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 +1,801 @@
+---
+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: Interest expense increased nominally by 1% from $935 million in
+    2022 to $944 million in 2023, and the change reflected only a small adjustment
+    in the financial operations.
+  sentences:
+  - What recent technological advancements has the company implemented in set-top
+    box (STB) solutions?
+  - How much did the interest expense change from 2022 to 2023?
+  - What are the conditions under which AENB is restricted from making dividend distributions
+    to TRS without OCC approval?
+- source_sentence: Our products are sold in approximately 105 countries.
+  sentences:
+  - How much were the costs related to the January 2023 restructuring plan?
+  - In how many countries are Eli Lilly and Company's products sold?
+  - What led to the 74.3% decrease in total net revenues for the Corporate and Other
+    segment in fiscal 2023 compared to fiscal 2022?
+- source_sentence: Item 8 is numbered as 39 in the document.
+  sentences:
+  - What number is associated with Item 8 in the document?
+  - What was the total amount of fixed lease payment obligations as of December 31,
+    2023?
+  - By how much would a 25 basis point increase in the expected rate of return on
+    assets (ROA) affect the 2024 Pension Expense for U.S. plans?
+- source_sentence: The Intelligent Edge business segment under the Aruba brand includes
+    a portfolio of solutions for secure edge-to-cloud connectivity, embracing work
+    from anywhere environments, mobility, and IoT device connectivity.
+  sentences:
+  - What types of wireless services does AT&T provide in Mexico?
+  - What was the approximate amount of civil penalties agreed upon in the consent
+    agreement with the EPA in November 2023?
+  - What is the focus of HPE's Intelligent Edge business segment?
+- source_sentence: As part of our solar energy system and energy storage contracts,
+    we may provide the customer with performance guarantees that commit that the underlying
+    system will meet or exceed the minimum energy generation or performance requirements
+    specified in the contract.
+  sentences:
+  - What types of guarantees does Tesla provide to its solar and energy storage customers?
+  - How many full-time employees did Microsoft report as of June 30, 2023?
+  - How are the details about the company's legal proceedings provided in the report?
+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: 0.71
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.84
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9142857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.71
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1737142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09142857142857143
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.71
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.84
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9142857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8124537511621754
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7797726757369615
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7826418437079763
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7042857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8357142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8657142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9114285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7042857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2785714285714286
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17314285714285713
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09114285714285714
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7042857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8357142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8657142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9114285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8077533543226267
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.77450283446712
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7775892822045911
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7028571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8228571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8585714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8971428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7028571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2742857142857143
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1717142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0897142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7028571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8228571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8585714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8971428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8004396670945336
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7693480725623582
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7733203320348766
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6771428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8142857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8542857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8971428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6771428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17085714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0897142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6771428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8142857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8542857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8971428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.788715031897326
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7538418367346936
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7573369186799356
+      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: 0.7814285714285715
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8128571428571428
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.86
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6642857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2604761904761905
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16257142857142853
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.086
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6642857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7814285714285715
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8128571428571428
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.86
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7600084252085629
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7282585034013601
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.733116708012112
+      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("Naruke/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'As part of our solar energy system and energy storage contracts, we may provide the customer with performance guarantees that commit that the underlying system will meet or exceed the minimum energy generation or performance requirements specified in the contract.',
