README.md

---
base_model: mixedbread-ai/mxbai-embed-large-v1
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:580
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: In response to hypothetical economic scenarios presented by the
    Federal Reserve, Wells Fargo formulated a capital action plan. This was done as
    a part of the CCAR (Comprehensive Capital Analysis and Review) process. The scenarios
    tested included a hypothetical severe global recession which, at its most stressful
    point, reduces our Pre-Provision Net Revenue (PPNR) to negative levels for four
    consecutive quarters.
  sentences:
  - What is the proposed dividend per share for the shareholders of Apple Inc. for
    the financial year ending in 2023?
  - What steps has Wells Fargo undertaken to sustain in the event of a severe global
    recession?
  - What was the total net income for Intel in 2021?
- source_sentence: Microsoft Corporation has been paying consistent dividends to its
    shareholders on a quarterly basis. The company's Board of Directors reviews the
    dividend policy on a regular basis and plans to continue paying quarterly dividends,
    subject to capital availability and financial conditions
  sentences:
  - What did Amazon.com, Inc. anticipate regarding its free cash flows in the future?
  - What is Tesla's outlook for 2024 in terms of vehicle production?
  - What is Microsoft Corporation's dividend policy?
- source_sentence: In the second quarter of 2023, Tesla's automotive revenue increased
    by 58% compared to the same period previous year. These results were primarily
    driven by increased vehicle deliveries and expansion in the China market.
  sentences:
  - What action did the Federal Reserve take to address the inflation surge in 2027?
  - What revenue did Apple Inc. report in the first quarter of 2021?
  - How did Tesla's automotive revenue perform in the second quarter of 2023?
- source_sentence: Intel Corporation is an American multinational corporation and
    technology company headquartered in Santa Clara, California. It's primarily known
    for designing and manufacturing semiconductors and various technology solutions,
    including processors for computer systems and servers, integrated digital technology
    platforms, and system-on-chip units for gateways.
  sentences:
  - What is Intel's main area of business?
  - What was the revenue growth percentage of Amazon in the second quarter of 2024?
  - How much capital expenditure did Amazon.com report in 2025?
- source_sentence: In 2023, EnergyCorp declared a dividend of $2.5 per share.
  sentences:
  - How did Amazon’s shift to one-day prime delivery affect its operational costs
    in 2023?
  - What dividend did the EnergyCorp pay to its shareholders in 2023?
  - What was the profit margin of Airbus in the year 2025?
model-index:
- name: Bmixedbread-ai/mxbai-embed-large-v1 Financial Matryoshka
  results:
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 1024
      type: dim_1024
    metrics:
    - type: cosine_accuracy@1
      value: 0.8923076923076924
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9692307692307692
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9692307692307692
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8923076923076924
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.32307692307692304
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.1938461538461538
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8923076923076924
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9692307692307692
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9692307692307692
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.941940347600734
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.927838827838828
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.928083028083028
      name: Cosine Map@100
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 768
      type: dim_768
    metrics:
    - type: cosine_accuracy@1
      value: 0.8923076923076924
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9692307692307692
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9692307692307692
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8923076923076924
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.32307692307692304
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.1938461538461538
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8923076923076924
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9692307692307692
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9692307692307692
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.9422922530434215
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.9282051282051282
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.9284418145956608
      name: Cosine Map@100
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 512
      type: dim_512
    metrics:
    - type: cosine_accuracy@1
      value: 0.8923076923076924
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9692307692307692
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9692307692307692
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8923076923076924
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.32307692307692304
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.1938461538461538
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8923076923076924
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9692307692307692
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9692307692307692
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.941940347600734
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.927838827838828
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.928113553113553
      name: Cosine Map@100
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 256
      type: dim_256
    metrics:
    - type: cosine_accuracy@1
      value: 0.8923076923076924
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9692307692307692
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9692307692307692
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8923076923076924
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.32307692307692304
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.1938461538461538
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8923076923076924
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9692307692307692
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9692307692307692
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.9416654482692324
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.9275641025641026
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.9278846153846154
      name: Cosine Map@100
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 128
      type: dim_128
    metrics:
    - type: cosine_accuracy@1
      value: 0.8461538461538461
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9538461538461539
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9692307692307692
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8461538461538461
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.31794871794871793
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.1938461538461538
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8461538461538461
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9538461538461539
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9692307692307692
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.9221774232775186
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.9012820512820513
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.9016398330351819
      name: Cosine Map@100
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 64
      type: dim_64
    metrics:
    - type: cosine_accuracy@1
      value: 0.8153846153846154
      name: Cosine Accuracy@1
    - type: cosine_accuracy@3
      value: 0.9692307692307692
      name: Cosine Accuracy@3
    - type: cosine_accuracy@5
      value: 0.9846153846153847
      name: Cosine Accuracy@5
    - type: cosine_accuracy@10
      value: 0.9846153846153847
      name: Cosine Accuracy@10
    - type: cosine_precision@1
      value: 0.8153846153846154
      name: Cosine Precision@1
    - type: cosine_precision@3
      value: 0.32307692307692304
      name: Cosine Precision@3
    - type: cosine_precision@5
      value: 0.19692307692307687
      name: Cosine Precision@5
    - type: cosine_precision@10
      value: 0.09846153846153843
      name: Cosine Precision@10
    - type: cosine_recall@1
      value: 0.8153846153846154
      name: Cosine Recall@1
    - type: cosine_recall@3
      value: 0.9692307692307692
      name: Cosine Recall@3
    - type: cosine_recall@5
      value: 0.9846153846153847
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.9846153846153847
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.9123594012651499
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.8876923076923079
      name: Cosine Mrr@10
    - type: cosine_map@100
      value: 0.8879622132253712
      name: Cosine Map@100
---

