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 +1,811 @@
+---
+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: The two patent families both expire in the United States in 2029.
+  sentences:
+  - What method is used to record amortization and costs for owned content that is
+    predominantly monetized on an individual basis?
+  - What year do the patent families related to DARZALEX expire in the United States?
+  - What was the primary reason for the net cash used in investing activities in 2022?
+- source_sentence: In October 2020, Fortis Advisors LLC filed a complaint against
+    Ethicon Inc. and others in Delaware's Court of Chancery. The lawsuit alleges breach
+    of contract and fraud related to Ethicon's acquisition of Auris Health Inc. in
+    2019. The case underwent a partial dismissal in December 2021, and as of January
+    2024, the trial's decision is pending.
+  sentences:
+  - What types of payment rates are used for dialysis treatments and associated pharmaceuticals?
+  - What legal claims does Fortis Advisors LLC allege against Ethicon Inc. in the
+    lawsuit related to the acquisition of Auris Health Inc.?
+  - What were the key components of the acquisition deal between ICE and Black Knight
+    completed on September 5, 2023?
+- source_sentence: Net cash provided by operating activities was $712.2 million and
+    $223.7 million for the year ended December 31, 2023 and 2022, respectively. The
+    increase was primarily driven by timing of payments to vendors and timing of the
+    receipt of payments from our customers, as well as an increase in interest income.
+  sentences:
+  - What caused the increase in net cash provided by operating activities between
+    2022 and 2023?
+  - How long did Joanne D. Smith serve as the Vice President - Marketing at Delta?
+  - How does the management experience of Mr. Robert G. Goldstein benefit the company?
+- source_sentence: We believe that, to varying degrees, our trademarks, trade names,
+    copyrights, proprietary processes, trade secrets, trade dress, domain names and
+    similar intellectual property add significant value to our business
+  sentences:
+  - What were the net interest expense on pre-acquisition-related debt and the cost
+    associated with the extinguishment of senior notes for 2022 as part of non-GAAP
+    adjustments?
+  - How did the fluctuation in foreign currency exchange rates impact the consolidated
+    net operating revenues in 2023?
+  - What does the company believe adds significant value to its business regarding
+    intellectual property?
+- source_sentence: The consolidated financial statements are incorporated by reference
+    in the Annual Report on Form 10-K, indicating they are treated as part of the
+    document for legal and reporting purposes.
+  sentences:
+  - What does it mean for financial statements to be incorporated by reference?
+  - What is contained within the pages 163-309 of the financial section?
+  - What were the key business segments of The Goldman Sachs Group, Inc. as reported
+    in their 2023 financial disclosures?
+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: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8714285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9028571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17428571428571427
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09028571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8714285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9028571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8043195367351605
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7724552154195008
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7766441682397275
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8328571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2776190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17371428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09042857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8328571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.804097602951568
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.771829365079365
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7756860707173107
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8214285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8557142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.89
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27380952380952384
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17114285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08899999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8214285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8557142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.89
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7977242461477416
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7678412698412698
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7726663884946474
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6785714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8257142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8528571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8857142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6785714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2752380952380953
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17057142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08857142857142856
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6785714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8257142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8528571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8857142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7864311013349103
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.754115079365079
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7585731100549844
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6642857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7828571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8157142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8642857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6642857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26095238095238094
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16314285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08642857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6642857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7828571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8157142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8642857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7634746514041137
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7313633786848066
