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 @@
+---
+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: We expect ME&T’s capital expenditures in 2024 to be around $2.0
+    billion to $2.5 billion.
+  sentences:
+  - What was the amount gained from the disposal of assets in 2022?
+  - What is the expected capital expenditure for ME&T in 2024?
+  - What is the expected total cost HP will incur from its Fiscal 2023 Plan, and how
+    is it primarily divided?
+- source_sentence: Average invested capital is calculated as the sum of (i) the average
+    of our total assets, (ii) the average LIFO reserve and (iii) the average accumulated
+    depreciation and amortization; minus (i) the average taxes receivable, (ii) the
+    average trade accounts payable, (iii) the average accrued salaries and wages and
+    (iv) the average other current liabilities, excluding accrued income taxes.
+  sentences:
+  - What are the components and the effective tax rates for the year 2023 as reported
+    in the financial statements?
+  - How is average invested capital calculated for ROIC?
+  - How did the interest income change in fiscal year 2023 compared to the previous
+    year?
+- source_sentence: Return on Invested Capital ('ROIC') as of May 31, 2023 was 31.5%
+    compared to 46.5% as of May 31, 2022.
+  sentences:
+  - How is NIKE's return on invested capital (ROIC) calculated, and what was its value
+    as of May 31, 2023?
+  - What role do medical directors play at outpatient dialysis centers, and what are
+    their general qualifications?
+  - What item number discusses legal proceedings in the report?
+- source_sentence: Net cash used in financing activities was $506.5 million in the
+    year ended December 31, 2022, and increased to $656.5 million in the year ended
+    December 31, 2023.
+  sentences:
+  - How has the change in foreign exchange rates affected cash and cash equivalents
+    in 2023 and 2021?
+  - What kind of financial documents are included in Part IV, Item 15(a)(1) of the
+    Annual Report on Form 10-K?
+  - How did the net cash used in financing activities in 2023 compare to 2022?
+- source_sentence: 'Alternative Payments Providers: These providers, such as closed
+    commerce ecosystems, BNPL solutions and cryptocurrency platforms, often have a
+    primary focus of enabling payments through ecommerce and mobile channels; however,
+    they are expanding or may expand their offerings to the physical point of sale.
+    These companies may process payments using in-house account transfers between
+    parties, electronic funds transfer networks like the ACH, global or local networks
+    like Visa, or some combination of the foregoing.'
+  sentences:
+  - What are some examples of alternative payments providers and how do they compete
+    with Visa?
+  - How much did the company's currently payable U.S. taxes amount to in 2023?
+  - What considerations are involved in recording an uncertain tax position?
+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: 0.6885714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8328571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8742857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9142857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6885714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2776190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17485714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09142857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6885714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8328571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8742857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9142857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8044897381040067
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7690017006802718
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.772240177124622
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6971428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8342857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8742857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6971428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27809523809523806
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17485714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09071428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6971428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8342857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8742857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8044496489287004
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7712602040816322
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7750129601859859
+      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: 0.8257142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8714285714285714
+      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: 0.2752380952380953
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17428571428571427
+      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: 0.8257142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8714285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.91
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8034440275222344
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7690856009070293
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7724648546606009
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6742857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.81
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8542857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6742857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17085714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6742857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.81
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8542857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7881399973034273
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7522210884353742
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7560032496112399
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6385714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7671428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8242857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.87
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6385714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2557142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16485714285714284
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.087
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6385714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7671428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8242857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.87
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7528845651704559
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7154948979591831
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7205565552029373
+      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("kperkins411/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Alternative Payments Providers: These providers, such as closed commerce ecosystems, BNPL solutions and cryptocurrency platforms, often have a primary focus of enabling payments through ecommerce and mobile channels; however, they are expanding or may expand their offerings to the physical point of sale. These companies may process payments using in-house account transfers between parties, electronic funds transfer networks like the ACH, global or local networks like Visa, or some combination of the foregoing.',
