---
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:3550
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: At the end of 2023, Alphabet Inc. reported total debts amounting
to $14.2 billion, compared to $10.9 billion at the end of 2022.
sentences:
- What was the total debt of Alphabet Inc. as of the end of 2023?
- What was ExxonMobil's contribution to the energy production in the Energy sector
during 2020?
- Describe Amazon's revenue growth in 2023?
- source_sentence: In 2022, Pfizer strategically managed cash flow from investments
by utilizing operating cash flow, issuing new debt, and through the monetization
of certain non-core assets. This approach of diversifying the source of funding
for investments was done to minimize risk and uncertainty in economic conditions.
sentences:
- How much capital expenditure did AUX Energy invest in renewable energy projects
in 2022?
- What effect did the 2023 market downturn have on Amazon's retail and cloud segments?
- How did Pfizer manage cash flows from investments in 2022?
- source_sentence: The primary revenue generators for JPMorgan Chase for the fiscal
year 2023 were the Corporate & Investment Bank (CIB) and the Asset & Wealth Management
(AWM) sectors. The CIB sector benefited from a rise in merger and acquisition
activities, while AWM saw large net inflows.
sentences:
- What is General Electric's strategic priority for its Aviation business segment?
- Which sectors contributed the most to the revenue of JPMorgan Chase for FY 2023?
- What is the principal activity of Apple Inc.?
- source_sentence: For the fiscal year 2023, Microsoft's Intelligent Cloud segment
generated revenues of $58 billion, demonstrating solid growth fueled by strong
demand for cloud services and server products.
sentences:
- What is the primary strategy of McDonald’s to drive growth in the future?
- What impact did the increase in gold prices have on Newmont Corporation's revenue
in 2023?
- What was the revenue generated by Microsoft's Intelligent Cloud segment for fiscal
year 2023?
- source_sentence: Microsoft, in their latest press release, revealed that they are
anticipating a revenue growth of approximately 12% for the fiscal year ending
in 2024.
sentences:
- What is Microsoft's projected revenue growth for fiscal year 2024?
- What is the fair value of equity method investments of Microsoft in the fiscal
year 2025?
- What was the impact of COVID-19 on Zoom's profits?
model-index:
- name: mxbai-embed-large-v1-financial-rag-matryoshka
results:
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 1024
type: dim_1024
metrics:
- type: cosine_accuracy@1
value: 0.8455696202531645
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9392405063291139
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9670886075949368
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9898734177215189
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8455696202531645
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.31308016877637135
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19341772151898737
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0989873417721519
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8455696202531645
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9392405063291139
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9670886075949368
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9898734177215189
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9212281141643793
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.898873819570022
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8993853803492357
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 768
type: dim_768
metrics:
- type: cosine_accuracy@1
value: 0.8455696202531645
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9392405063291139
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9670886075949368
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9898734177215189
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8455696202531645
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3130801687763713
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.1934177215189873
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0989873417721519
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8455696202531645
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9392405063291139
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9670886075949368
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9898734177215189
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9217284365901642
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8994826200522402
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8999494134557425
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 512
type: dim_512
