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 +1,815 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: The net cash provided by operating activities during fiscal 2023
+    was related to net income of $208 million, adjusted for non-cash items including
+    $3.8 billion of depreciation and amortization and $3.3 billion related to stock-based
+    compensation expense.
+  sentences:
+  - What are the three key aspects encompassed in a company's internal control over
+    financial reporting?
+  - What was the net cash provided by operating activities for fiscal 2023?
+  - What are the two operating segments of NVIDIA as mentioned in the text?
+- source_sentence: Intellectual Property  To establish and protect our proprietary
+    rights, we rely on a combination of patents, trademarks, copyrights, trade secrets,
+    including know-how, license agreements, confidentiality procedures, non-disclosure
+    agreements with third parties, employee disclosure and invention assignment agreements,
+    and other contractual rights.
+  sentences:
+  - What condition does Synthroid treat and what type of drug is it formulated as?
+  - What legal tools does the company use to protect its intellectual property?
+  - In which item and part of a financial document would you find information on legal
+    proceedings?
+- source_sentence: Cost of revenues is comprised of TAC and other costs of revenues.
+    TAC includes amounts paid to our distribution partners and Google Network partners
+    primarily for ads displayed on their properties. Other cost of revenues includes
+    compensation expense related to our data centers and operations, content acquisition
+    costs, depreciation expense related to technical infrastructure, and inventory
+    and other costs related to devices we sell.
+  sentences:
+  - What is included in the cost of revenues for Google?
+  - What was the total net uncertain tax positions as of December 31, 2023?
+  - What portion of the restructuring charges incurred in fiscal 2023 are expected
+    to be settled with cash?
+- source_sentence: Comprehensive income (loss) | $ | (362) | | $ | 1,868 | $ | 4,775
+  sentences:
+  - What measures does the company take to ensure product quality?
+  - How many pages does Item 8, which includes Financial Statements and Supplementary
+    Data, span?
+  - What was the total comprehensive income for Airbnb, Inc. in 2023?
+- source_sentence: We make our branded beverage products available to consumers throughout
+    the world through our network of independent bottling partners, distributors,
+    wholesalers and retailers as well as our consolidated bottling and distribution
+    operations.
+  sentences:
+  - How does The Coca-Cola Company distribute its beverage products globally?
+  - What accounting method is predominantly used to determine inventory costs in the
+    Company's supermarket divisions before LIFO adjustments?
+  - How are the company's inventories valued?
+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: 0.7142857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8485714285714285
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8814285714285715
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9171428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7142857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28285714285714286
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17628571428571424
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09171428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7142857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8485714285714285
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8814285714285715
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9171428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8195547708074192
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7879784580498865
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.791495828863575
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7157142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8457142857142858
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8814285714285715
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.92
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7157142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2819047619047619
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17628571428571424
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09199999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7157142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8457142857142858
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8814285714285715
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.92
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8200080507124731
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7878299319727888
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7911645774121049
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6914285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8471428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.88
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.91
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6914285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28238095238095234
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.176
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09099999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6914285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8471428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.91
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8087696033003087
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7755997732426303
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7799208675704249
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6914285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.83
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.87
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6914285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27666666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.174
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0907142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6914285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.83
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.87
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8024684596621504
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7686116780045347
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7729258054107728
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6585714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8028571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8357142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8828571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6585714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2676190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1671428571428571
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08828571428571429
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6585714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8028571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8357142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8828571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7735846622621076
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.738378684807256
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7433829659777168
+      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 tokens
+- **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/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("girijesh/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'We make our branded beverage products available to consumers throughout the world through our network of independent bottling partners, distributors, wholesalers and retailers as well as our consolidated bottling and distribution operations.',
+    'How does The Coca-Cola Company distribute its beverage products globally?',
+    "What accounting method is predominantly used to determine inventory costs in the Company's supermarket divisions before LIFO adjustments?",
+]
+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   | 0.7143     |
+| cosine_accuracy@3   | 0.8486     |
+| cosine_accuracy@5   | 0.8814     |
+| cosine_accuracy@10  | 0.9171     |