# Bmixedbread-ai/mxbai-embed-large-v1 Financial Matryoshka

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1). It maps sentences & paragraphs to a 1024-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:** [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) <!-- at revision 990580e27d329c7408b3741ecff85876e128e203 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 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': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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})
)
```

## 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("rbhatia46/mxbai-embed-large-v1-financial-rag-matryoshka")
# Run inference
sentences = [
    'In 2023, EnergyCorp declared a dividend of $2.5 per share.',
    'What dividend did the EnergyCorp pay to its shareholders in 2023?',
    'How did Amazon’s shift to one-day prime delivery affect its operational costs in 2023?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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_1024`
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

| Metric              | Value      |
|:--------------------|:-----------|
| cosine_accuracy@1   | 0.8923     |
| cosine_accuracy@3   | 0.9692     |
| cosine_accuracy@5   | 0.9692     |
| cosine_accuracy@10  | 0.9846     |
| cosine_precision@1  | 0.8923     |
| cosine_precision@3  | 0.3231     |
| cosine_precision@5  | 0.1938     |
| cosine_precision@10 | 0.0985     |
| cosine_recall@1     | 0.8923     |
| cosine_recall@3     | 0.9692     |
| cosine_recall@5     | 0.9692     |
| cosine_recall@10    | 0.9846     |
| cosine_ndcg@10      | 0.9419     |
| cosine_mrr@10       | 0.9278     |
| **cosine_map@100**  | **0.9281** |

#### 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   | 0.8923     |
| cosine_accuracy@3   | 0.9692     |
| cosine_accuracy@5   | 0.9692     |
| cosine_accuracy@10  | 0.9846     |
| cosine_precision@1  | 0.8923     |
| cosine_precision@3  | 0.3231     |
| cosine_precision@5  | 0.1938     |
| cosine_precision@10 | 0.0985     |
| cosine_recall@1     | 0.8923     |
| cosine_recall@3     | 0.9692     |
| cosine_recall@5     | 0.9692     |
| cosine_recall@10    | 0.9846     |
| cosine_ndcg@10      | 0.9423     |
| cosine_mrr@10       | 0.9282     |
| **cosine_map@100**  | **0.9284** |

#### 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   | 0.8923     |
| cosine_accuracy@3   | 0.9692     |
| cosine_accuracy@5   | 0.9692     |
| cosine_accuracy@10  | 0.9846     |
| cosine_precision@1  | 0.8923     |
| cosine_precision@3  | 0.3231     |
| cosine_precision@5  | 0.1938     |
| cosine_precision@10 | 0.0985     |
| cosine_recall@1     | 0.8923     |
| cosine_recall@3     | 0.9692     |
| cosine_recall@5     | 0.9692     |
| cosine_recall@10    | 0.9846     |
| cosine_ndcg@10      | 0.9419     |
| cosine_mrr@10       | 0.9278     |
| **cosine_map@100**  | **0.9281** |

#### 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   | 0.8923     |
| cosine_accuracy@3   | 0.9692     |
| cosine_accuracy@5   | 0.9692     |
| cosine_accuracy@10  | 0.9846     |
| cosine_precision@1  | 0.8923     |
| cosine_precision@3  | 0.3231     |
| cosine_precision@5  | 0.1938     |
| cosine_precision@10 | 0.0985     |
| cosine_recall@1     | 0.8923     |
| cosine_recall@3     | 0.9692     |
| cosine_recall@5     | 0.9692     |
| cosine_recall@10    | 0.9846     |
| cosine_ndcg@10      | 0.9417     |
| cosine_mrr@10       | 0.9276     |
| **cosine_map@100**  | **0.9279** |

#### 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   | 0.8462     |
| cosine_accuracy@3   | 0.9538     |
| cosine_accuracy@5   | 0.9692     |
| cosine_accuracy@10  | 0.9846     |
| cosine_precision@1  | 0.8462     |
