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 +1,814 @@
+---
+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: A change in key assumptions such as the discount rate or projected
+    future revenues, expenses and cash flows could materially affect the determination
+    of fair values.
+  sentences:
+  - How many shares of common stock were sold in fiscal 2021 under GameStop Corp.'s
+    at-the-market equity offering programs?
+  - How does a change in key assumptions potentially affect the determination of fair
+    values of assets?
+  - What is the primary revenue source for Comcast's Theme Parks segment?
+- source_sentence: In January 2023, we announced our intention to implement a cost
+    reduction program to reduce automotive fixed costs by $2.0 billion on an annual
+    run rate basis by the end of 2024. This goal includes the impact of higher expected
+    depreciation and amortization expense and inflationary cost increases on fixed
+    cost but excludes changes in our pension income. In addition to people costs,
+    we are reducing our marketing and advertising expenses, streamlining our engineering
+    expense by reducing complexity across the vehicle portfolio, adjusting the cadivers-SafieiaıcıUrbanıcık,
+    prioritizing growth initiatives, and reducing our overall overhead and discretionary
+    costs.
+  sentences:
+  - What method does AbbVie primarily use to record investments in equity securities
+    with readily determinable fair values?
+  - What measures is General Motors taking to reduce costs and streamline operations?
+  - As of December 31, 2023, what is the total balance of acquisitions, foreign currency
+    translation and other adjustments?
+- source_sentence: AutoZone utilizes a computerized proprietary Point-of-Sale System
+    including bar code scanning and terminals to enhance customer service by efficiently
+    processing transactions and assisting in administrative tasks.
+  sentences:
+  - How does AutoZone's Point-of-Sale System enhance customer service?
+  - What unique feature did fiscal year 2021 have compared to 2023 and 2022?
+  - What was the primary source of the increase in premiums written by Berkshire Hathaway's
+    Property/Casualty reinsurance in 2023?
+- source_sentence: In 2023, capital expenditures for aircraft and related equipment
+    by FedEx Express saw a decrease of 26% compared to 2022.
+  sentences:
+  - What was the increase in earnings from operations for Optum from 2022 to 2023?
+  - What did the FCA require regarding the continued publication of certain LIBOR
+    settings after 2021?
+  - What was the percentage decrease in FedEx's aircraft and related equipment capital
+    expenditures in 2023 compared to 2022?
+- source_sentence: In 1983, Walmart opened its first Sam's Club, and in 1988, it opened
+    its first supercenter.
+  sentences:
+  - When did Walmart open its first Sam's Club and supercenter?
+  - Which standards and guidelines does the company use for informing its sustainability
+    disclosures?
+  - What accounting treatment does the Company apply to refunds issued to customers?
+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: 0.7028571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8371428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8728571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9185714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7028571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27904761904761904
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17457142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09185714285714283
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7028571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8371428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8728571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9185714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.81196519287814
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7777465986394556
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7809887604595412
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6985714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8328571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9242857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2776190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09242857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8328571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9242857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8104528945408784
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7743191609977326
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7771143041520369
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6942857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8585714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9085714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6942857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1717142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09085714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6942857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8585714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9085714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8026074561436641
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7686825396825395
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7726124326414546
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6885714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8157142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8571428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9071428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6885714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27190476190476187
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1714285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09071428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6885714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8157142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8571428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9071428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7972617985734928
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7622108843537415
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.765720886169324
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.66
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7985714285714286
+      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: 0.66
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2661904761904762
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1671428571428571
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08828571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.66
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7985714285714286
+      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: 0.7715751288332002
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7360753968253966
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7400601081956545
+      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("anishareddyalla/bge-base-financial-matryoshka-anisha")
+# Run inference
+sentences = [
+    "In 1983, Walmart opened its first Sam's Club, and in 1988, it opened its first supercenter.",
+    "When did Walmart open its first Sam's Club and supercenter?",
