Model save

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 +1,862 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: How many hours of training and development did Bank of America
+    provide to its employees in 2023?
+  sentences:
+  - In recent years, several jurisdictions have enhanced their laws and regulations
+    in this area, increased their enforcement activities, and/or increased the level
+    of cross-border coordination and information sharing.
+  - In 2023, Bank of America delivered approximately 6.7 million hours of training
+    and development to its teammates through Bank of America Academy.
+  - Chevron affiliates manage a total of 338 thousand net acres, as detailed in the
+    table for acreage distribution as of December 31, 2023.
+- source_sentence: What are the projected trends for Comcast's residential connectivity
+    revenue in 2023?
+  sentences:
+  - In 2023, Switzerland’s Federal Council passed legislation which would implement
+    a federal minimum tax in Switzerland of 15% in 2024.
+  - We believe our residential connectivity revenue will increase as a result of growth
+    in average domestic broadband revenue per customer, as well as increases in domestic
+    wireless and international connectivity revenue.
+  - Approximately 97% of our debt securities were investment-grade quality, with a
+    weighted average credit rating of AA- at the end of 2023.
+- source_sentence: What type of merchandise is included under seasonal and electronics
+    merchandise?
+  sentences:
+  - Seasonal and electronics merchandise at the company includes items related to
+    Christmas, Easter, Halloween, and Valentine's Day, along with personal electronics
+    like pre-paid cellular phones and services.
+  - Hewlett Packard Enterprise, with over half of their revenue generated overseas,
+    experiences impact from fluctuations in foreign currency exchange rates. These
+    fluctuations have increased product costs and moderated revenue and earnings growth,
+    particularly in recent periods.
+  - Net investment income grew from $597 million in 2021 to $895 million in 2023,
+    which is a 43.0% increase.
+- source_sentence: What are the types of dialysis available for ESKD patients and
+    how often is hemodialysis typically performed?
+  sentences:
+  - Note 16 is important in a Form 10-K for providing detailed information on legal
+    proceedings as 'Commitments and Contingencies.'
+  - Amazon believes that the principal competitive factors in its retail businesses
+    include selection, price, and convenience, including fast and reliable fulfillment.
+  - Dialysis options for ESKD patients include hemodialysis, which is usually performed
+    three times per week, and peritoneal dialysis.
+- source_sentence: How much total cash did The Hershey Company use for share repurchases
+    in 2023 excluding excise tax?
+  sentences:
+  - In 2023, The Hershey Company used a total of $267.3 million in cash for share
+    repurchases, excluding any excise tax.
+  - Operating income increased $5.8 billion, or 72.8%, in 2023 compared to 2022. The
+    increase in operating income was primarily driven by the absence of $5.8 billion
+    of opioid litigation charges recorded in 2022 and increases in the Pharmacy &
+    Consumer Wellness segment, primarily driven by the absence of a $2.5 billion loss
+    on assets held for sale recorded in 2022 related to the write-down of the Company’s
+    Omnicare® long-term care business which was partially offset by continued pharmacy
+    reimbursement pressure and decreased COVID-19 vaccinations and diagnostic testing
+    compared to 2022, as well as an increase in the Health Services segment.
+  - Net income for the year ended December 31, 2023, was $307,568, contrasting with
+    a net loss of $694,288 in 2022.
+datasets:
+- philschmid/finanical-rag-embedding-dataset
+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: 0.6914285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8257142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9228571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6914285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2752380952380952
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1737142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09228571428571428
+      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: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9228571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8071406101424283
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.770200113378685
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7731689567146356
+      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: 0.8314285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9142857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17371428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09142857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8314285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9142857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8065430842560983
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7719557823129252
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.775512801809706
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6842857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8214285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8671428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9057142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6842857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2738095238095238
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1734285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09057142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6842857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8214285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8671428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9057142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7965883498968402
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7613792517006803
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7655926405987631
+      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: 0.8157142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8557142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9057142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6828571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27190476190476187
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17114285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09057142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6828571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8157142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8557142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9057142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7942960704612301
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7586780045351473
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7624961899058385
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6485714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7771428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8171428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.87
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6485714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2590476190476191
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16342857142857142
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.087
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6485714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7771428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8171428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.87
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7582844308652432
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7225646258503399
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7276362979042951
+      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 [finanical-rag-embedding-dataset](https://huggingface.co/datasets/philschmid/finanical-rag-embedding-dataset) 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:**
+    - [finanical-rag-embedding-dataset](https://huggingface.co/datasets/philschmid/finanical-rag-embedding-dataset)
