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 +1,826 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Item 3—Legal Proceedings See discussion of Legal Proceedings in
+    Note 10 to the consolidated financial statements included in Item 8 of this Report.
+  sentences:
+  - What financial measures are presented on a non-GAAP basis in this Annual Report
+    on Form 10-K?
+  - Which section of the report discusses Legal Proceedings?
+  - What criteria was used to audit the internal control over financial reporting
+    of The Procter & Gamble Company as of June 30, 2023?
+- source_sentence: A portion of the defense and/or settlement costs associated with
+    such litigation is covered by indemnification from third parties in limited cases.
+  sentences:
+  - How did the writers' and actors' strikes affect the Company's entertainment segment
+    in 2023?
+  - Can indemnification from third parties also contribute to covering litigation
+    costs?
+  - What was the balance of net cash used in financing activities for Costco for the
+    52 weeks ended August 28, 2022?
+- source_sentence: In the company, to have a diverse and inclusive workforce, there
+    is an emphasis on attracting and hiring talented people who represent a mix of
+    backgrounds, identities, and experiences.
+  sentences:
+  - What does AT&T emphasize to ensure they have a diverse and inclusive workforce?
+  - What drove the growth in marketplace revenue for the year ended December 31, 2023?
+  - What was the effect of prior-period medical claims reserve development on the
+    Insurance segment's benefit ratio in 2023?
+- source_sentence: Internal control over financial reporting is a process designed
+    to provide reasonable assurance regarding the reliability of financial reporting
+    and the preparation of financial statements for external purposes in accordance
+    with generally accepted accounting principles. It includes various policies and
+    procedures that ensure accurate and fair record maintenance, proper transaction
+    recording, and prevention or detection of unauthorized use or acquisition of assets.
+  sentences:
+  - How much did net cash used in financing activities decrease in fiscal 2023 compared
+    to the previous fiscal year?
+  - How does Visa ensure the protection of its intellectual property?
+  - What is the purpose of internal control over financial reporting according to
+    the document?
+- source_sentence: Non-GAAP earnings from operations and non-GAAP operating profit
+    margin consist of earnings from operations or earnings from operations as a percentage
+    of net revenue excluding the items mentioned above and charges relating to the
+    amortization of intangible assets, goodwill impairment, transformation costs and
+    acquisition, disposition and other related charges. Hewlett Packard Enterprise
+    excludes these items because they are non-cash expenses, are significantly impacted
+    by the timing and magnitude of acquisitions, and are inconsistent in amount and
+    frequency.
+  sentences:
+  - What specific charges are excluded from Hewlett Packard Enterprise's non-GAAP
+    operating profit margin and why?
+  - How many shares were outstanding at the beginning of 2023 and what was their aggregate
+    intrinsic value?
+  - What was the annual amortization expense forecast for acquisition-related intangible
+    assets in 2025, according to a specified financial projection?
