Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,744 @@
----
-license: mit
----
+---
+language:
+- tr
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:482091
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+- dataset_size:5749
+- loss:CoSENTLoss
+base_model: artiwise-ai/modernbert-base-tr-uncased
+widget:
+- source_sentence: Ya da dışarı çıkıp yürü ya da biraz koşun. Bunu düzenli olarak
+    yapmıyorum ama Washington bunu yapmak için harika bir yer.
+  sentences:
+  - “Washington's yürüyüş ya da koşu için harika bir yer.”
+  - H-2A uzaylılar Amerika Birleşik Devletleri'nde zaman kısa süreleri var.
+  - “Washington'da düzenli olarak yürüyüşe ya da koşuya çıkıyorum.”
+- source_sentence: Orta yaylalar ve güney kıyıları arasındaki kontrast daha belirgin
+    olamazdı.
+  sentences:
+  - İşitme Yardımı Uyumluluğu Müzakere Kuralları Komitesi, Federal İletişim Komisyonu'nun
+    bir ürünüdür.
+  - Dağlık ve sahil arasındaki kontrast kolayca işaretlendi.
+  - Kontrast işaretlenemedi.
+- source_sentence: Bir 1997 Henry J. Kaiser Aile Vakfı anket yönetilen bakım planlarında
+    Amerikalılar temelde kendi bakımı ile memnun olduğunu bulundu.
+  sentences:
+  - Kaplanları takip ederken çok sessiz olmalısın.
+  - Henry Kaiser vakfı insanların sağlık hizmetlerinden hoşlandığını gösteriyor.
+  - Henry Kaiser Vakfı insanların sağlık hizmetlerinden nefret ettiğini gösteriyor.
+- source_sentence: Eminim yapmışlardır.
+  sentences:
+  - Eminim öyle yapmışlardır.
+  - Batı Teksas'ta 100 10 dereceydi.
+  - Eminim yapmamışlardır.
+- source_sentence: Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti,
+    her şeyi denedi ve daha az ilgileniyordu.
+  sentences:
+  - Oğlu her şeye olan ilgisini kaybediyordu.
+  - Pek bir şey yapmadım.
+  - Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu.
+datasets:
+- emrecan/all-nli-tr
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+- cosine_accuracy
+model-index:
+- name: SentenceTransformer based on artiwise-ai/modernbert-base-tr-uncased
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts dev
+      type: sts-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.8317261658296335
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8334779716915757
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts test
+      type: sts-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.8033832035561776
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8081240893794807
+      name: Spearman Cosine
+    - type: pearson_cosine
+      value: 0.8033832035561776
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8081240893794807
+      name: Spearman Cosine
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli tr test
+      type: all-nli-tr-test
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9403370022773743
+      name: Cosine Accuracy
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: sts22 test
+      type: sts22-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.48198502241312763
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5339803342070422
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb dev 768
+      type: stsb-dev-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8504708785024945
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8545740930493043
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb dev 512
+      type: stsb-dev-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8517136938786618
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8557175083021253
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb dev 256
+      type: stsb-dev-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.8469723060661682
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8520958012990156
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb dev 128
+      type: stsb-dev-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8380362588675845
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8463279752442665
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb dev 64
+      type: stsb-dev-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.8274239260291338
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8398529067073018
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb test 768
+      type: stsb-test-768
+    metrics:
+    - type: pearson_cosine
+      value: 0.8252032099479898
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8326772469479152
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb test 512
+      type: stsb-test-512
+    metrics:
+    - type: pearson_cosine
+      value: 0.8257575707499885
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.833435201318002
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb test 256
+      type: stsb-test-256
+    metrics:
+    - type: pearson_cosine
+      value: 0.821132738273645
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8314809982555892
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb test 128
+      type: stsb-test-128
+    metrics:
+    - type: pearson_cosine
+      value: 0.8131512623185564
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8266667840848597
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: stsb test 64
+      type: stsb-test-64
+    metrics:
+    - type: pearson_cosine
+      value: 0.7980595038048237
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8154520345893972
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on artiwise-ai/modernbert-base-tr-uncased
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [artiwise-ai/modernbert-base-tr-uncased](https://huggingface.co/artiwise-ai/modernbert-base-tr-uncased) on the [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [artiwise-ai/modernbert-base-tr-uncased](https://huggingface.co/artiwise-ai/modernbert-base-tr-uncased) <!-- at revision fe2ec5fcfd7afd1e0378d295dfd7fadfb55ea965 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr)
+- **Language:** tr
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: ModernBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti, her şeyi denedi ve daha az ilgileniyordu.',
+    'Oğlu her şeye olan ilgisini kaybediyordu.',
+    'Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Datasets: `sts-dev`, `sts-test`, `sts-test` and `sts22-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | sts-dev    | sts-test   | sts22-test |
+|:--------------------|:-----------|:-----------|:-----------|