+| cosine_precision@1  | 0.7143     |
+| cosine_precision@3  | 0.2829     |
+| cosine_precision@5  | 0.1763     |
+| cosine_precision@10 | 0.0917     |
+| cosine_recall@1     | 0.7143     |
+| cosine_recall@3     | 0.8486     |
+| cosine_recall@5     | 0.8814     |
+| cosine_recall@10    | 0.9171     |
+| cosine_ndcg@10      | 0.8196     |
+| cosine_mrr@10       | 0.788      |
+| **cosine_map@100**  | **0.7915** |
+
+#### 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   | 0.7157     |
+| cosine_accuracy@3   | 0.8457     |
+| cosine_accuracy@5   | 0.8814     |
+| cosine_accuracy@10  | 0.92       |
+| cosine_precision@1  | 0.7157     |
+| cosine_precision@3  | 0.2819     |
+| cosine_precision@5  | 0.1763     |
+| cosine_precision@10 | 0.092      |
+| cosine_recall@1     | 0.7157     |
+| cosine_recall@3     | 0.8457     |
+| cosine_recall@5     | 0.8814     |
+| cosine_recall@10    | 0.92       |
+| cosine_ndcg@10      | 0.82       |
+| cosine_mrr@10       | 0.7878     |
+| **cosine_map@100**  | **0.7912** |
+
+#### 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   | 0.6914     |
+| cosine_accuracy@3   | 0.8471     |
+| cosine_accuracy@5   | 0.88       |
+| cosine_accuracy@10  | 0.91       |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.2824     |
+| cosine_precision@5  | 0.176      |
+| cosine_precision@10 | 0.091      |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.8471     |
+| cosine_recall@5     | 0.88       |
+| cosine_recall@10    | 0.91       |
+| cosine_ndcg@10      | 0.8088     |
+| cosine_mrr@10       | 0.7756     |
+| **cosine_map@100**  | **0.7799** |
+
+#### 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   | 0.6914     |
+| cosine_accuracy@3   | 0.83       |
+| cosine_accuracy@5   | 0.87       |
+| cosine_accuracy@10  | 0.9071     |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.2767     |
+| cosine_precision@5  | 0.174      |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.83       |
+| cosine_recall@5     | 0.87       |
+| cosine_recall@10    | 0.9071     |
+| cosine_ndcg@10      | 0.8025     |
+| cosine_mrr@10       | 0.7686     |
+| **cosine_map@100**  | **0.7729** |
+
+#### 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   | 0.6586     |
+| cosine_accuracy@3   | 0.8029     |
+| cosine_accuracy@5   | 0.8357     |
+| cosine_accuracy@10  | 0.8829     |
+| cosine_precision@1  | 0.6586     |
+| cosine_precision@3  | 0.2676     |
+| cosine_precision@5  | 0.1671     |
+| cosine_precision@10 | 0.0883     |
+| cosine_recall@1     | 0.6586     |
+| cosine_recall@3     | 0.8029     |
+| cosine_recall@5     | 0.8357     |
+| cosine_recall@10    | 0.8829     |
+| cosine_ndcg@10      | 0.7736     |
+| cosine_mrr@10       | 0.7384     |
+| **cosine_map@100**  | **0.7434** |
+
+<!--
+## 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: 8 tokens</li><li>mean: 44.98 tokens</li><li>max: 439 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.31 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | anchor                                                                                                                    |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------|
+  | <code>Change in control events potentially triggering benefits under the CIC Plan and Mr. Begor’s agreement would occur, subject to certain exceptions, if (1) any person acquires 20% or more of our voting stock; (2) upon a merger or other business combination, our shareholders receive less than two-thirds of the common stock and combined voting power of the new company; (3) members of the current Board of Directors ceasing to constitute a majority of the Board of Directors, except for new directors that are regularly elected; (4) we sell or otherwise dispose of all or substantially all of our assets; or (5) we liquidate or dissolve.</code> | <code>What events potentially trigger benefits under Mark W. Begor's change in control agreement and the CIC Plan?</code> |
+  | <code>The growth in marketplace revenue was primarily due to the impact of the pricing update to increase our seller transaction fee for the Etsy marketplace from 5% to 6.5% beginning on April 11, 2022, and an increase in foreign currency payments, which we earn an additional transaction fee on, in the year ended December 31, 2023.</code>                                                                                                                                                                                                                                                                                                                    | <code>What drove the growth in marketplace revenue for the year ended December 31, 2023?</code>                           |
+  | <code>We are focused on ensuring that we efficiently allocate our resources to the areas with the highest potential for profitable growth. ... The uncertain macroeconomic environment in many of these markets is expected to continue and we aim to ensure our investments in these international markets are appropriate relative to the size of the opportunity.</code>                                                                                                                                                                                                                                                                                             | <code>What are Hershey's goals for international expansion and how are they being approached?</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`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: 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`: 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
+- `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`: 4
+- `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`: 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}
+- `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_768_cosine_map@100 | dim_512_cosine_map@100 | dim_256_cosine_map@100 | dim_128_cosine_map@100 | dim_64_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.9697     | 6      | -             | 0.7527                 | 0.7516                 | 0.7454                 | 0.7253                 | 0.6808                |
+| 1.6162     | 10     | 2.3351        | -                      | -                      | -                      | -                      | -                     |
+| 1.9394     | 12     | -             | 0.7740                 | 0.7699                 | 0.7707                 | 0.7474                 | 0.7188                |
+| 2.9091     | 18     | -             | 0.7784                 | 0.7790                 | 0.7735                 | 0.7575                 | 0.7275                |
+| 3.2323     | 20     | 1.0519        | -                      | -                      | -                      | -                      | -                     |
+| **3.8788** | **24** | **-**         | **0.7818**             | **0.7784**             | **0.7763**             | **0.7581**             | **0.7293**            |
+| 0.9697     | 6      | -             | 0.7836                 | 0.7826                 | 0.7817                 | 0.7664                 | 0.7353                |
+| 1.6162     | 10     | 0.8132        | -                      | -                      | -                      | -                      | -                     |
+| 1.9394     | 12     | -             | 0.7887                 | 0.7887                 | 0.7837                 | 0.7714                 | 0.7409                |
+| 2.9091     | 18     | -             | 0.7897                 | 0.7902                 | 0.7798                 | 0.7721                 | 0.7410                |
+| 3.2323     | 20     | 0.6098        | -                      | -                      | -                      | -                      | -                     |
+| **3.8788** | **24** | **-**         | **0.7915**             | **0.7912**             | **0.7799**             | **0.7729**             | **0.7434**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.2.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 1.0.1
+- 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": "3.2.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+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 sha256:01bf7e520ef93bfb6c39b341b76c78c8b410fef4265b3f8c3dfa2ba507ed8f0d
+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]"
+}