+    'Which standards and guidelines does the company use for informing its sustainability disclosures?',
+]
+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   | 0.7029    |
+| cosine_accuracy@3   | 0.8371    |
+| cosine_accuracy@5   | 0.8729    |
+| cosine_accuracy@10  | 0.9186    |
+| cosine_precision@1  | 0.7029    |
+| cosine_precision@3  | 0.279     |
+| cosine_precision@5  | 0.1746    |
+| cosine_precision@10 | 0.0919    |
+| cosine_recall@1     | 0.7029    |
+| cosine_recall@3     | 0.8371    |
+| cosine_recall@5     | 0.8729    |
+| cosine_recall@10    | 0.9186    |
+| cosine_ndcg@10      | 0.812     |
+| cosine_mrr@10       | 0.7777    |
+| **cosine_map@100**  | **0.781** |
+
+#### 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   | 0.6986     |
+| cosine_accuracy@3   | 0.8329     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9243     |
+| cosine_precision@1  | 0.6986     |
+| cosine_precision@3  | 0.2776     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0924     |
+| cosine_recall@1     | 0.6986     |
+| cosine_recall@3     | 0.8329     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9243     |
+| cosine_ndcg@10      | 0.8105     |
+| cosine_mrr@10       | 0.7743     |
+| **cosine_map@100**  | **0.7771** |
+
+#### 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   | 0.6943     |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.8586     |
+| cosine_accuracy@10  | 0.9086     |
+| cosine_precision@1  | 0.6943     |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.1717     |
+| cosine_precision@10 | 0.0909     |
+| cosine_recall@1     | 0.6943     |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.8586     |
+| cosine_recall@10    | 0.9086     |
+| cosine_ndcg@10      | 0.8026     |
+| cosine_mrr@10       | 0.7687     |
+| **cosine_map@100**  | **0.7726** |
+
+#### 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   | 0.6886     |
+| cosine_accuracy@3   | 0.8157     |
+| cosine_accuracy@5   | 0.8571     |
+| cosine_accuracy@10  | 0.9071     |
+| cosine_precision@1  | 0.6886     |
+| cosine_precision@3  | 0.2719     |
+| cosine_precision@5  | 0.1714     |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.6886     |
+| cosine_recall@3     | 0.8157     |
+| cosine_recall@5     | 0.8571     |
+| cosine_recall@10    | 0.9071     |
+| cosine_ndcg@10      | 0.7973     |
+| cosine_mrr@10       | 0.7622     |
+| **cosine_map@100**  | **0.7657** |
+
+#### 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   | 0.66       |
+| cosine_accuracy@3   | 0.7986     |
+| cosine_accuracy@5   | 0.8357     |
+| cosine_accuracy@10  | 0.8829     |
+| cosine_precision@1  | 0.66       |
+| cosine_precision@3  | 0.2662     |
+| cosine_precision@5  | 0.1671     |
+| cosine_precision@10 | 0.0883     |
+| cosine_recall@1     | 0.66       |
+| cosine_recall@3     | 0.7986     |
+| cosine_recall@5     | 0.8357     |
+| cosine_recall@10    | 0.8829     |
+| cosine_ndcg@10      | 0.7716     |
+| cosine_mrr@10       | 0.7361     |
+| **cosine_map@100**  | **0.7401** |
+
+<!--
+## 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: 8 tokens</li><li>mean: 46.43 tokens</li><li>max: 439 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.76 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | anchor                                                                                                                                                                                           |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The Company’s human capital management strategy is built on three fundamental focus areas: Attracting and recruiting the best talent, Developing and retaining talent, Empowering and inspiring talent.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | <code>What strategies are outlined in the Company's human capital management?</code>                                                                                                             |
+  | <code>Opinion on the Consolidated Financial Statements We have audited the accompanying consolidated balance sheets of Costco Wholesale Corporation and subsidiaries (the Company) as of September 3, 2023, and August 28, 2022, the related consolidated statements of income, comprehensive income, equity, and cash flows for the 53-week period ended September 3, 2023, and the 52-week periods ended August 28, 2022, and August 29, 2021, and the related notes (collectively, the consolidated financial statements). In our opinion, the consolidated financial statements present fairly, in all material respects, the financial position of the Company as of September 3, 2023, and August 28, 2022, and the results of its operations and its cash flows for each of the 53-week period ended September 3, 2023, and the 52-week periods ended August 28, 2022, and August 29, 2021, in conformity with U.S. generally accepted accounting principles.</code> | <code>What was the opinion of the independent registered public accounting firm on Costco Wholesale Corporation's consolidated financial statements for the year ended September 3, 2023?</code> |
+  | <code>Nonperforming loans and leases are generally those that have been placed on nonaccrual status, such as when they are 90 days past due or have confirmed cases of fraud or bankruptcy. Additionally, specific types of loans like consumer real estate-secured loans are classified as nonperforming at 90 days past due unless they are fully insured, and commercial loans and leases are classified as nonperforming when past due 90 days or more unless well-secured and in the process of collection.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                     | <code>What criteria are used to classify loans and leases as nonperforming according to the described credit policy?</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
+- `eval_on_start`: 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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8122     | 10     | 1.5488        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7540                 | 0.7565                 | 0.7660                 | 0.7176                | 0.7693                 |
+| 1.6244     | 20     | 0.674         | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7622                 | 0.7715                 | 0.7781                 | 0.7352                | 0.7790                 |
+| 2.4365     | 30     | 0.4592        | -                      | -                      | -                      | -                     | -                      |
+| **2.9239** | **36** | **-**         | **0.7648**             | **0.7729**             | **0.7778**             | **0.7384**            | **0.7799**             |
+| 3.2487     | 40     | 0.4113        | -                      | -                      | -                      | -                     | -                      |
+| 3.8985     | 48     | -             | 0.7657                 | 0.7726                 | 0.7771                 | 0.7401                | 0.7810                 |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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": "4.42.4",
+  "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": "4.42.4",
+    "pytorch": "2.3.1+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 sha256:4ac6888d3098cb42ec8a75c22c7dc99a35b878cf193625d7b40bd0ff14dc7a0d
+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]"
+}