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 +1,807 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+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: Chevron regularly conducts employee surveys throughout the year
+    to assess the health of the company’s culture, allowing them to gain insights
+    into employee well-being.
+  sentences:
+  - What was the net cash provided by operating activities for the year ended December
+    31, 2023?
+  - How often does Chevron conduct employee surveys to assess the health of its culture?
+  - What were the total future minimum lease payments for Comcast's operating leases
+    as of December 31, 2023?
+- source_sentence: Gross margin for the fiscal year decreased 250 basis points to
+    43.5% primarily driven by higher product costs, higher markdowns and unfavorable
+    changes in foreign currency exchange rates, partially offset by strategic pricing
+    actions.
+  sentences:
+  - How does the company maintain high standards of product quality and safety?
+  - What were the main factors that negatively impacted NIKE's gross margin in fiscal
+    2023?
+  - What was the growth rate of Visa Inc.'s commercial payments volume internationally
+    between 2021 and 2022?
+- source_sentence: Mr. Teter holds a B.S. degree in Mechanical Engineering from the
+    University of California at Davis and a J.D. degree from Stanford Law School.
+  sentences:
+  - What degrees does Timothy S. Teter hold and from which institutions?
+  - What regulations are in place in Europe regarding interactions between pharmaceutical
+    companies and physicians?
+  - What economic factors particularly affected Garmin's consumer behavior in 2023?
+- source_sentence: Our Office of Diversity, Equity and Inclusion supports our focus
+    on associate diversity, supplier diversity, and engagement with our communities.
+  sentences:
+  - What are the three segments of alcohol ready-to-drink beverages the company is
+    focusing on?
+  - How much net cash was provided by operating activities in 2023?
+  - What is the focus of The Home Depot's Office of Diversity, Equity and Inclusion?
+- source_sentence: Net cash used in financing activities totaled $2,614 in 2023, compared
+    to $4,283 in 2022.
+  sentences:
+  - What was the net cash used in financing activities in 2023 and how does it compare
+    to 2022?
+  - What are Chipotle's key strategies for business growth as discussed in their strategy?
+  - What are the primary regulatory authorities that supervise and regulate JPMorgan
+    Chase in the U.S.?
+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: 0.6971428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9057142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6971428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1737142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09057142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6971428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9057142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.803607128355984
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.770687641723356
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.77485834386751
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6957142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8228571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6957142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2742857142857143
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0904285714285714
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6957142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8228571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.802840202489837
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7701360544217687
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7744106258164117
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6871428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8185714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8528571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6871428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27285714285714285
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17057142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6871428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8185714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8528571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.795190594370522
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7619773242630383
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7664081914180308
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6685714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8128571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8428571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8942857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6685714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27095238095238094
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16857142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08942857142857143
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6685714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8128571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8428571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8942857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7840862792892018
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7486655328798184
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7527149388922518
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6471428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7828571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8242857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8685714285714285
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6471428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26095238095238094
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16485714285714284
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08685714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6471428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7828571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8242857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8685714285714285
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7601900384958588
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.725268707482993
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7302983967510448
+      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 json 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 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **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("revtestuser/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Net cash used in financing activities totaled $2,614 in 2023, compared to $4,283 in 2022.',