+| pearson_cosine      | 0.8317     | 0.8034     | 0.482      |
+| **spearman_cosine** | **0.8335** | **0.8081** | **0.534**  |
+
+#### Triplet
+
+* Dataset: `all-nli-tr-test`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| **cosine_accuracy** | **0.9403** |
+
+#### Semantic Similarity
+
+* Datasets: `stsb-dev-768` and `stsb-test-768`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | stsb-dev-768 | stsb-test-768 |
+|:--------------------|:-------------|:--------------|
+| pearson_cosine      | 0.8505       | 0.8252        |
+| **spearman_cosine** | **0.8546**   | **0.8327**    |
+
+#### Semantic Similarity
+
+* Datasets: `stsb-dev-512` and `stsb-test-512`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | stsb-dev-512 | stsb-test-512 |
+|:--------------------|:-------------|:--------------|
+| pearson_cosine      | 0.8517       | 0.8258        |
+| **spearman_cosine** | **0.8557**   | **0.8334**    |
+
+#### Semantic Similarity
+
+* Datasets: `stsb-dev-256` and `stsb-test-256`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | stsb-dev-256 | stsb-test-256 |
+|:--------------------|:-------------|:--------------|
+| pearson_cosine      | 0.847        | 0.8211        |
+| **spearman_cosine** | **0.8521**   | **0.8315**    |
+
+#### Semantic Similarity
+
+* Datasets: `stsb-dev-128` and `stsb-test-128`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | stsb-dev-128 | stsb-test-128 |
+|:--------------------|:-------------|:--------------|
+| pearson_cosine      | 0.838        | 0.8132        |
+| **spearman_cosine** | **0.8463**   | **0.8267**    |
+
+#### Semantic Similarity
+
+* Datasets: `stsb-dev-64` and `stsb-test-64`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | stsb-dev-64 | stsb-test-64 |
+|:--------------------|:------------|:-------------|
+| pearson_cosine      | 0.8274      | 0.7981       |
+| **spearman_cosine** | **0.8399**  | **0.8155**   |
+
+<!--
+## 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
+
+#### all-nli-tr
+
+* Dataset: [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) at [daeabfb](https://huggingface.co/datasets/emrecan/all-nli-tr/tree/daeabfbc01f82757ab998bd23ce0ddfceaa5e24d)
+* Size: 5,749 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                       | score                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                          | float                                                          |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 8.87 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 8.9 tokens</li><li>max: 24 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.23</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                                 | sentence2                                                          | score            |
+  |:----------------------------------------------------------|:-------------------------------------------------------------------|:-----------------|
+  | <code>Bir uçak kalkıyor.</code>                           | <code>Bir hava uçağı kalkıyor.</code>                              | <code>5.0</code> |
+  | <code>Bir adam büyük bir flüt çalıyor.</code>             | <code>Bir adam flüt çalıyor.</code>                                | <code>3.8</code> |
+  | <code>Bir adam pizzaya rendelenmiş peynir yayıyor.</code> | <code>Bir adam pişmemiş pizzaya rendelenmiş peynir yayıyor.</code> | <code>3.8</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### all-nli-tr
+
+* Dataset: [all-nli-tr](https://huggingface.co/datasets/emrecan/all-nli-tr) at [daeabfb](https://huggingface.co/datasets/emrecan/all-nli-tr/tree/daeabfbc01f82757ab998bd23ce0ddfceaa5e24d)
+* Size: 1,500 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                        | score                                                         |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | float                                                         |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 13.39 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.5 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.1</li><li>max: 5.0</li></ul> |
+* Samples:
+  | sentence1                                    | sentence2                                           | score             |
+  |:---------------------------------------------|:----------------------------------------------------|:------------------|
+  | <code>Şapkalı bir adam dans ediyor.</code>   | <code>Sert şapka takan bir adam dans ediyor.</code> | <code>5.0</code>  |
+  | <code>Küçük bir çocuk ata biniyor.</code>    | <code>Bir çocuk ata biniyor.</code>                 | <code>4.75</code> |
+  | <code>Bir adam yılana fare yediriyor.</code> | <code>Adam yılana fare yediriyor.</code>            | <code>5.0</code>  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CoSENTLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `num_train_epochs`: 10
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 144
+- `bf16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 1e-05
+- `weight_decay`: 0.01
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 144
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `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 | sts-dev_spearman_cosine | sts-test_spearman_cosine | all-nli-tr-test_cosine_accuracy | sts22-test_spearman_cosine | stsb-dev-768_spearman_cosine | stsb-dev-512_spearman_cosine | stsb-dev-256_spearman_cosine | stsb-dev-128_spearman_cosine | stsb-dev-64_spearman_cosine | stsb-test-768_spearman_cosine | stsb-test-512_spearman_cosine | stsb-test-256_spearman_cosine | stsb-test-128_spearman_cosine | stsb-test-64_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:-----------------------:|:------------------------:|:-------------------------------:|:--------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:----------------------------:|:---------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------:|:----------------------------:|
