533b3a15897c5d1e31312ca9a0532d345
+size 1715019
diff --git a/checkpoint-2079/rng_state.pth b/checkpoint-2079/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7aca73bbfbfbe67944f0d78581aca7162bce6c09
--- /dev/null
+++ b/checkpoint-2079/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bc5024a787692a4d7f38816d8d4cebfac75844ad0e708d5509da8b49d34e47
+size 14645
diff --git a/checkpoint-2079/scaler.pt b/checkpoint-2079/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..519b3a3a3f32d908b25eea621abfd90a82b214f7
--- /dev/null
+++ b/checkpoint-2079/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10354d1d65a8ea0cab60b6880392a6fdef91bdc8d2eafbb18ca1599d3a27f7d
+size 1383
diff --git a/checkpoint-2079/scheduler.pt b/checkpoint-2079/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..42450f363e1f6bb55324eb9d1c579a55f6a169ec
--- /dev/null
+++ b/checkpoint-2079/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f50b78397a5b4f9a0d3308e8b1ad396b4267f9f2fa04a1619312b44f7b2ef77
+size 1465
diff --git a/checkpoint-2079/sentence_bert_config.json b/checkpoint-2079/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-2079/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-2079/special_tokens_map.json b/checkpoint-2079/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-2079/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-2079/tokenizer.json b/checkpoint-2079/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-2079/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-2079/tokenizer_config.json b/checkpoint-2079/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-2079/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-2079/trainer_state.json b/checkpoint-2079/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..a6a2d12b3198c559f75fdd9ad95562d2a7a9d1ba
--- /dev/null
+++ b/checkpoint-2079/trainer_state.json
@@ -0,0 +1,119 @@
+{
+  "best_global_step": 2079,
+  "best_metric": 0.0014588695485144854,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-2079",
+  "epoch": 2.998918918918919,
+  "eval_steps": 100,
+  "global_step": 2079,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.15965162217617035,
+      "learning_rate": 2.7341619887730554e-05,
+      "loss": 0.038,
+      "step": 500
+    },
+    {
+      "epoch": 0.9989189189189189,
+      "eval_loss": 0.002777691464871168,
+      "eval_runtime": 792.7494,
+      "eval_samples_per_second": 3359.543,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.975327415818089,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7701693773269653,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911172257655966,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9624723810391563,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7597355842590332,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9441287064717891,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9527175567355498,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9724290300680068,
+      "eval_steps_per_second": 4.375,
+      "step": 693
+    },
+    {
+      "epoch": 1.4425225225225224,
+      "grad_norm": 0.11966603249311447,
+      "learning_rate": 2.1327185244587008e-05,
+      "loss": 0.0128,
+      "step": 1000
+    },
+    {
+      "epoch": 1.998918918918919,
+      "eval_loss": 0.002118302509188652,
+      "eval_runtime": 789.0568,
+      "eval_samples_per_second": 3375.265,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9846242227629088,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.6801187992095947,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955904030209028,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9765449140552956,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6780189275741577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9651303277408154,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9721848413657824,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9809442711989229,
+      "eval_steps_per_second": 4.395,
+      "step": 1386
+    },
+    {
+      "epoch": 2.1643243243243244,
+      "grad_norm": 0.04637068510055542,
+      "learning_rate": 1.5312750601443466e-05,
+      "loss": 0.0084,
+      "step": 1500
+    },
+    {
+      "epoch": 2.885045045045045,
+      "grad_norm": 0.07652924209833145,
+      "learning_rate": 9.29831595829992e-06,
+      "loss": 0.0065,
+      "step": 2000
+    },
+    {
+      "epoch": 2.998918918918919,
+      "eval_loss": 0.0014588695485144854,
+      "eval_runtime": 782.4422,
+      "eval_samples_per_second": 3403.799,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9879171547865789,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7181636691093445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.996840725826042,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9815604299892273,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7181636691093445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9725931427811844,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9775832353646149,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.98557011840788,
+      "eval_steps_per_second": 4.432,
+      "step": 2079
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2772,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 768,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2079/training_args.bin b/checkpoint-2079/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65b989c1e3d30efe64e2dc0572f41454e6d26706
