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 +1,844 @@
+---
+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: The total lease payments for 2023 were initially valued at $1,008
+    million, but after incorporating $43 million for interest, the final amount totaled
+    $1,051 million.
+  sentences:
+  - What percentage of Kenvue's shares did Johnson & Johnson own after the exchange
+    offer on August 23, 2023?
+  - What was the increase in total lease payments from the base amount to the final
+    amount including interest in 2023?
+  - What is the primary use of Global Business Services within Procter & Gamble?
+- source_sentence: We amortize software costs using the straight-line method over
+    the expected life of the software, generally 3 to 7 years.
+  sentences:
+  - How often does the company issue standby letters of credit, performance or surety
+    bonds, or other guarantees?
+  - What is the amortization method used for software costs and what is their expected
+    useful life range?
+  - How are the translation adjustments of foreign entity operations recorded in financial
+    statements?
+- source_sentence: In 2023, we continued to invest in our colleagues, building on
+    a wide range of learning and development opportunities and enhancing our competitive
+    benefits in key areas including holistic health and wellness, total compensation
+    and flexibility. We conduct an annual Colleague Experience Survey to better understand
+    our colleagues’ needs and overall experience at American Express.
+  sentences:
+  - How does American Express support employee development and well-being?
+  - By what percentage did admissions revenues increase during the year ended December
+    31, 2023 compared to the prior year?
+  - What is the maximum amount payable by the Corporation for most credit derivatives,
+    and how is this measured in terms of credit risk management?
+- source_sentence: Prepaid expenses were $69,167 in 2022 and increased to $97,670
+    in 2023.
+  sentences:
+  - What functional responsibility does Mary E. Adcock have at Kroger?
+  - What is Apple's approach to licenses for intellectual property owned by third
+    parties used in its products and services?
+  - How much did the prepaid expenses increase from 2022 to 2023?
+- source_sentence: Generated cash flows from operations of $4.5 billion.
+  sentences:
+  - How much did cash flows from operations amount to in 2022?
+  - What was the overall turnover rate at the company in fiscal year 2023?
+  - What are the expectations the company has for its employees in aligning with the
+    Code of Conduct?
+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: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8242857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8671428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2747619047619047
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1734285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09071428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8242857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8671428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8052852140611453
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7727052154195015
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7763711302515639
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7114285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8242857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9085714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7114285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2747619047619047
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09085714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7114285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8242857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9085714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8098666238099614
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7784104308390026
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7819743643907353
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8242857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8557142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8914285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2747619047619047
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17114285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08914285714285713
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8242857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8557142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8914285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8008524512077413
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7714569160997735
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7758614780389599
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6828571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8128571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8485714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8914285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6828571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.270952380952381
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16971428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08914285714285713
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6828571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8128571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8485714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8914285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7893688537538128
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.756581632653061
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7607042782514057
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6614285714285715
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7957142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8285714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8771428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6614285714285715
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2652380952380953
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1657142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0877142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6614285714285715
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7957142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8285714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8771428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7706919427250147
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.736583900226757
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7408800803327711