+    'What are some examples of alternative payments providers and how do they compete with Visa?',
+    "How much did the company's currently payable U.S. taxes amount to in 2023?",
+]
+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   | 0.6886     |
+| cosine_accuracy@3   | 0.8329     |
+| cosine_accuracy@5   | 0.8743     |
+| cosine_accuracy@10  | 0.9143     |
+| cosine_precision@1  | 0.6886     |
+| cosine_precision@3  | 0.2776     |
+| cosine_precision@5  | 0.1749     |
+| cosine_precision@10 | 0.0914     |
+| cosine_recall@1     | 0.6886     |
+| cosine_recall@3     | 0.8329     |
+| cosine_recall@5     | 0.8743     |
+| cosine_recall@10    | 0.9143     |
+| cosine_ndcg@10      | 0.8045     |
+| cosine_mrr@10       | 0.769      |
+| **cosine_map@100**  | **0.7722** |
+
+#### 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   | 0.6971    |
+| cosine_accuracy@3   | 0.8343    |
+| cosine_accuracy@5   | 0.8743    |
+| cosine_accuracy@10  | 0.9071    |
+| cosine_precision@1  | 0.6971    |
+| cosine_precision@3  | 0.2781    |
+| cosine_precision@5  | 0.1749    |
+| cosine_precision@10 | 0.0907    |
+| cosine_recall@1     | 0.6971    |
+| cosine_recall@3     | 0.8343    |
+| cosine_recall@5     | 0.8743    |
+| cosine_recall@10    | 0.9071    |
+| cosine_ndcg@10      | 0.8044    |
+| cosine_mrr@10       | 0.7713    |
+| **cosine_map@100**  | **0.775** |
+
+#### 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   | 0.8257     |
+| cosine_accuracy@5   | 0.8714     |
+| cosine_accuracy@10  | 0.91       |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.2752     |
+| cosine_precision@5  | 0.1743     |
+| cosine_precision@10 | 0.091      |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.8257     |
+| cosine_recall@5     | 0.8714     |
+| cosine_recall@10    | 0.91       |
+| cosine_ndcg@10      | 0.8034     |
+| cosine_mrr@10       | 0.7691     |
+| **cosine_map@100**  | **0.7725** |
+
+#### 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   | 0.6743    |
+| cosine_accuracy@3   | 0.81      |
+| cosine_accuracy@5   | 0.8543    |
+| cosine_accuracy@10  | 0.9       |
+| cosine_precision@1  | 0.6743    |
+| cosine_precision@3  | 0.27      |
+| cosine_precision@5  | 0.1709    |
+| cosine_precision@10 | 0.09      |
+| cosine_recall@1     | 0.6743    |
+| cosine_recall@3     | 0.81      |
+| cosine_recall@5     | 0.8543    |
+| cosine_recall@10    | 0.9       |
+| cosine_ndcg@10      | 0.7881    |
+| cosine_mrr@10       | 0.7522    |
+| **cosine_map@100**  | **0.756** |
+
+#### 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   | 0.6386     |
+| cosine_accuracy@3   | 0.7671     |
+| cosine_accuracy@5   | 0.8243     |
+| cosine_accuracy@10  | 0.87       |
+| cosine_precision@1  | 0.6386     |
+| cosine_precision@3  | 0.2557     |
+| cosine_precision@5  | 0.1649     |
+| cosine_precision@10 | 0.087      |
+| cosine_recall@1     | 0.6386     |
+| cosine_recall@3     | 0.7671     |
+| cosine_recall@5     | 0.8243     |
+| cosine_recall@10    | 0.87       |
+| cosine_ndcg@10      | 0.7529     |
+| cosine_mrr@10       | 0.7155     |
+| **cosine_map@100**  | **0.7206** |
+
+<!--
+## 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: 45.51 tokens</li><li>max: 371 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 20.83 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                 | anchor                                                                                                                                                             |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Activities related to sales before 2023 experienced adjustments due to changes in estimates, impacting the rebates and chargebacks accounts, and led to an ending balance of $4,493 million for the year 2023.</code>                                                                                              | <code>What adjustments were made to the rebates and chargebacks balances for previous years' sales and how did they affect the end of year balance in 2023?</code> |
+  | <code>We’re focused on making hosting just as popular as traveling on Airbnb. We will continue to invest in growing the size and quality of our Host community. We plan to attract more Hosts globally by expanding use cases and supporting all different types of Hosts, including those who host occasionally.</code> | <code>What is Airbnb's long-term corporate strategy regarding hosting?</code>                                                                                      |
+  | <code>Due to protectionist measures in various regions, Nike has experienced increased product costs. The company responds by monitoring trends, engaging in processes to mitigate restrictions, and advocating for trade liberalization in trade agreements.</code>                                                     | <code>What challenges related to trade protectionism has Nike faced, and what measures has the company taken in response?</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_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:--------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.96     | 3      | -             | 0.7116                 | 0.7341                 | 0.7448                 | 0.6550                | 0.7455                 |
+| 1.92     | 6      | -             | 0.7317                 | 0.7520                 | 0.7586                 | 0.6975                | 0.7591                 |
+| 2.88     | 9      | -             | 0.7334                 | 0.7553                 | 0.7631                 | 0.7039                | 0.7630                 |
+| 3.2      | 10     | 3.3636        | -                      | -                      | -                      | -                     | -                      |
+| **3.84** | **12** | **-**         | **0.7368**             | **0.759**              | **0.7634**             | **0.7054**            | **0.7638**             |
+| 0.96     | 3      | -             | 0.7415                 | 0.7601                 | 0.7672                 | 0.7102                | 0.7661                 |
+| 1.92     | 6      | -             | 0.7486                 | 0.7683                 | 0.7720                 | 0.7205                | 0.7718                 |
+| 2.88     | 9      | -             | 0.7556                 | 0.7718                 | 0.7750                 | 0.7215                | 0.7717                 |
+| 3.2      | 10     | 1.66          | -                      | -                      | -                      | -                     | -                      |
+| **3.84** | **12** | **-**         | **0.756**              | **0.7725**             | **0.775**              | **0.7206**            | **0.7722**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+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": "2.1.2+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 sha256:78d4d9f47bd3a53539da03a8de0f65d2b290c9dfd67510f519c25b4a67383f3b
+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]"
+}