| cosine_precision@3  | 0.3179     |
| cosine_precision@5  | 0.1938     |
| cosine_precision@10 | 0.0985     |
| cosine_recall@1     | 0.8462     |
| cosine_recall@3     | 0.9538     |
| cosine_recall@5     | 0.9692     |
| cosine_recall@10    | 0.9846     |
| cosine_ndcg@10      | 0.9222     |
| cosine_mrr@10       | 0.9013     |
| **cosine_map@100**  | **0.9016** |

#### 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   | 0.8154    |
| cosine_accuracy@3   | 0.9692    |
| cosine_accuracy@5   | 0.9846    |
| cosine_accuracy@10  | 0.9846    |
| cosine_precision@1  | 0.8154    |
| cosine_precision@3  | 0.3231    |
| cosine_precision@5  | 0.1969    |
| cosine_precision@10 | 0.0985    |
| cosine_recall@1     | 0.8154    |
| cosine_recall@3     | 0.9692    |
| cosine_recall@5     | 0.9846    |
| cosine_recall@10    | 0.9846    |
| cosine_ndcg@10      | 0.9124    |
| cosine_mrr@10       | 0.8877    |
| **cosine_map@100**  | **0.888** |

<!--
## 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: 580 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: 16 tokens</li><li>mean: 44.21 tokens</li><li>max: 98 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 17.5 tokens</li><li>max: 30 tokens</li></ul> |
* Samples:
  | positive                                                                                                                                                                                    | anchor                                                                                      |
  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------|
  | <code>For the fiscal year 2020, Microsoft Corporation reported a net income of $44.3 billion, showing a 13% increase from the previous year.</code>                                         | <code>What was the net income of Microsoft Corporation for the fiscal year 2020?</code>     |
  | <code>As of the latest financial report, Amazon has a current price to earnings ratio (P/E ratio) of 76.6.</code>                                                                           | <code>What is Amazon's current P/E ratio according to their latest financial report?</code> |
  | <code>Microsoft Corporation posted an EBITDA (Earnings Before Interest, Taxes, Depreciation, and Amortization) margin of approximately 47% in 2021, showcasing strong profitability.</code> | <code>What was Microsoft Corporation's EBITDA margin in 2021?</code>                        |
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
  ```json
  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          1024,
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          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  | dim_1024_cosine_map@100 | 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 |
|:----------:|:-----:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
| 0.8421     | 1     | 0.9032                  | 0.8846                 | 0.9033                 | 0.9109                 | 0.8695                | 0.9186                 |
| 1.6842     | 2     | 0.9121                  | 0.8948                 | 0.9174                 | 0.9199                 | 0.8777                | 0.9198                 |
| 2.5263     | 3     | 0.9281                  | 0.9013                 | 0.9202                 | 0.9281                 | 0.8879                | 0.9204                 |
| **3.3684** | **4** | **0.9281**              | **0.9016**             | **0.9279**             | **0.9281**             | **0.888**             | **0.9284**             |

* The bold row denotes the saved checkpoint.

### Framework Versions
- Python: 3.10.6
- 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.*
-->