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7360563668571922
+      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("Yohhei/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'The consolidated financial statements are incorporated by reference in the Annual Report on Form 10-K, indicating they are treated as part of the document for legal and reporting purposes.',
+    'What does it mean for financial statements to be incorporated by reference?',
+    'What is contained within the pages 163-309 of the financial section?',
+]
+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   | 0.7014     |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.8714     |
+| cosine_accuracy@10  | 0.9029     |
+| cosine_precision@1  | 0.7014     |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.1743     |
+| cosine_precision@10 | 0.0903     |
+| cosine_recall@1     | 0.7014     |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.8714     |
+| cosine_recall@10    | 0.9029     |
+| cosine_ndcg@10      | 0.8043     |
+| cosine_mrr@10       | 0.7725     |
+| **cosine_map@100**  | **0.7766** |
+
+#### 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   | 0.7        |
+| cosine_accuracy@3   | 0.8329     |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9043     |
+| cosine_precision@1  | 0.7        |
+| cosine_precision@3  | 0.2776     |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0904     |
+| cosine_recall@1     | 0.7        |
+| cosine_recall@3     | 0.8329     |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9043     |
+| cosine_ndcg@10      | 0.8041     |
+| cosine_mrr@10       | 0.7718     |
+| **cosine_map@100**  | **0.7757** |
+
+#### 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   | 0.7        |
+| cosine_accuracy@3   | 0.8214     |
+| cosine_accuracy@5   | 0.8557     |
+| cosine_accuracy@10  | 0.89       |
+| cosine_precision@1  | 0.7        |
+| cosine_precision@3  | 0.2738     |
+| cosine_precision@5  | 0.1711     |
+| cosine_precision@10 | 0.089      |
+| cosine_recall@1     | 0.7        |
+| cosine_recall@3     | 0.8214     |
+| cosine_recall@5     | 0.8557     |
+| cosine_recall@10    | 0.89       |
+| cosine_ndcg@10      | 0.7977     |
+| cosine_mrr@10       | 0.7678     |
+| **cosine_map@100**  | **0.7727** |
+
+#### 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   | 0.6786     |
+| cosine_accuracy@3   | 0.8257     |
+| cosine_accuracy@5   | 0.8529     |
+| cosine_accuracy@10  | 0.8857     |
+| cosine_precision@1  | 0.6786     |
+| cosine_precision@3  | 0.2752     |
+| cosine_precision@5  | 0.1706     |
+| cosine_precision@10 | 0.0886     |
+| cosine_recall@1     | 0.6786     |
+| cosine_recall@3     | 0.8257     |
+| cosine_recall@5     | 0.8529     |
+| cosine_recall@10    | 0.8857     |
+| cosine_ndcg@10      | 0.7864     |
+| cosine_mrr@10       | 0.7541     |
+| **cosine_map@100**  | **0.7586** |
+
+#### 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   | 0.6643     |
+| cosine_accuracy@3   | 0.7829     |
+| cosine_accuracy@5   | 0.8157     |
+| cosine_accuracy@10  | 0.8643     |
+| cosine_precision@1  | 0.6643     |
+| cosine_precision@3  | 0.261      |
+| cosine_precision@5  | 0.1631     |
+| cosine_precision@10 | 0.0864     |
+| cosine_recall@1     | 0.6643     |
+| cosine_recall@3     | 0.7829     |
+| cosine_recall@5     | 0.8157     |
+| cosine_recall@10    | 0.8643     |
+| cosine_ndcg@10      | 0.7635     |
+| cosine_mrr@10       | 0.7314     |
+| **cosine_map@100**  | **0.7361** |
+
+<!--
+## 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: 8 tokens</li><li>mean: 45.16 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.44 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                      | anchor                                                                                                                                             |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Highlights during fiscal year 2023 include the following: We generated $18,085 million of cash from operations.</code>                                                                                                                                                                                                                  | <code>What was the amount of cash generated from operations by the company in fiscal year 2023?</code>                                             |
+  | <code>U.S. government and agency securities | $ | 7,950 | | $ | (336 | ) | $ | 45,273 | $ | (3,534 | ) | $ | 53,223 | $ | (3,870 | )</code>                                                                                                                                                                                                   | <code>How much were unrealized losses on U.S. government and agency securities for those held for 12 months or greater as of June 30, 2023?</code> |
+  | <code>For assets under development, assets are grouped and assessed for impairment by estimating the undiscounted cash flows, which include remaining construction costs, over the asset's remaining useful life. If cash flows do not exceed the carrying amount, impairment based on fair value versus carrying value is considered.</code> | <code>How is the impairment of assets assessed for projects still under development?</code>                                                        |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `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   | 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     | 1.5313        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7416                 | 0.7521                 | 0.7554                 | 0.7079                | 0.7609                 |
+| 1.6244     | 20     | 0.6553        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7549                 | 0.7693                 | 0.7732                 | 0.7318                | 0.7716                 |
+| 2.4365     | 30     | 0.445         | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7565                 | 0.7738                 | 0.7746                 | 0.7367                | 0.7763                 |
+| 3.2487     | 40     | 0.3917        | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7586**             | **0.7727**             | **0.7757**             | **0.7361**            | **0.7766**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.8.10
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.32.0
+- 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.*
+-->

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": "3.0.1",
+    "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:a227424bca80ecbc3f52c95f390d72b9d061205303bc0a2e52dfa169048f729a
+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]"
+}