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 +1,817 @@
+---
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+language:
+- en
+library_name: sentence-transformers
+license: apache-2.0
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: AutoZone, Inc. began operations in 1979.
+  sentences:
+  - What types of products and markets does the company cater to in the semiconductor
+    industry?
+  - When did AutoZone, Inc. begin its operations?
+  - How much did general and administrative expenses related to merger, acquisition,
+    and other costs change from 2022 to 2023?
+- source_sentence: See Note 14 to the consolidated financial statements in Item 8
+    of this Annual regarding legal proceedings.
+  sentences:
+  - What is the source to find detailed information about legal proceedings in the
+    Annual Report?
+  - Where in the Annual Report can one find a description of certain legal matters
+    and their impact on the company?
+  - What strategic actions is Hershey taking to maintain its leadership in the U.S.
+    confectionery market?
+- source_sentence: ICE Bonds focuses on increasing efficiency in fixed income markets
+    by offering electronic markets that support trading protocols including click-to-trade,
+    request for quotation (RFQ), and auctions.
+  sentences:
+  - What services does the ICE Bonds platform provide and what is its focus?
+  - What was the percentage increase in the generic dispensing rate of the Health
+    Services segment from 2022 to 2023?
+  - How many shares of Class A common stock were repurchased and retired in 2023,
+    and what was the total cost including excise tax accruals?
+- source_sentence: Subject to various United States and foreign laws and regulations,
+    including those related to intellectual property, data privacy and security, cybersecurity,
+    tax, employment, competition and antitrust, anti-corruption, anti-bribery, and
+    AI. Compliance with these laws has no current material adverse impact on capital
+    expenditures, results of operations or competitive position.
+  sentences:
+  - How much did the total loans and lending commitments amount to as of December
+    2023?
+  - What types of laws and regulations does the company need to comply with?
+  - Where are the consolidated financial statements listed in the Annual Report on
+    Form 10-K located?
+- source_sentence: CMS made significant changes to the structure of the hierarchical
+    condition category model in version 28, which may impact risk adjustment factor
+    scores for a larger percentage of Medicare Advantage beneficiaries and could result
+    in changes to beneficiary RAF scores with or without a change in the patient’s
+    health status.
+  sentences:
+  - How does Tesla reduce costs and promote renewable power at their Supercharger
+    stations?
+  - What is the primary method by which the company manages its cash, cash equivalents,
+    and marketable securities?
+  - What significant regulatory change did CMS make to the hierarchical condition
+    category model in its version 28?
+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: 0.6985714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8442857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8814285714285715
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9271428571428572
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2814285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17628571428571424
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09271428571428571
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8442857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8814285714285715
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9271428571428572
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8156553778675095
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7796054421768707
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7822282461868646
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.71
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8457142857142858
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8785714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9271428571428572
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.71
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2819047619047619
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17571428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09271428571428571
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.71
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8457142857142858
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8785714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9271428571428572
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8194766272347418
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7848673469387758
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7873446316370609
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7085714285714285
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8342857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9142857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7085714285714285
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27809523809523806
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09142857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7085714285714285
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8342857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9142857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8116052646620258
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.77881462585034
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7821002568762089
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.69
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.86
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.91
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.69
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.172
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09099999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.69
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.86
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.91
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8013750432226047
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7664954648526079
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7698726210622817
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6657142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.79
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8285714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8857142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6657142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2633333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1657142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08857142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6657142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.79
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8285714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8857142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7732501027431213
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7375017006802721
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7416822153678694