+    'What was the net cash used in financing activities in 2023 and how does it compare to 2022?',
+    "What are Chipotle's key strategies for business growth as discussed in their strategy?",
+]
+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   | 0.6971     |
+| cosine_accuracy@3   | 0.82       |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9057     |
+| cosine_precision@1  | 0.6971     |
+| cosine_precision@3  | 0.2733     |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0906     |
+| cosine_recall@1     | 0.6971     |
+| cosine_recall@3     | 0.82       |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9057     |
+| cosine_ndcg@10      | 0.8036     |
+| cosine_mrr@10       | 0.7707     |
+| **cosine_map@100**  | **0.7749** |
+
+#### 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   | 0.6957     |
+| cosine_accuracy@3   | 0.8229     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9043     |
+| cosine_precision@1  | 0.6957     |
+| cosine_precision@3  | 0.2743     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0904     |
+| cosine_recall@1     | 0.6957     |
+| cosine_recall@3     | 0.8229     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9043     |
+| cosine_ndcg@10      | 0.8028     |
+| cosine_mrr@10       | 0.7701     |
+| **cosine_map@100**  | **0.7744** |
+
+#### 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   | 0.6871     |
+| cosine_accuracy@3   | 0.8186     |
+| cosine_accuracy@5   | 0.8529     |
+| cosine_accuracy@10  | 0.8986     |
+| cosine_precision@1  | 0.6871     |
+| cosine_precision@3  | 0.2729     |
+| cosine_precision@5  | 0.1706     |
+| cosine_precision@10 | 0.0899     |
+| cosine_recall@1     | 0.6871     |
+| cosine_recall@3     | 0.8186     |
+| cosine_recall@5     | 0.8529     |
+| cosine_recall@10    | 0.8986     |
+| cosine_ndcg@10      | 0.7952     |
+| cosine_mrr@10       | 0.762      |
+| **cosine_map@100**  | **0.7664** |
+
+#### 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   | 0.6686     |
+| cosine_accuracy@3   | 0.8129     |
+| cosine_accuracy@5   | 0.8429     |
+| cosine_accuracy@10  | 0.8943     |
+| cosine_precision@1  | 0.6686     |
+| cosine_precision@3  | 0.271      |
+| cosine_precision@5  | 0.1686     |
+| cosine_precision@10 | 0.0894     |
+| cosine_recall@1     | 0.6686     |
+| cosine_recall@3     | 0.8129     |
+| cosine_recall@5     | 0.8429     |
+| cosine_recall@10    | 0.8943     |
+| cosine_ndcg@10      | 0.7841     |
+| cosine_mrr@10       | 0.7487     |
+| **cosine_map@100**  | **0.7527** |
+
+#### 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   | 0.6471     |
+| cosine_accuracy@3   | 0.7829     |
+| cosine_accuracy@5   | 0.8243     |
+| cosine_accuracy@10  | 0.8686     |
+| cosine_precision@1  | 0.6471     |
+| cosine_precision@3  | 0.261      |
+| cosine_precision@5  | 0.1649     |
+| cosine_precision@10 | 0.0869     |
+| cosine_recall@1     | 0.6471     |
+| cosine_recall@3     | 0.7829     |
+| cosine_recall@5     | 0.8243     |
+| cosine_recall@10    | 0.8686     |
+| cosine_ndcg@10      | 0.7602     |
+| cosine_mrr@10       | 0.7253     |
+| **cosine_map@100**  | **0.7303** |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* 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: 44.91 tokens</li><li>max: 246 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.43 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                    | anchor                                                                                                                                                                                 |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Certain provisions of the final rule become effective on April 1, 2024, but the majority of the final rule’s operative provisions (including the revisions to the definition of “limited purpose bank”) become effective on January 1, 2026, with additional data collection and reporting requirements becoming effective on January 1, 2027.</code> | <code>What are the effective dates for the main provisions and additional data collection and reporting requirements of the final rule impacting AENB's compliance obligations?</code> |
+  | <code>Our total revenue for 2023 was $134.90 billion, an increase of 16% compared to 2022.</code>                                                                                                                                                                                                                                                           | <code>What was the total revenue for the year 2023 and the percentage increase from 2022?</code>                                                                                       |
+  | <code>As of December 31, 2023, our domestic Chief Medical Officer leads a team of 22 nephrologists in our physician leadership team as part of our domestic Office of the Chief Medical Officer.</code>                                                                                                                                                     | <code>How many physicians are part of the domestic Office of the Chief Medical Officer at DaVita as of December 31, 2023?</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
+- `fp16`: True
+- `tf32`: False
+- `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`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8122     | 10     | 1.6288        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7384                 | 0.7485                 | 0.7508                 | 0.7013                | 0.7561                 |
+| 1.6244     | 20     | 0.6896        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7499                 | 0.7621                 | 0.7676                 | 0.7220                | 0.7704                 |
+| 2.4365     | 30     | 0.4965        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7529                 | 0.7669                 | 0.7739                 | 0.7302                | 0.7754                 |
+| 3.2487     | 40     | 0.415         | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7527**             | **0.7664**             | **0.7744**             | **0.7303**            | **0.7749**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.1.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.34.2
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.1.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bf6d9fb31e8bbbf008ba6482419b108bbe179611e719076e317de67ca7777f
+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]"
+}