+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: 0.7157142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8571428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8871428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9314285714285714
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7157142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2857142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1774285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09314285714285712
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7157142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8571428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8871428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9314285714285714
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8274896625809096
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7939818594104311
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7969204030602811
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7142857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8571428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8871428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9314285714285714
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7142857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2857142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1774285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09314285714285712
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7142857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8571428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8871428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9314285714285714
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8267670378473014
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7930204081632654
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7958033409607879
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7157142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8514285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8828571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.93
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7157142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2838095238095238
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17657142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09299999999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7157142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8514285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8828571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.93
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.825504930245723
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7918724489795919
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7945830508495424
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7142857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8428571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8742857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9214285714285714
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7142857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28095238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17485714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09214285714285712
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7142857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8428571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8742857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9214285714285714
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8203162516614704
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7878543083900227
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7909435994513387
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6828571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.81
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.85
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6828571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09042857142857143
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6828571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.81
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.85
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7926026006937184
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7570844671201811
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7606949750229449
+      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). 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 tokens
+- **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': 512, 'do_lower_case': True}) with Transformer model: 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("NickyNicky/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Non-GAAP earnings from operations and non-GAAP operating profit margin consist of earnings from operations or earnings from operations as a percentage of net revenue excluding the items mentioned above and charges relating to the amortization of intangible assets, goodwill impairment, transformation costs and acquisition, disposition and other related charges. Hewlett Packard Enterprise excludes these items because they are non-cash expenses, are significantly impacted by the timing and magnitude of acquisitions, and are inconsistent in amount and frequency.',
+    "What specific charges are excluded from Hewlett Packard Enterprise's non-GAAP operating profit margin and why?",
+    'How many shares were outstanding at the beginning of 2023 and what was their aggregate intrinsic value?',
+]
+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
+
+#### Information Retrieval
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7157     |
+| cosine_accuracy@3   | 0.8571     |
+| cosine_accuracy@5   | 0.8871     |
+| cosine_accuracy@10  | 0.9314     |
+| cosine_precision@1  | 0.7157     |
+| cosine_precision@3  | 0.2857     |
+| cosine_precision@5  | 0.1774     |
+| cosine_precision@10 | 0.0931     |
+| cosine_recall@1     | 0.7157     |
+| cosine_recall@3     | 0.8571     |
+| cosine_recall@5     | 0.8871     |
+| cosine_recall@10    | 0.9314     |
+| cosine_ndcg@10      | 0.8275     |
+| cosine_mrr@10       | 0.794      |
+| **cosine_map@100**  | **0.7969** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7143     |
+| cosine_accuracy@3   | 0.8571     |
+| cosine_accuracy@5   | 0.8871     |
+| cosine_accuracy@10  | 0.9314     |
+| cosine_precision@1  | 0.7143     |
+| cosine_precision@3  | 0.2857     |
+| cosine_precision@5  | 0.1774     |
+| cosine_precision@10 | 0.0931     |
+| cosine_recall@1     | 0.7143     |
+| cosine_recall@3     | 0.8571     |
+| cosine_recall@5     | 0.8871     |
+| cosine_recall@10    | 0.9314     |
+| cosine_ndcg@10      | 0.8268     |
+| cosine_mrr@10       | 0.793      |
+| **cosine_map@100**  | **0.7958** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7157     |
+| cosine_accuracy@3   | 0.8514     |
+| cosine_accuracy@5   | 0.8829     |
+| cosine_accuracy@10  | 0.93       |
+| cosine_precision@1  | 0.7157     |
+| cosine_precision@3  | 0.2838     |
+| cosine_precision@5  | 0.1766     |