--- /dev/null
+++ b/checkpoint-2079/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee490aac80277022fdde76dd6763dbabee88802149f3f246e7d0572b504fcdaf
+size 6097
diff --git a/checkpoint-2079/unigram.json b/checkpoint-2079/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-2079/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-2772/1_Pooling/config.json b/checkpoint-2772/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-2772/1_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-2772/README.md b/checkpoint-2772/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..9a84e5978ee70bae5e9e71ca5147d9d57b96935b
--- /dev/null
+++ b/checkpoint-2772/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: 0.9885216725241056
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7183246612548828
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9824706124974221
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7085607051849365
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9782229269572558
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9867553479166427
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9971022799526896
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9739458779668466
+      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           | 0.9885     |
+| cosine_accuracy_threshold | 0.7183     |
+| cosine_f1                 | 0.9825     |
+| cosine_f1_threshold       | 0.7086     |
+| cosine_precision          | 0.9782     |
+| cosine_recall             | 0.9868     |
+| **cosine_ap**             | **0.9971** |
+| cosine_mcc                | 0.9739     |
+
+<!--
+## 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`: epoch
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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                                                                |
+| 0.7207 | 500  | 0.038         | -               | -                                                                     |
+| 0.9989 | 693  | -             | 0.0028          | 0.9911                                                                |
+| 1.4425 | 1000 | 0.0128        | -               | -                                                                     |
+| 1.9989 | 1386 | -             | 0.0021          | 0.9956                                                                |
+| 2.1643 | 1500 | 0.0084        | -               | -                                                                     |
+| 2.8850 | 2000 | 0.0065        | -               | -                                                                     |
+| 2.9989 | 2079 | -             | 0.0015          | 0.9968                                                                |
+| 3.6068 | 2500 | 0.0056        | -               | -                                                                     |
+| 3.9989 | 2772 | -             | 0.0014          | 0.9971                                                                |
+
+
+### 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-2772/config.json b/checkpoint-2772/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-2772/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-2772/config_sentence_transformers.json b/checkpoint-2772/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-2772/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-2772/model.safetensors b/checkpoint-2772/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a8c6a1dee5b1f6a8892e79a11f68f590faf9973
--- /dev/null
+++ b/checkpoint-2772/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cbcc5809568045ff4d80ea5eff6ddee83cd424541447967273a7023c7e187e
+size 470637416
diff --git a/checkpoint-2772/modules.json b/checkpoint-2772/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-2772/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-2772/optimizer.pt b/checkpoint-2772/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9bd1fbad4bb9ae4a9a2f7efdb6032bce3861cdbd
--- /dev/null
+++ b/checkpoint-2772/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3e5f9bb09ee4343f28e1fd561f33a38c1f23ae8dae410e77420c9278ae6ac8
+size 1715019
diff --git a/checkpoint-2772/rng_state.pth b/checkpoint-2772/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..31e770ff31240d06bc2a3276c51abd81e5939015
--- /dev/null
+++ b/checkpoint-2772/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd92514717bc3cb44100d9bb038875d49cd30e2d1925b33a6ddd1f8bbba8e940
+size 14645
diff --git a/checkpoint-2772/scaler.pt b/checkpoint-2772/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a2233c7bd1582b63aac0399e4f2f7c1c477c9d78
--- /dev/null
+++ b/checkpoint-2772/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d00f48ebab6e58e9ae555bb7a1dc0eb436c3b5115601ee219420aae460b550
+size 1383
diff --git a/checkpoint-2772/scheduler.pt b/checkpoint-2772/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..006ea736b7fd9bd40174b2a1b3c05a2d65172f62
--- /dev/null
+++ b/checkpoint-2772/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c76e070cc219bc8a3b3a9bbab555445f78c28c96a21cc55f454628bf0d5ef07
+size 1465
