Add new SentenceTransformer model

1_Pooling/config.json

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

README.md

@@ -0,0 +1,851 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: Item 8 in IBM's 2023 Annual Report to Stockholders details the
+    Financial Statements and Supplementary Data, which are included on pages 44 through
+    121.
+  sentences:
+  - What is the purpose of the unused credit facility fee payments, and what is their
+    total as of June 30, 2023?
+  - What section of IBM's Annual Report for 2023 contains the Financial Statements
+    and Supplementary Data?
+  - What position did K. Michelle Borninkhof hold at McDonald’s before joining AutoZone?
+- source_sentence: When evaluating for impairment, we first compare the carrying value
+    of the asset to the asset’s estimated future undiscounted cash flows. If the estimated
+    undiscounted future cash flows are less than the carrying value of the asset,
+    we determine if we have an impairment loss by comparing the carrying value of
+    the asset to the asset's estimated fair value and recognize an impairment charge
+    when the asset’s carrying value exceeds its estimated fair price.
+  sentences:
+  - What was the percentage change in net revenues for the Consumer Products segment
+    from 2022 to 2023?
+  - How are impairment losses on long-lived assets determined?
+  - What was the amount of pretax net losses on derivative instruments expected to
+    be reclassified into earnings over the next 12 months as of December 31, 2023,
+    according to the data provided?
+- source_sentence: The company develops and produces renewable fuels, including but
+    not limited to renewable diesel, renewable gasoline, biodiesel, sustainable aviation
+    fuel and renewable natural gas (RNG).
+  sentences:
+  - What types of renewable fuels does the Chevron Renewable Energy Group produce?
+  - What are the main contributors to the revenue of Xbox?
+  - How have changes by Apple and Google affected the company's advertising capabilities?
+- source_sentence: Our ERGs provide many contributions, such as mentoring programs
+    that connect diverse employees with senior leaders who can support their career
+    goals, partnerships with recruiters and diverse early career and professional
+    organizations that can assist in strengthening the diverse talent pipeline and
+    programs that educate and inform on the richness of the global cultures that we
+    share.
+  sentences:
+  - What phase of renovation was announced for Marina Bay Sands in 2023?
+  - How did the unit sales of new homes change in the fourth quarter of 2022 compared
+    to 2021?
+  - What kinds of contributions do ERGs provide?
+- source_sentence: The initial terms of Hilton's management contracts are typically
+    20 to 30 years.
+  sentences:
+  - What are the typical initial terms of Hilton's management contracts?
+  - What was the total revenue in millions for 2023 according to the disaggregated
+    revenue information by segment?
+  - What principle governs Macao under the Basic Law after December 20, 1999?
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: BGE base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8257142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8585714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2752380952380952
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1717142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0907142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8257142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8585714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8042901803629035
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7714574829931975
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.774634210341598
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.85
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9057142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09057142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.85
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9057142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8020168113658792
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7691179138321999
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7725170259617702
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6828571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8528571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6828571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17057142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6828571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8528571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7934699471629124
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7592913832199544
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.762707392745061
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6742857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7971428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8285714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.87
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6742857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26571428571428574
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1657142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.087
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6742857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7971428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8285714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.87
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7733108370502226
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7422732426303855
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7472617177636981
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6242857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7514285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7914285714285715
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8371428571428572
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6242857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25047619047619046
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15828571428571425
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0837142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6242857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7514285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7914285714285715
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8371428571428572
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7307335092507811
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6966581632653059
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7018444934217598