+| cosine_precision@10 | 0.093      |
+| cosine_recall@1     | 0.7157     |
+| cosine_recall@3     | 0.8514     |
+| cosine_recall@5     | 0.8829     |
+| cosine_recall@10    | 0.93       |
+| cosine_ndcg@10      | 0.8255     |
+| cosine_mrr@10       | 0.7919     |
+| **cosine_map@100**  | **0.7946** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7143     |
+| cosine_accuracy@3   | 0.8429     |
+| cosine_accuracy@5   | 0.8743     |
+| cosine_accuracy@10  | 0.9214     |
+| cosine_precision@1  | 0.7143     |
+| cosine_precision@3  | 0.281      |
+| cosine_precision@5  | 0.1749     |
+| cosine_precision@10 | 0.0921     |
+| cosine_recall@1     | 0.7143     |
+| cosine_recall@3     | 0.8429     |
+| cosine_recall@5     | 0.8743     |
+| cosine_recall@10    | 0.9214     |
+| cosine_ndcg@10      | 0.8203     |
+| cosine_mrr@10       | 0.7879     |
+| **cosine_map@100**  | **0.7909** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6829     |
+| cosine_accuracy@3   | 0.81       |
+| cosine_accuracy@5   | 0.85       |
+| cosine_accuracy@10  | 0.9043     |
+| cosine_precision@1  | 0.6829     |
+| cosine_precision@3  | 0.27       |
+| cosine_precision@5  | 0.17       |
+| cosine_precision@10 | 0.0904     |
+| cosine_recall@1     | 0.6829     |
+| cosine_recall@3     | 0.81       |
+| cosine_recall@5     | 0.85       |
+| cosine_recall@10    | 0.9043     |
+| cosine_ndcg@10      | 0.7926     |
+| cosine_mrr@10       | 0.7571     |
+| **cosine_map@100**  | **0.7607** |
+
+<!--
+## 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: 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: 46.8 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.89 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                   | anchor                                                                                               |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|
+  | <code>Retail sales mix by product type for company-operated stores shows beverages at 74%, food at 22%, and other items at 4%.</code>                                                                                                                                                                      | <code>What are the primary products sold in Starbucks company-operated stores?</code>                |
+  | <code>The pre-tax adjustment for transformation costs was $136 in 2021 and $111 in 2020. Transformation costs primarily include costs related to store and business closure costs and third party professional consulting fees associated with business transformation and cost saving initiatives.</code> | <code>What was the purpose of pre-tax adjustments for transformation costs by The Kroger Co.?</code> |
+  | <code>HP's Consolidated Financial Statements are prepared in accordance with United States generally accepted accounting principles (GAAP).</code>                                                                                                                                                         | <code>What principles do HP's Consolidated Financial Statements adhere to?</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`: 40
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 10
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `optim`: adamw_torch_fused
+- `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`: 40
+- `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
+- `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`: 10
+- `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
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `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_fused
+- `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`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:------:|:----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.9114 | 9    | -             | 0.7311                 | 0.7527                 | 0.7618                 | 0.6911                | 0.7612                 |
+| 1.0127 | 10   | 1.9734        | -                      | -                      | -                      | -                     | -                      |
+| 1.9241 | 19   | -             | 0.7638                 | 0.7748                 | 0.7800                 | 0.7412                | 0.7836                 |
+| 2.0253 | 20   | 0.8479        | -                      | -                      | -                      | -                     | -                      |
+| 2.9367 | 29   | -             | 0.7775                 | 0.7842                 | 0.7902                 | 0.7473                | 0.7912                 |
+| 3.0380 | 30   | 0.524         | -                      | -                      | -                      | -                     | -                      |
+| 3.9494 | 39   | -             | 0.7831                 | 0.7860                 | 0.7915                 | 0.7556                | 0.7939                 |
+| 4.0506 | 40   | 0.3826        | -                      | -                      | -                      | -                     | -                      |
+| 4.9620 | 49   | -             | 0.7896                 | 0.7915                 | 0.7927                 | 0.7616                | 0.7983                 |
+| 5.0633 | 50   | 0.3165        | -                      | -                      | -                      | -                     | -                      |
+| 5.9747 | 59   | -             | 0.7925                 | 0.7946                 | 0.7943                 | 0.7603                | 0.7978                 |
+| 6.0759 | 60   | 0.2599        | -                      | -                      | -                      | -                     | -                      |
+| 6.9873 | 69   | -             | 0.7918                 | 0.7949                 | 0.7951                 | 0.7608                | 0.7976                 |
+| 7.0886 | 70   | 0.2424        | -                      | -                      | -                      | -                     | -                      |
+| 8.0    | 79   | -             | 0.7925                 | 0.7956                 | 0.7959                 | 0.7612                | 0.7989                 |
+| 8.1013 | 80   | 0.2243        | -                      | -                      | -                      | -                     | -                      |
+| 8.9114 | 88   | -             | 0.7927                 | 0.7956                 | 0.7961                 | 0.7610                | 0.7983                 |
+| 9.1139 | 90   | 0.2222        | 0.7909                 | 0.7946                 | 0.7958                 | 0.7607                | 0.7969                 |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.2.0+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### 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 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.2.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3641bb32d2b41024a3dff23be2f0a524b09cdc40a9cef0a224d1beaacb5ce3
+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 +1,57 @@
+{
+  "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,
+  "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]"
+}