diff --git a/checkpoint-2772/sentence_bert_config.json b/checkpoint-2772/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-2772/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-2772/special_tokens_map.json b/checkpoint-2772/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-2772/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-2772/tokenizer.json b/checkpoint-2772/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-2772/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-2772/tokenizer_config.json b/checkpoint-2772/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-2772/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-2772/trainer_state.json b/checkpoint-2772/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..52f0cacdeca59f0b1fc2fbc8f5ac86d5a7e3f39d
--- /dev/null
+++ b/checkpoint-2772/trainer_state.json
@@ -0,0 +1,142 @@
+{
+  "best_global_step": 2772,
+  "best_metric": 0.001379696768708527,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-2772",
+  "epoch": 3.998918918918919,
+  "eval_steps": 100,
+  "global_step": 2772,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.15965162217617035,
+      "learning_rate": 2.7341619887730554e-05,
+      "loss": 0.038,
+      "step": 500
+    },
+    {
+      "epoch": 0.9989189189189189,
+      "eval_loss": 0.002777691464871168,
+      "eval_runtime": 792.7494,
+      "eval_samples_per_second": 3359.543,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.975327415818089,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7701693773269653,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911172257655966,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9624723810391563,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7597355842590332,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9441287064717891,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9527175567355498,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9724290300680068,
+      "eval_steps_per_second": 4.375,
+      "step": 693
+    },
+    {
+      "epoch": 1.4425225225225224,
+      "grad_norm": 0.11966603249311447,
+      "learning_rate": 2.1327185244587008e-05,
+      "loss": 0.0128,
+      "step": 1000
+    },
+    {
+      "epoch": 1.998918918918919,
+      "eval_loss": 0.002118302509188652,
+      "eval_runtime": 789.0568,
+      "eval_samples_per_second": 3375.265,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9846242227629088,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.6801187992095947,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9955904030209028,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9765449140552956,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.6780189275741577,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9651303277408154,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9721848413657824,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9809442711989229,
+      "eval_steps_per_second": 4.395,
+      "step": 1386
+    },
+    {
+      "epoch": 2.1643243243243244,
+      "grad_norm": 0.04637068510055542,
+      "learning_rate": 1.5312750601443466e-05,
+      "loss": 0.0084,
+      "step": 1500
+    },
+    {
+      "epoch": 2.885045045045045,
+      "grad_norm": 0.07652924209833145,
+      "learning_rate": 9.29831595829992e-06,
+      "loss": 0.0065,
+      "step": 2000
+    },
+    {
+      "epoch": 2.998918918918919,
+      "eval_loss": 0.0014588695485144854,
+      "eval_runtime": 782.4422,
+      "eval_samples_per_second": 3403.799,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9879171547865789,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7181636691093445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.996840725826042,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9815604299892273,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7181636691093445,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9725931427811844,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9775832353646149,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.98557011840788,
+      "eval_steps_per_second": 4.432,
+      "step": 2079
+    },
+    {
+      "epoch": 3.606846846846847,
+      "grad_norm": 0.04797244444489479,
+      "learning_rate": 3.2838813151563755e-06,
+      "loss": 0.0056,
+      "step": 2500
+    },
+    {
+      "epoch": 3.998918918918919,
+      "eval_loss": 0.001379696768708527,
+      "eval_runtime": 780.7313,
+      "eval_samples_per_second": 3411.258,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.9885216725241056,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7183246612548828,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9971022799526896,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9824706124974221,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7085607051849365,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9739458779668466,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9782229269572558,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9867553479166427,
+      "eval_steps_per_second": 4.442,
+      "step": 2772
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2772,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 768,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2772/training_args.bin b/checkpoint-2772/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65b989c1e3d30efe64e2dc0572f41454e6d26706
--- /dev/null