+      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/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, '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("deter3/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Generated cash flows from operations of $4.5 billion.',
+    'How much did cash flows from operations amount to in 2022?',
+    'What was the overall turnover rate at the company in fiscal year 2023?',
+]
+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, 0.7518, 0.2425],
+#         [0.7518, 1.0000, 0.2768],
+#         [0.2425, 0.2768, 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   | 0.7014     |
+| cosine_accuracy@3   | 0.8243     |
+| cosine_accuracy@5   | 0.8671     |
+| cosine_accuracy@10  | 0.9071     |
+| cosine_precision@1  | 0.7014     |
+| cosine_precision@3  | 0.2748     |
+| cosine_precision@5  | 0.1734     |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.7014     |
+| cosine_recall@3     | 0.8243     |
+| cosine_recall@5     | 0.8671     |
+| cosine_recall@10    | 0.9071     |
+| **cosine_ndcg@10**  | **0.8053** |
+| cosine_mrr@10       | 0.7727     |
+| cosine_map@100      | 0.7764     |
+
+#### 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   | 0.7114     |
+| cosine_accuracy@3   | 0.8243     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9086     |
+| cosine_precision@1  | 0.7114     |
+| cosine_precision@3  | 0.2748     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0909     |
+| cosine_recall@1     | 0.7114     |
+| cosine_recall@3     | 0.8243     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9086     |
+| **cosine_ndcg@10**  | **0.8099** |
+| cosine_mrr@10       | 0.7784     |
+| cosine_map@100      | 0.782      |
+
+#### 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   | 0.7014     |
+| cosine_accuracy@3   | 0.8243     |
+| cosine_accuracy@5   | 0.8557     |
+| cosine_accuracy@10  | 0.8914     |
+| cosine_precision@1  | 0.7014     |
+| cosine_precision@3  | 0.2748     |
+| cosine_precision@5  | 0.1711     |
+| cosine_precision@10 | 0.0891     |
+| cosine_recall@1     | 0.7014     |
+| cosine_recall@3     | 0.8243     |
+| cosine_recall@5     | 0.8557     |
+| cosine_recall@10    | 0.8914     |
+| **cosine_ndcg@10**  | **0.8009** |
+| cosine_mrr@10       | 0.7715     |
+| cosine_map@100      | 0.7759     |
+
+#### 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   | 0.6829     |
+| cosine_accuracy@3   | 0.8129     |
+| cosine_accuracy@5   | 0.8486     |
+| cosine_accuracy@10  | 0.8914     |
+| cosine_precision@1  | 0.6829     |
+| cosine_precision@3  | 0.271      |
+| cosine_precision@5  | 0.1697     |
+| cosine_precision@10 | 0.0891     |
+| cosine_recall@1     | 0.6829     |
+| cosine_recall@3     | 0.8129     |
+| cosine_recall@5     | 0.8486     |
+| cosine_recall@10    | 0.8914     |
+| **cosine_ndcg@10**  | **0.7894** |
+| cosine_mrr@10       | 0.7566     |
+| cosine_map@100      | 0.7607     |
+
+#### 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   | 0.6614     |
+| cosine_accuracy@3   | 0.7957     |
+| cosine_accuracy@5   | 0.8286     |
+| cosine_accuracy@10  | 0.8771     |
+| cosine_precision@1  | 0.6614     |
+| cosine_precision@3  | 0.2652     |
+| cosine_precision@5  | 0.1657     |
+| cosine_precision@10 | 0.0877     |
+| cosine_recall@1     | 0.6614     |
+| cosine_recall@3     | 0.7957     |
+| cosine_recall@5     | 0.8286     |
+| cosine_recall@10    | 0.8771     |
+| **cosine_ndcg@10**  | **0.7707** |
+| cosine_mrr@10       | 0.7366     |
+| cosine_map@100      | 0.7409     |
+
+<!--
+## 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: 13 tokens</li><li>mean: 45.95 tokens</li><li>max: 248 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.43 tokens</li><li>max: 41 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                    | anchor                                                                                                              |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------|
+  | <code>The Company's nominal par value per share was slightly reduced to USD $0.10, reflecting in the share capital, as of December 30, 2023.</code>                                                                         | <code>What was the nominal par value per share of Garmin Ltd. in U.S. dollars as of December 30, 2023?</code>       |
+  | <code>Over the last several years, the number and potential significance of the litigation and investigations involving the company have increased, and there can be no assurance that this trend will not continue.</code> | <code>How has the litigation and investigation landscape changed for the company over recent years?</code>          |
+  | <code>As of January 31, 2023, assets located outside the Americas were 15 percent of total assets.</code>                                                                                                                   | <code>What percentage of Salesforce's total assets were located outside the Americas as of January 31, 2023?</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
+- `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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.8122     | 10     | 1.5429        | -                      | -                      | -                      | -                      | -                     |
+| 0.9746     | 12     | -             | 0.7915                 | 0.7927                 | 0.7820                 | 0.7722                 | 0.7396                |
+| 1.6244     | 20     | 0.6772        | -                      | -                      | -                      | -                      | -                     |
+| 1.9492     | 24     | -             | 0.8019                 | 0.8041                 | 0.7971                 | 0.7835                 | 0.7625                |
+| 2.4365     | 30     | 0.5496        | -                      | -                      | -                      | -                      | -                     |
+| 2.9239     | 36     | -             | 0.8048                 | 0.8070                 | 0.8007                 | 0.7879                 | 0.7690                |
+| 3.2487     | 40     | 0.4528        | -                      | -                      | -                      | -                      | -                     |
+| **3.8985** | **48** | **-**         | **0.8053**             | **0.8099**             | **0.8009**             | **0.7894**             | **0.7707**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 5.0.0
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 1.8.1
+- 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 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.0.0",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "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 sha256:602fa462b6cf004974e1d1d519b38e0c1d6926a95cef0764d5a478dedc312e69
+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]"
+}