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json 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:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 512, 'do_lower_case': True, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## 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("preetham315/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    "The initial terms of Hilton's management contracts are typically 20 to 30 years.",
+    "What are the typical initial terms of Hilton's management contracts?",
+    'What was the total revenue in millions for 2023 according to the disaggregated revenue information by segment?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.8917, 0.2945],
+#         [0.8917, 1.0000, 0.2615],
+#         [0.2945, 0.2615, 1.0000]])
+```
+
+<!--
+### 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
+
+#### Information Retrieval
+
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7        |
+| cosine_accuracy@3   | 0.8257     |
+| cosine_accuracy@5   | 0.8586     |
+| cosine_accuracy@10  | 0.9071     |
+| cosine_precision@1  | 0.7        |
+| cosine_precision@3  | 0.2752     |
+| cosine_precision@5  | 0.1717     |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.7        |
+| cosine_recall@3     | 0.8257     |
+| cosine_recall@5     | 0.8586     |
+| cosine_recall@10    | 0.9071     |
+| **cosine_ndcg@10**  | **0.8043** |
+| cosine_mrr@10       | 0.7715     |
+| cosine_map@100      | 0.7746     |
+
+#### Information Retrieval
+
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.7       |
+| cosine_accuracy@3   | 0.82      |
+| cosine_accuracy@5   | 0.85      |
+| cosine_accuracy@10  | 0.9057    |
+| cosine_precision@1  | 0.7       |
+| cosine_precision@3  | 0.2733    |
+| cosine_precision@5  | 0.17      |
+| cosine_precision@10 | 0.0906    |
+| cosine_recall@1     | 0.7       |
+| cosine_recall@3     | 0.82      |
+| cosine_recall@5     | 0.85      |
+| cosine_recall@10    | 0.9057    |
+| **cosine_ndcg@10**  | **0.802** |
+| cosine_mrr@10       | 0.7691    |
+| cosine_map@100      | 0.7725    |
+
+#### Information Retrieval
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6829     |
+| cosine_accuracy@3   | 0.82       |
+| cosine_accuracy@5   | 0.8529     |
+| cosine_accuracy@10  | 0.9        |
+| cosine_precision@1  | 0.6829     |
+| cosine_precision@3  | 0.2733     |
+| cosine_precision@5  | 0.1706     |
+| cosine_precision@10 | 0.09       |
+| cosine_recall@1     | 0.6829     |
+| cosine_recall@3     | 0.82       |
+| cosine_recall@5     | 0.8529     |
+| cosine_recall@10    | 0.9        |
+| **cosine_ndcg@10**  | **0.7935** |
+| cosine_mrr@10       | 0.7593     |
+| cosine_map@100      | 0.7627     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6743     |
+| cosine_accuracy@3   | 0.7971     |
+| cosine_accuracy@5   | 0.8286     |
+| cosine_accuracy@10  | 0.87       |
+| cosine_precision@1  | 0.6743     |
+| cosine_precision@3  | 0.2657     |
+| cosine_precision@5  | 0.1657     |
+| cosine_precision@10 | 0.087      |
+| cosine_recall@1     | 0.6743     |
+| cosine_recall@3     | 0.7971     |
+| cosine_recall@5     | 0.8286     |
+| cosine_recall@10    | 0.87       |
+| **cosine_ndcg@10**  | **0.7733** |
+| cosine_mrr@10       | 0.7423     |
+| cosine_map@100      | 0.7473     |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6243     |
+| cosine_accuracy@3   | 0.7514     |
+| cosine_accuracy@5   | 0.7914     |
+| cosine_accuracy@10  | 0.8371     |
+| cosine_precision@1  | 0.6243     |
+| cosine_precision@3  | 0.2505     |
+| cosine_precision@5  | 0.1583     |
+| cosine_precision@10 | 0.0837     |
+| cosine_recall@1     | 0.6243     |
+| cosine_recall@3     | 0.7514     |
+| cosine_recall@5     | 0.7914     |
+| cosine_recall@10    | 0.8371     |
+| **cosine_ndcg@10**  | **0.7307** |
+| cosine_mrr@10       | 0.6967     |
+| cosine_map@100      | 0.7018     |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 6,300 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                           | anchor                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                           |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 44.97 tokens</li><li>max: 371 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.7 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                              | anchor                                                                             |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | <code>As of December 31, 2023, cash and cash equivalents totaled $6.2 billion, showing an increase from $4.7 billion in 2022.</code>                                                  | <code>What amount did cash and cash equivalents reach at the end of 2023?</code>   |
+  | <code>The GDPR imposes a comprehensive data protection regime with the potential for regulatory fines as much as up to the greater of 4% of worldwide turnover or €20 million.</code> | <code>How does the GDPR penalize non-compliance in terms of fines?</code>          |
+  | <code>The 'Index to Financial Statement Schedules' serves as a guide to organize and present the content of the financial statement schedules.</code>                                 | <code>What purpose does the 'Index to Financial Statement Schedules' serve?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "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`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch
+- `batch_sampler`: no_duplicates
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `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
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `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}
+- `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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `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
+- `hub_revision`: None
+- `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`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step   | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| -1      | -1     | -             | 0.7623                 | 0.7640                 | 0.7500                 | 0.7045                 | 0.6426                |
+| 0.8122  | 10     | 1.4367        | -                      | -                      | -                      | -                      | -                     |
+| **1.0** | **13** | **-**         | **0.8043**             | **0.802**              | **0.7935**             | **0.7733**             | **0.7307**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.1
+- PyTorch: 2.9.0+cu126
+- Accelerate: 1.11.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## 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}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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 +1,31 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.1",
+    "pytorch": "2.9.0+cu126"
+  },
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cab9be04b83fd199090c8d0be20d2e4f4adba7bb27f7add7f014f5f81d8280
+size 437951328

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": true
+}

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}