+++ b/checkpoint-2772/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee490aac80277022fdde76dd6763dbabee88802149f3f246e7d0572b504fcdaf
+size 6097
diff --git a/checkpoint-2772/unigram.json b/checkpoint-2772/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-2772/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/checkpoint-693/1_Pooling/config.json b/checkpoint-693/1_Pooling/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a97f8d140b6aee43dfac9fc4521b2842657c5608
--- /dev/null
+++ b/checkpoint-693/1_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-693/README.md b/checkpoint-693/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..87afec63e9872aeb6d09fa8e4f09cf6444dd321d
--- /dev/null
+++ b/checkpoint-693/README.md
@@ -0,0 +1,458 @@
+---
+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: 0.975327415818089
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7701693773269653
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.9624723810391563
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7597355842590332
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.9527175567355498
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.9724290300680068
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.9911172257655966
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.9441287064717891
+      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           | 0.9753     |
+| cosine_accuracy_threshold | 0.7702     |
+| cosine_f1                 | 0.9625     |
+| cosine_f1_threshold       | 0.7597     |
+| cosine_precision          | 0.9527     |
+| cosine_recall             | 0.9724     |
+| **cosine_ap**             | **0.9911** |
+| cosine_mcc                | 0.9441     |
+
+<!--
+## 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`: epoch
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `gradient_accumulation_steps`: 4
+- `learning_rate`: 3e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `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`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 768
+- `per_device_eval_batch_size`: 768
+- `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`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: 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                                                                |
+| 0.7207 | 500  | 0.038         | -               | -                                                                     |
+| 0.9989 | 693  | -             | 0.0028          | 0.9911                                                                |
+
+
+### 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-693/config.json b/checkpoint-693/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/checkpoint-693/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-693/config_sentence_transformers.json b/checkpoint-693/config_sentence_transformers.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcf436801f55bd22a257de2aad7eef5cfd06efaa
--- /dev/null
+++ b/checkpoint-693/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-693/model.safetensors b/checkpoint-693/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..06cd55927f1f07b1cf79bfc5291950f0470bdac4
--- /dev/null
+++ b/checkpoint-693/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6a956772ef690a39d936766b88abb632b4097a69e44693ef370cdba1402b0a
+size 470637416
diff --git a/checkpoint-693/modules.json b/checkpoint-693/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/checkpoint-693/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-693/optimizer.pt b/checkpoint-693/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6b54af43a9998ae53624c0727821518a7be66354
--- /dev/null
+++ b/checkpoint-693/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2549b503dadc023f022f593ea09e716cc46bbd0f9b5487563b1874212dba9fcf
+size 1715019
diff --git a/checkpoint-693/rng_state.pth b/checkpoint-693/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cf1046ef69b1591483b5336d32c88d39fc7c6bd5
--- /dev/null
+++ b/checkpoint-693/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62cce1358dd6e58045d6ce9a84ccca9443e538e49305c0b5fd2413d42a5234f
+size 14645
diff --git a/checkpoint-693/scaler.pt b/checkpoint-693/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b543c03e8b1819d4b359b04188c400785292ee37
--- /dev/null
+++ b/checkpoint-693/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b08803626d75222e2baa22e4c13f53a5ace62bffa12fbbdf01b1d93bc64e8d5
+size 1383
diff --git a/checkpoint-693/scheduler.pt b/checkpoint-693/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6738a361b23dbcbeb623d201937eab8d2e4cc842
--- /dev/null
+++ b/checkpoint-693/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29430865f8e0f9b166864bbe8f7af84a753be1b09712d85e79bf5ff2a4cc577b
+size 1465
diff --git a/checkpoint-693/sentence_bert_config.json b/checkpoint-693/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/checkpoint-693/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-693/special_tokens_map.json b/checkpoint-693/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/checkpoint-693/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-693/tokenizer.json b/checkpoint-693/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..e3420945e193cc0791136cdc6e5cd69801c838af
--- /dev/null