+- **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("bnkc123/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'How much total cash did The Hershey Company use for share repurchases in 2023 excluding excise tax?',
+    'In 2023, The Hershey Company used a total of $267.3 million in cash for share repurchases, excluding any excise tax.',
+    'Operating income increased $5.8 billion, or 72.8%, in 2023 compared to 2022. The increase in operating income was primarily driven by the absence of $5.8 billion of opioid litigation charges recorded in 2022 and increases in the Pharmacy & Consumer Wellness segment, primarily driven by the absence of a $2.5 billion loss on assets held for sale recorded in 2022 related to the write-down of the Company’s Omnicare® long-term care business which was partially offset by continued pharmacy reimbursement pressure and decreased COVID-19 vaccinations and diagnostic testing compared to 2022, as well as an increase in the Health Services segment.',
+]
+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) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6914     |
+| cosine_accuracy@3   | 0.8257     |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9229     |
+| cosine_precision@1  | 0.6914     |
+| cosine_precision@3  | 0.2752     |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0923     |
+| cosine_recall@1     | 0.6914     |
+| cosine_recall@3     | 0.8257     |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9229     |
+| **cosine_ndcg@10**  | **0.8071** |
+| cosine_mrr@10       | 0.7702     |
+| cosine_map@100      | 0.7732     |
+
+#### 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   | 0.6986     |
+| cosine_accuracy@3   | 0.8314     |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9143     |
+| cosine_precision@1  | 0.6986     |
+| cosine_precision@3  | 0.2771     |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0914     |
+| cosine_recall@1     | 0.6986     |
+| cosine_recall@3     | 0.8314     |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9143     |
+| **cosine_ndcg@10**  | **0.8065** |
+| cosine_mrr@10       | 0.772      |
+| cosine_map@100      | 0.7755     |
+
+#### 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   | 0.6843     |
+| cosine_accuracy@3   | 0.8214     |
+| cosine_accuracy@5   | 0.8671     |
+| cosine_accuracy@10  | 0.9057     |
+| cosine_precision@1  | 0.6843     |
+| cosine_precision@3  | 0.2738     |
+| cosine_precision@5  | 0.1734     |
+| cosine_precision@10 | 0.0906     |
+| cosine_recall@1     | 0.6843     |
+| cosine_recall@3     | 0.8214     |
+| cosine_recall@5     | 0.8671     |
+| cosine_recall@10    | 0.9057     |
+| **cosine_ndcg@10**  | **0.7966** |
+| cosine_mrr@10       | 0.7614     |
+| cosine_map@100      | 0.7656     |
+
+#### 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   | 0.8157     |
+| cosine_accuracy@5   | 0.8557     |
+| cosine_accuracy@10  | 0.9057     |
+| cosine_precision@1  | 0.6829     |
+| cosine_precision@3  | 0.2719     |
+| cosine_precision@5  | 0.1711     |
+| cosine_precision@10 | 0.0906     |
+| cosine_recall@1     | 0.6829     |
+| cosine_recall@3     | 0.8157     |
+| cosine_recall@5     | 0.8557     |
+| cosine_recall@10    | 0.9057     |
+| **cosine_ndcg@10**  | **0.7943** |
+| cosine_mrr@10       | 0.7587     |
+| cosine_map@100      | 0.7625     |
+
+#### 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   | 0.6486     |
+| cosine_accuracy@3   | 0.7771     |
+| cosine_accuracy@5   | 0.8171     |
+| cosine_accuracy@10  | 0.87       |
+| cosine_precision@1  | 0.6486     |
+| cosine_precision@3  | 0.259      |
+| cosine_precision@5  | 0.1634     |
+| cosine_precision@10 | 0.087      |
+| cosine_recall@1     | 0.6486     |
+| cosine_recall@3     | 0.7771     |
+| cosine_recall@5     | 0.8171     |
+| cosine_recall@10    | 0.87       |
+| **cosine_ndcg@10**  | **0.7583** |
+| cosine_mrr@10       | 0.7226     |
+| cosine_map@100      | 0.7276     |
+
+<!--
+## 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
+
+#### finanical-rag-embedding-dataset
+
+* Dataset: [finanical-rag-embedding-dataset](https://huggingface.co/datasets/philschmid/finanical-rag-embedding-dataset) at [e0b1781](https://huggingface.co/datasets/philschmid/finanical-rag-embedding-dataset/tree/e0b17819cf52d444066c99f4a176f5717e066300)
+* Size: 6,300 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                             |
+  | details | <ul><li>min: 9 tokens</li><li>mean: 20.65 tokens</li><li>max: 51 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 45.4 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                            | positive                                                                                                                                                                                                                                                                       |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How much cash did FedEx have at the end of May 2023?</code>                                                                                                 | <code>FedEx reported having $6.9 billion in cash and cash equivalents at the end of May 2023.</code>                                                                                                                                                                           |
+  | <code>What were Caterpillar's total obligations for the purchase of goods and services as of December 31, 2023?</code>                                            | <code>We have short-term obligations related to the purchase of goods and services made in the ordinary course of business. These consist of invoices received and recorded as liabilities as of December 31, 2023, but scheduled for payment in 2024 of $7.91 billion.</code> |
+  | <code>What was the total number of outstanding stock option awards at the beginning and end of 2023, and what were their weighted average exercise prices?</code> | <code>Stock option activity under the Plan for the years ended reveals that stock options both started and ended with 6.2 million outstanding in 2023. The weighted average exercise price at the beginning of the year was $50.40 and $50.42 at the end.</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
+- `push_to_hub`: True
+- `hub_model_id`: bnkc123/bge-base-financial-matryoshka
+- `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
+- `torch_empty_cache_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}
+- `tp_size`: 0
+- `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`: True
+- `resume_from_checkpoint`: None
+- `hub_model_id`: bnkc123/bge-base-financial-matryoshka
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</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     | 25.3869       | -                      | -                      | -                      | -                      | -                     |
+| 1.0       | 13     | -             | 0.7943                 | 0.7907                 | 0.7884                 | 0.7756                 | 0.7419                |
+| 1.5685    | 20     | 9.8731        | -                      | -                      | -                      | -                      | -                     |
+| 2.0       | 26     | -             | 0.8040                 | 0.8032                 | 0.7939                 | 0.7906                 | 0.7553                |
+| 2.3249    | 30     | 7.6627        | -                      | -                      | -                      | -                      | -                     |
+| 3.0       | 39     | -             | 0.8067                 | 0.8054                 | 0.7989                 | 0.7930                 | 0.7584                |
+| 3.0812    | 40     | 6.5397        | -                      | -                      | -                      | -                      | -                     |
+| **3.731** | **48** | **-**         | **0.8071**             | **0.8065**             | **0.7966**             | **0.7943**             | **0.7583**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.6
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.6.0
+- Datasets: 3.5.1
+- Tokenizers: 0.21.1
+
+## 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_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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
+}