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("dpokhrel/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'CMS made significant changes to the structure of the hierarchical condition category model in version 28, which may impact risk adjustment factor scores for a larger percentage of Medicare Advantage beneficiaries and could result in changes to beneficiary RAF scores with or without a change in the patient’s health status.',
+    'What significant regulatory change did CMS make to the hierarchical condition category model in its version 28?',
+    'What is the primary method by which the company manages its cash, cash equivalents, and marketable securities?',
+]
+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   | 0.6986     |
+| cosine_accuracy@3   | 0.8443     |
+| cosine_accuracy@5   | 0.8814     |
+| cosine_accuracy@10  | 0.9271     |
+| cosine_precision@1  | 0.6986     |
+| cosine_precision@3  | 0.2814     |
+| cosine_precision@5  | 0.1763     |
+| cosine_precision@10 | 0.0927     |
+| cosine_recall@1     | 0.6986     |
+| cosine_recall@3     | 0.8443     |
+| cosine_recall@5     | 0.8814     |
+| cosine_recall@10    | 0.9271     |
+| cosine_ndcg@10      | 0.8157     |
+| cosine_mrr@10       | 0.7796     |
+| **cosine_map@100**  | **0.7822** |
+
+#### 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   | 0.71       |
+| cosine_accuracy@3   | 0.8457     |
+| cosine_accuracy@5   | 0.8786     |
+| cosine_accuracy@10  | 0.9271     |
+| cosine_precision@1  | 0.71       |
+| cosine_precision@3  | 0.2819     |
+| cosine_precision@5  | 0.1757     |
+| cosine_precision@10 | 0.0927     |
+| cosine_recall@1     | 0.71       |
+| cosine_recall@3     | 0.8457     |
+| cosine_recall@5     | 0.8786     |
+| cosine_recall@10    | 0.9271     |
+| cosine_ndcg@10      | 0.8195     |
+| cosine_mrr@10       | 0.7849     |
+| **cosine_map@100**  | **0.7873** |
+
+#### 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   | 0.7086     |
+| cosine_accuracy@3   | 0.8343     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9143     |
+| cosine_precision@1  | 0.7086     |
+| cosine_precision@3  | 0.2781     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0914     |
+| cosine_recall@1     | 0.7086     |
+| cosine_recall@3     | 0.8343     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9143     |
+| cosine_ndcg@10      | 0.8116     |
+| cosine_mrr@10       | 0.7788     |
+| **cosine_map@100**  | **0.7821** |
+
+#### 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   | 0.69       |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.86       |
+| cosine_accuracy@10  | 0.91       |
+| cosine_precision@1  | 0.69       |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.172      |
+| cosine_precision@10 | 0.091      |
+| cosine_recall@1     | 0.69       |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.86       |
+| cosine_recall@10    | 0.91       |
+| cosine_ndcg@10      | 0.8014     |
+| cosine_mrr@10       | 0.7665     |
+| **cosine_map@100**  | **0.7699** |
+
+#### 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   | 0.6657     |
+| cosine_accuracy@3   | 0.79       |
+| cosine_accuracy@5   | 0.8286     |
+| cosine_accuracy@10  | 0.8857     |
+| cosine_precision@1  | 0.6657     |
+| cosine_precision@3  | 0.2633     |
+| cosine_precision@5  | 0.1657     |
+| cosine_precision@10 | 0.0886     |
+| cosine_recall@1     | 0.6657     |
+| cosine_recall@3     | 0.79       |
+| cosine_recall@5     | 0.8286     |
+| cosine_recall@10    | 0.8857     |
+| cosine_ndcg@10      | 0.7733     |
+| cosine_mrr@10       | 0.7375     |
+| **cosine_map@100**  | **0.7417** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 6,300 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                            | anchor                                                                            |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 46.37 tokens</li><li>max: 248 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.57 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                  | anchor                                                                                                    |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------|
+  | <code>Scenario analysis is used to quantify the impact of a specified event, including how the event impacts multiple risk factors simultaneously. For example, for sovereign stress testing, it calculates potential exposure related to sovereign positions as well as the corresponding debt, equity, and currency exposures that may be impacted by sovereign distress.</code>        | <code>How does Goldman Sachs utilize scenario analysis in its risk management strategy?</code>            |
+  | <code>The company is involved in various other legal proceedings incidental to the conduct of our business, including, but not limited to, claims and allegations related to wage and hour violations, unlawful termination, employment practices, product liability, privacy and cybersecurity, environmental matters, and intellectual property rights or regulatory compliance.</code> | <code>What types of legal proceedings is the company currently involved in?</code>                        |
+  | <code>In 2023, $505 million was utilized for common stock repurchases.</code>                                                                                                                                                                                                                                                                                                             | <code>How much cash was utilized for common stock repurchases in the year ended 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
+- `bf16`: True
+- `half_precision_backend`: cpu_amp
+- `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
+- `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`: cpu_amp
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: 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     | 1.5241        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7486                 | 0.7656                 | 0.7662                 | 0.7108                | 0.7679                 |
+| 1.6244     | 20     | 0.658         | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7656                 | 0.7793                 | 0.7843                 | 0.7348                | 0.7798                 |
+| 2.4365     | 30     | 0.4743        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7683                 | 0.7814                 | 0.7859                 | 0.7400                | 0.7812                 |
+| 3.2487     | 40     | 0.4241        | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7699**             | **0.7821**             | **0.7873**             | **0.7417**            | **0.7822**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.5
+- Sentence Transformers: 3.0.1
+- Transformers: 4.43.4
+- PyTorch: 2.4.0.dev20240607+cu118
+- Accelerate: 0.32.0
+- Datasets: 2.20.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.43.4",
+    "pytorch": "2.4.0.dev20240607+cu118"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076041a1f6d0caead36542ba7d54a10391e27097e08b4fd9eff10f127a848618
+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]"
+}