+++ b/checkpoint-693/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987
diff --git a/checkpoint-693/tokenizer_config.json b/checkpoint-693/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/checkpoint-693/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-693/trainer_state.json b/checkpoint-693/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..ad25e6ff7bbb3b9c63f05f9ab563a2911ec79272
--- /dev/null
+++ b/checkpoint-693/trainer_state.json
@@ -0,0 +1,66 @@
+{
+  "best_global_step": 693,
+  "best_metric": 0.002777691464871168,
+  "best_model_checkpoint": "data/fine-tuned-sbert-sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2-original-adafactor/checkpoint-693",
+  "epoch": 0.9989189189189189,
+  "eval_steps": 100,
+  "global_step": 693,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.15965162217617035,
+      "learning_rate": 2.7341619887730554e-05,
+      "loss": 0.038,
+      "step": 500
+    },
+    {
+      "epoch": 0.9989189189189189,
+      "eval_loss": 0.002777691464871168,
+      "eval_runtime": 792.7494,
+      "eval_samples_per_second": 3359.543,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy": 0.975327415818089,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_accuracy_threshold": 0.7701693773269653,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_ap": 0.9911172257655966,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1": 0.9624723810391563,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_f1_threshold": 0.7597355842590332,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_mcc": 0.9441287064717891,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_precision": 0.9527175567355498,
+      "eval_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_cosine_recall": 0.9724290300680068,
+      "eval_steps_per_second": 4.375,
+      "step": 693
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2772,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 768,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-693/training_args.bin b/checkpoint-693/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65b989c1e3d30efe64e2dc0572f41454e6d26706
--- /dev/null
+++ b/checkpoint-693/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee490aac80277022fdde76dd6763dbabee88802149f3f246e7d0572b504fcdaf
+size 6097
diff --git a/checkpoint-693/unigram.json b/checkpoint-693/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/checkpoint-693/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..26e48501fdf44110239e00ad4d438aee8679504a
--- /dev/null
+++ b/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/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
new file mode 100644
index 0000000000000000000000000000000000000000..34c624633cd67ccbbd8a83004ef88100000c3c25
--- /dev/null
+++ b/eval/binary_classification_evaluation_sentence-transformers-paraphrase-multilingual-MiniLM-L12-v2_results.csv
@@ -0,0 +1,6 @@
+epoch,steps,cosine_accuracy,cosine_accuracy_threshold,cosine_f1,cosine_precision,cosine_recall,cosine_f1_threshold,cosine_ap,cosine_mcc
+0.9989189189189189,693,0.975327415818089,0.7701694,0.9624723810391563,0.9527175567355498,0.9724290300680068,0.7597356,0.9911172257655966,0.9441287064717891
+1.998918918918919,1386,0.9846242227629088,0.6801188,0.9765449140552956,0.9721848413657824,0.9809442711989229,0.6780189,0.9955904030209028,0.9651303277408154
+2.998918918918919,2079,0.9879171547865789,0.71816367,0.9815604299892273,0.9775832353646149,0.98557011840788,0.71816367,0.996840725826042,0.9725931427811844
+3.998918918918919,2772,0.9885216725241056,0.71832466,0.9824706124974221,0.9782229269572558,0.9867553479166427,0.7085607,0.9971022799526896,0.9739458779668466
+3.998918918918919,2772,0.9885216725241056,0.71832466,0.9824706124974221,0.9782229269572558,0.9867553479166427,0.7085607,0.9971022799526896,0.9739458779668466
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a8c6a1dee5b1f6a8892e79a11f68f590faf9973
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cbcc5809568045ff4d80ea5eff6ddee83cd424541447967273a7023c7e187e
+size 470637416
diff --git a/modules.json b/modules.json
new file mode 100644
index 0000000000000000000000000000000000000000..f7640f94e81bb7f4f04daf1668850b38763a13d9
--- /dev/null
+++ b/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/sentence_bert_config.json b/sentence_bert_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5fd10429389515d3e5cccdeda08cae5fea1ae82e
--- /dev/null
+++ b/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/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..b1879d702821e753ffe4245048eee415d54a9385
--- /dev/null
+++ b/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/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/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..facf4436a8f11c26085c16a14f4e576853927a9e
--- /dev/null
+++ b/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/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..65b989c1e3d30efe64e2dc0572f41454e6d26706
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee490aac80277022fdde76dd6763dbabee88802149f3f246e7d0572b504fcdaf
+size 6097
diff --git a/unigram.json b/unigram.json
new file mode 100644
index 0000000000000000000000000000000000000000..2faa9ec874108d53a017ff2c7ab98d155fb21a82
--- /dev/null
+++ b/unigram.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260