+    'What types of guarantees does Tesla provide to its solar and energy storage customers?',
+    'How many full-time employees did Microsoft report as of June 30, 2023?',
+]
+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   | 0.71       |
+| cosine_accuracy@3   | 0.84       |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9143     |
+| cosine_precision@1  | 0.71       |
+| cosine_precision@3  | 0.28       |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0914     |
+| cosine_recall@1     | 0.71       |
+| cosine_recall@3     | 0.84       |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9143     |
+| cosine_ndcg@10      | 0.8125     |
+| cosine_mrr@10       | 0.7798     |
+| **cosine_map@100**  | **0.7826** |
+
+#### 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   | 0.7043     |
+| cosine_accuracy@3   | 0.8357     |
+| cosine_accuracy@5   | 0.8657     |
+| cosine_accuracy@10  | 0.9114     |
+| cosine_precision@1  | 0.7043     |
+| cosine_precision@3  | 0.2786     |
+| cosine_precision@5  | 0.1731     |
+| cosine_precision@10 | 0.0911     |
+| cosine_recall@1     | 0.7043     |
+| cosine_recall@3     | 0.8357     |
+| cosine_recall@5     | 0.8657     |
+| cosine_recall@10    | 0.9114     |
+| cosine_ndcg@10      | 0.8078     |
+| cosine_mrr@10       | 0.7745     |
+| **cosine_map@100**  | **0.7776** |
+
+#### 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   | 0.7029     |
+| cosine_accuracy@3   | 0.8229     |
+| cosine_accuracy@5   | 0.8586     |
+| cosine_accuracy@10  | 0.8971     |
+| cosine_precision@1  | 0.7029     |
+| cosine_precision@3  | 0.2743     |
+| cosine_precision@5  | 0.1717     |
+| cosine_precision@10 | 0.0897     |
+| cosine_recall@1     | 0.7029     |
+| cosine_recall@3     | 0.8229     |
+| cosine_recall@5     | 0.8586     |
+| cosine_recall@10    | 0.8971     |
+| cosine_ndcg@10      | 0.8004     |
+| cosine_mrr@10       | 0.7693     |
+| **cosine_map@100**  | **0.7733** |
+
+#### 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   | 0.6771     |
+| cosine_accuracy@3   | 0.8143     |
+| cosine_accuracy@5   | 0.8543     |
+| cosine_accuracy@10  | 0.8971     |
+| cosine_precision@1  | 0.6771     |
+| cosine_precision@3  | 0.2714     |
+| cosine_precision@5  | 0.1709     |
+| cosine_precision@10 | 0.0897     |
+| cosine_recall@1     | 0.6771     |
+| cosine_recall@3     | 0.8143     |
+| cosine_recall@5     | 0.8543     |
+| cosine_recall@10    | 0.8971     |
+| cosine_ndcg@10      | 0.7887     |
+| cosine_mrr@10       | 0.7538     |
+| **cosine_map@100**  | **0.7573** |
+
+#### 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   | 0.7814     |
+| cosine_accuracy@5   | 0.8129     |
+| cosine_accuracy@10  | 0.86       |
+| cosine_precision@1  | 0.6643     |
+| cosine_precision@3  | 0.2605     |
+| cosine_precision@5  | 0.1626     |
+| cosine_precision@10 | 0.086      |
+| cosine_recall@1     | 0.6643     |
+| cosine_recall@3     | 0.7814     |
+| cosine_recall@5     | 0.8129     |
+| cosine_recall@10    | 0.86       |
+| cosine_ndcg@10      | 0.76       |
+| cosine_mrr@10       | 0.7283     |
+| **cosine_map@100**  | **0.7331** |
+
+<!--
+## 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: 9 tokens</li><li>mean: 45.57 tokens</li><li>max: 289 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 20.32 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                 | anchor                                                                                                                                                       |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The detailed information about commitments and contingencies related to legal proceedings is included under Note 13 in Part II, Item 8 of the Annual Report.</code>                                                                                                                                                                                                                                                                                | <code>Where can detailed information about the commitments and contingencies related to legal proceedings be found in the Annual Report on Form 10-K?</code> |
+  | <code>American Express's decision to reinvest gains into its business will depend on regulatory and other approvals, consultation requirements, the execution of ancillary agreements, the cost and availability of financing for the purchaser to fund the transaction and the potential loss of key customers, vendors and other business partners and management’s decisions regarding future operations, strategies and business initiatives.</code> | <code>What factors influence American Express's decision to reinvest gains into its business?</code>                                                         |
+  | <code>Lease obligations as of June 30, 2023, related to office space and various facilities totaled $883.1 million, with lease terms ranging from one to 21 years and are mostly renewable.</code>                                                                                                                                                                                                                                                       | <code>How much were lease obligations related to office space and other facilities as of June 30, 2023, and what were the terms?</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`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 2
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: 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`: 16
+- `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`: 2
+- `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`: 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
+- `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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.4061     | 10     | 0.9835        | -                      | -                      | -                      | -                     | -                      |
+| 0.8122     | 20     | 0.4319        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 24     | -             | 0.7541                 | 0.7729                 | 0.7738                 | 0.7242                | 0.7786                 |
+| 1.2183     | 30     | 0.3599        | -                      | -                      | -                      | -                     | -                      |
+| 1.6244     | 40     | 0.2596        | -                      | -                      | -                      | -                     | -                      |
+| **1.9492** | **48** | **-**         | **0.7573**             | **0.7733**             | **0.7776**             | **0.7331**            | **0.7826**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.3.0+cu121
+- Accelerate: 0.32.1
+- 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": "4.41.2",
+  "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": "2.3.0+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 sha256:6db0fe99c8d6f5aced3b2bd1fb7f5fe5ad0447ec1a7e0383c102ac880c88d81b
+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]"
+}