+| 0.1327 | 1000 | 6.5142        | 3.0122          | 0.8163                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.2655 | 2000 | 3.063         | 2.5473          | 0.8284                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.3982 | 3000 | 2.5516        | 2.3314          | 0.8274                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.5310 | 4000 | 2.2681        | 2.2253          | 0.8330                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.6637 | 5000 | 2.1122        | 2.1568          | 0.8329                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.7965 | 6000 | 1.9427        | 2.0958          | 0.8359                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 0.9292 | 7000 | 1.856         | 2.0770          | 0.8335                  | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| -1     | -1   | -             | -               | -                       | 0.8081                   | 0.9403                          | 0.5340                     | -                            | -                            | -                            | -                            | -                           | -                             | -                             | -                             | -                             | -                            |
+| 1.1111 | 200  | 39.4792       | 29.2091         | -                       | -                        | -                               | -                          | 0.8327                       | 0.8323                       | 0.8284                       | 0.8243                       | 0.8135                      | -                             | -                             | -                             | -                             | -                            |
+| 2.2222 | 400  | 28.0902       | 29.4698         | -                       | -                        | -                               | -                          | 0.8539                       | 0.8542                       | 0.8509                       | 0.8473                       | 0.8387                      | -                             | -                             | -                             | -                             | -                            |
+| 3.3333 | 600  | 26.8504       | 31.4975         | -                       | -                        | -                               | -                          | 0.8532                       | 0.8535                       | 0.8495                       | 0.8443                       | 0.8376                      | -                             | -                             | -                             | -                             | -                            |
+| 4.4444 | 800  | 25.7399       | 33.3569         | -                       | -                        | -                               | -                          | 0.8538                       | 0.8542                       | 0.8505                       | 0.8455                       | 0.8378                      | -                             | -                             | -                             | -                             | -                            |
+| 5.5556 | 1000 | 24.6547       | 35.7253         | -                       | -                        | -                               | -                          | 0.8537                       | 0.8545                       | 0.8510                       | 0.8459                       | 0.8393                      | -                             | -                             | -                             | -                             | -                            |
+| 6.6667 | 1200 | 23.589        | 37.8066         | -                       | -                        | -                               | -                          | 0.8548                       | 0.8557                       | 0.8522                       | 0.8466                       | 0.8398                      | -                             | -                             | -                             | -                             | -                            |
+| 7.7778 | 1400 | 22.7868       | 39.3319         | -                       | -                        | -                               | -                          | 0.8546                       | 0.8557                       | 0.8521                       | 0.8464                       | 0.8396                      | -                             | -                             | -                             | -                             | -                            |
+| 8.8889 | 1600 | 22.2741       | 40.3429         | -                       | -                        | -                               | -                          | 0.8548                       | 0.8560                       | 0.8524                       | 0.8466                       | 0.8400                      | -                             | -                             | -                             | -                             | -                            |
+| 10.0   | 1800 | 21.9617       | 40.6515         | -                       | -                        | -                               | -                          | 0.8546                       | 0.8557                       | 0.8521                       | 0.8463                       | 0.8399                      | -                             | -                             | -                             | -                             | -                            |
+| -1     | -1   | -             | -               | -                       | -                        | -                               | -                          | -                            | -                            | -                            | -                            | -                           | 0.8327                        | 0.8334                        | 0.8315                        | 0.8267                        | 0.8155                       |
+
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.7.0
+- 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 2,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 3,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "unk_token_id": 1,
+  "vocab_size": 32000
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a919df608e22a098ffb2545481d6d91bea0d037ad4e5191aa13017ffe428d703
+size 539643640

modules.json

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

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 8192,
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}