metrics:
- type: cosine_accuracy@1
value: 0.8405063291139241
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9367088607594937
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9645569620253165
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9898734177215189
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8405063291139241
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.31223628691983124
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19291139240506328
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0989873417721519
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8405063291139241
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9367088607594937
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9645569620253165
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9898734177215189
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9186273598847787
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8954631303998389
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8958871142668611
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 256
type: dim_256
metrics:
- type: cosine_accuracy@1
value: 0.8455696202531645
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9392405063291139
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9645569620253165
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9898734177215189
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8455696202531645
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3130801687763713
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19291139240506328
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.0989873417721519
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8455696202531645
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9392405063291139
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9645569620253165
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9898734177215189
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9201161947922436
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8975597749648381
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8979721416614026
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 128
type: dim_128
metrics:
- type: cosine_accuracy@1
value: 0.8405063291139241
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9417721518987342
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9645569620253165
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9848101265822785
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8405063291139241
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3139240506329114
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19291139240506328
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09848101265822784
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8405063291139241
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9417721518987342
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9645569620253165
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9848101265822785
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9170562815583235
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8948693992364878
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8957325656059834
name: Cosine Map@100
- task:
type: information-retrieval
name: Information Retrieval
dataset:
name: dim 64
type: dim_64
metrics:
- type: cosine_accuracy@1
value: 0.8405063291139241
name: Cosine Accuracy@1
- type: cosine_accuracy@3
value: 0.9316455696202531
name: Cosine Accuracy@3
- type: cosine_accuracy@5
value: 0.9569620253164557
name: Cosine Accuracy@5
- type: cosine_accuracy@10
value: 0.9822784810126582
name: Cosine Accuracy@10
- type: cosine_precision@1
value: 0.8405063291139241
name: Cosine Precision@1
- type: cosine_precision@3
value: 0.3105485232067511
name: Cosine Precision@3
- type: cosine_precision@5
value: 0.19139240506329114
name: Cosine Precision@5
- type: cosine_precision@10
value: 0.09822784810126582
name: Cosine Precision@10
- type: cosine_recall@1
value: 0.8405063291139241
name: Cosine Recall@1
- type: cosine_recall@3
value: 0.9316455696202531
name: Cosine Recall@3
- type: cosine_recall@5
value: 0.9569620253164557
name: Cosine Recall@5
- type: cosine_recall@10
value: 0.9822784810126582
name: Cosine Recall@10
- type: cosine_ndcg@10
value: 0.9153318022971121
name: Cosine Ndcg@10
- type: cosine_mrr@10
value: 0.8934589109905566
name: Cosine Mrr@10
- type: cosine_map@100
value: 0.8943102728098851
name: Cosine Map@100
---
# mxbai-embed-large-v1-financial-rag-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)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 tokens
- **Similarity Function:** Cosine Similarity
- **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 = [
'Microsoft, in their latest press release, revealed that they are anticipating a revenue growth of approximately 12% for the fiscal year ending in 2024.',
"What is Microsoft's projected revenue growth for fiscal year 2024?",
"What was the impact of COVID-19 on Zoom's profits?",
]
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]
```
## Evaluation
### Metrics
#### Information Retrieval
* Dataset: `dim_1024`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.8456 |
| cosine_accuracy@3 | 0.9392 |
| cosine_accuracy@5 | 0.9671 |
| cosine_accuracy@10 | 0.9899 |
| cosine_precision@1 | 0.8456 |
| cosine_precision@3 | 0.3131 |
| cosine_precision@5 | 0.1934 |
| cosine_precision@10 | 0.099 |
| cosine_recall@1 | 0.8456 |
| cosine_recall@3 | 0.9392 |
| cosine_recall@5 | 0.9671 |
| cosine_recall@10 | 0.9899 |
| cosine_ndcg@10 | 0.9212 |
| cosine_mrr@10 | 0.8989 |
| **cosine_map@100** | **0.8994** |
#### Information Retrieval
* Dataset: `dim_768`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.8456 |
| cosine_accuracy@3 | 0.9392 |
| cosine_accuracy@5 | 0.9671 |
| cosine_accuracy@10 | 0.9899 |
| cosine_precision@1 | 0.8456 |
| cosine_precision@3 | 0.3131 |
| cosine_precision@5 | 0.1934 |
| cosine_precision@10 | 0.099 |
| cosine_recall@1 | 0.8456 |
| cosine_recall@3 | 0.9392 |
| cosine_recall@5 | 0.9671 |
| cosine_recall@10 | 0.9899 |
| cosine_ndcg@10 | 0.9217 |
| cosine_mrr@10 | 0.8995 |
| **cosine_map@100** | **0.8999** |
#### Information Retrieval
* Dataset: `dim_512`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.8405 |
| cosine_accuracy@3 | 0.9367 |
| cosine_accuracy@5 | 0.9646 |
| cosine_accuracy@10 | 0.9899 |
| cosine_precision@1 | 0.8405 |
| cosine_precision@3 | 0.3122 |
| cosine_precision@5 | 0.1929 |
| cosine_precision@10 | 0.099 |
| cosine_recall@1 | 0.8405 |
| cosine_recall@3 | 0.9367 |
| cosine_recall@5 | 0.9646 |
| cosine_recall@10 | 0.9899 |
| cosine_ndcg@10 | 0.9186 |
| cosine_mrr@10 | 0.8955 |
| **cosine_map@100** | **0.8959** |
#### Information Retrieval
* Dataset: `dim_256`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:----------|
| cosine_accuracy@1 | 0.8456 |
| cosine_accuracy@3 | 0.9392 |
| cosine_accuracy@5 | 0.9646 |
| cosine_accuracy@10 | 0.9899 |
| cosine_precision@1 | 0.8456 |
| cosine_precision@3 | 0.3131 |
| cosine_precision@5 | 0.1929 |
| cosine_precision@10 | 0.099 |
| cosine_recall@1 | 0.8456 |
| cosine_recall@3 | 0.9392 |
| cosine_recall@5 | 0.9646 |
| cosine_recall@10 | 0.9899 |
| cosine_ndcg@10 | 0.9201 |
| cosine_mrr@10 | 0.8976 |
| **cosine_map@100** | **0.898** |
#### Information Retrieval
* Dataset: `dim_128`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.8405 |
| cosine_accuracy@3 | 0.9418 |
| cosine_accuracy@5 | 0.9646 |
| cosine_accuracy@10 | 0.9848 |
| cosine_precision@1 | 0.8405 |
| cosine_precision@3 | 0.3139 |
| cosine_precision@5 | 0.1929 |
| cosine_precision@10 | 0.0985 |
| cosine_recall@1 | 0.8405 |
| cosine_recall@3 | 0.9418 |
| cosine_recall@5 | 0.9646 |
| cosine_recall@10 | 0.9848 |
| cosine_ndcg@10 | 0.9171 |
| cosine_mrr@10 | 0.8949 |
| **cosine_map@100** | **0.8957** |
#### Information Retrieval
* Dataset: `dim_64`
* Evaluated with [InformationRetrievalEvaluator
](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| cosine_accuracy@1 | 0.8405 |
| cosine_accuracy@3 | 0.9316 |
| cosine_accuracy@5 | 0.957 |
| cosine_accuracy@10 | 0.9823 |
| cosine_precision@1 | 0.8405 |
| cosine_precision@3 | 0.3105 |
| cosine_precision@5 | 0.1914 |
| cosine_precision@10 | 0.0982 |
| cosine_recall@1 | 0.8405 |
| cosine_recall@3 | 0.9316 |
| cosine_recall@5 | 0.957 |
| cosine_recall@10 | 0.9823 |
| cosine_ndcg@10 | 0.9153 |
| cosine_mrr@10 | 0.8935 |
| **cosine_map@100** | **0.8943** |
## Training Details
### Training Dataset
#### Unnamed Dataset
* Size: 3,550 training samples
* Columns: positive
and anchor
* Approximate statistics based on the first 1000 samples:
| | positive | anchor |
|:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details |
The total revenue for Google as of 2021 stands at approximately $181 billion, primarily driven by the performance of its advertising and cloud segments, hailing from the Information Technology sector.
| What is the total revenue of Google as of 2021?
|
| In Q4 2021, Amazon.com Inc. reported a significant increase in net income, reaching $14.3 billion, due to the surge in online shopping during the pandemic.
| What was the Net Income of Amazon.com Inc. in Q4 2021?
|
| Coca-Cola reported full-year 2021 revenue of $37.3 billion, a rise of 13% compared to $33.0 billion in 2020. This was primarily due to strong volume growth as well as improved pricing and mix.
| How did Coca-Cola's revenue performance in 2021 measure against its previous year?
|
* Loss: [MatryoshkaLoss
](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`: 10
- `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