Add new SentenceTransformer model.

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "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 +1,818 @@
+---
+base_model: TaylorAI/bge-micro-v2
+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:11863
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: In the fiscal year 2022, the emissions were categorized into different
+    scopes, with each scope representing a specific source of emissions
+  sentences:
+  - 'Question: What is NetLink proactive in identifying to be more efficient in? '
+  - What standard is the Environment, Health, and Safety Management System (EHSMS)
+    audited to by a third-party accredited certification body at the operational assets
+    level of CLI?
+  - What do the different scopes represent in terms of emissions in the fiscal year
+    2022?
+- source_sentence: NetLink is committed to protecting the security of all information
+    and information systems, including both end-user data and corporate data. To this
+    end, management ensures that the appropriate IT policies, personal data protection
+    policy, risk mitigation strategies, cyber security programmes, systems, processes,
+    and controls are in place to protect our IT systems and confidential data
+  sentences:
+  - '"What recognition did NetLink receive in FY22?"'
+  - What measures does NetLink have in place to protect the security of all information
+    and information systems, including end-user data and corporate data?
+  - 'Question: What does Disclosure 102-10 discuss regarding the organization and
+    its supply chain?'
+- source_sentence: In the domain of economic performance, the focus is on the financial
+    health and growth of the organization, ensuring sustainable profitability and
+    value creation for stakeholders
+  sentences:
+  - What does NetLink prioritize by investing in its network to ensure reliability
+    and quality of infrastructure?
+  - What percentage of the total energy was accounted for by heat, steam, and chilled
+    water in 2021 according to the given information?
+  - What is the focus in the domain of economic performance, ensuring sustainable
+    profitability and value creation for stakeholders?
+- source_sentence: Disclosure 102-41 discusses collective bargaining agreements and
+    is found on page 98
+  sentences:
+  - What topic is discussed in Disclosure 102-41 on page 98 of the document?
+  - What was the number of cases in 2021, following a decrease from 42 cases in 2020?
+  - What type of data does GRI 101 provide in relation to connecting the nation?
+- source_sentence: Employee health and well-being has never been more topical than
+    it was in the past year. We understand that people around the world, including
+    our employees, have been increasingly exposed to factors affecting their physical
+    and mental wellbeing. We are committed to creating an environment that supports
+    our employees and ensures they feel valued and have a sense of belonging. We utilised
+  sentences:
+  - What aspect of the standard covers the evaluation of the management approach?
+  - 'Question: What is the company''s commitment towards its employees'' health and
+    well-being based on the provided context information?'
+  - What types of skills does NetLink focus on developing through their training and
+    development opportunities for employees?
+model-index:
+- name: BGE micro v2 ESG
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 384
+      type: dim_384
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7549523729242181
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8991823316193206
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9237123830397033
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9447020146674534
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7549523729242181
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2997274438731068
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1847424766079407
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09447020146674537
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.020970899247894956
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.02497728698942558
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.025658677306658433
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.026241722629651493
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.18912117167223944
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8309359566693303
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.023120117824201005
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7496417432352693
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8958105032453848
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9187389361881481
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9417516648402596
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7496417432352693
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2986035010817949
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1837477872376296
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09417516648402599
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.020823381756535267
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.02488362509014959
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.025520526005226342
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.026159768467784998
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.188171652806899
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8261983036492017
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.022991454812532088
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7355643597740875
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8874652280198938
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9105622523813538
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9341650509989041
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7355643597740875
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2958217426732979
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1821124504762708
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09341650509989044
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.02043234332705799
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.0246518118894415
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.025293395899482058
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.02594902919441401
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.18580500893220617
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8144083444724101
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.022667974495178208
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6972098120205682
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8493635673944196
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8830818511337772
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.913175419371154
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6972098120205682
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28312118913147316
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17661637022675547
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09131754193711542
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.019366939222793565
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.023593432427622775
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.024530051420382712
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.02536598387142095
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.1787893349481174
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7792686076088251
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.021712360244980362
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 32
+      type: dim_32
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5974036921520695
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7523392059344179
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7970159318890668
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8448115990896063
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5974036921520695
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25077973531147263
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15940318637781337
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08448115990896064
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.016594547004224157
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.02089831127595606
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.022139331441362976
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.023466988863600182
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.15933281345013575
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6849689711507925
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.019142044257794796
+      name: Cosine Map@100
+---
+
+# BGE micro v2 ESG
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-v2). It maps sentences & paragraphs to a 384-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:** [TaylorAI/bge-micro-v2](https://huggingface.co/TaylorAI/bge-micro-v2) <!-- at revision 3edf6d7de0faa426b09780416fe61009f26ae589 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 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': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("elsayovita/bge-micro-v2-esg-v2")
+# Run inference
+sentences = [
+    'Employee health and well-being has never been more topical than it was in the past year. We understand that people around the world, including our employees, have been increasingly exposed to factors affecting their physical and mental wellbeing. We are committed to creating an environment that supports our employees and ensures they feel valued and have a sense of belonging. We utilised',
+    "Question: What is the company's commitment towards its employees' health and well-being based on the provided context information?",
+    'What types of skills does NetLink focus on developing through their training and development opportunities for employees?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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_384`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.755      |
+| cosine_accuracy@3   | 0.8992     |
+| cosine_accuracy@5   | 0.9237     |
+| cosine_accuracy@10  | 0.9447     |
+| cosine_precision@1  | 0.755      |
+| cosine_precision@3  | 0.2997     |
+| cosine_precision@5  | 0.1847     |
+| cosine_precision@10 | 0.0945     |
+| cosine_recall@1     | 0.021      |
+| cosine_recall@3     | 0.025      |
+| cosine_recall@5     | 0.0257     |
+| cosine_recall@10    | 0.0262     |
+| cosine_ndcg@10      | 0.1891     |
+| cosine_mrr@10       | 0.8309     |
+| **cosine_map@100**  | **0.0231** |
+
+#### 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   | 0.7496    |
+| cosine_accuracy@3   | 0.8958    |
+| cosine_accuracy@5   | 0.9187    |
+| cosine_accuracy@10  | 0.9418    |
+| cosine_precision@1  | 0.7496    |
+| cosine_precision@3  | 0.2986    |
+| cosine_precision@5  | 0.1837    |
+| cosine_precision@10 | 0.0942    |
+| cosine_recall@1     | 0.0208    |
+| cosine_recall@3     | 0.0249    |
+| cosine_recall@5     | 0.0255    |
+| cosine_recall@10    | 0.0262    |
+| cosine_ndcg@10      | 0.1882    |
+| cosine_mrr@10       | 0.8262    |
+| **cosine_map@100**  | **0.023** |
+
+#### 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   | 0.7356     |
+| cosine_accuracy@3   | 0.8875     |
+| cosine_accuracy@5   | 0.9106     |
+| cosine_accuracy@10  | 0.9342     |
+| cosine_precision@1  | 0.7356     |
+| cosine_precision@3  | 0.2958     |
+| cosine_precision@5  | 0.1821     |
+| cosine_precision@10 | 0.0934     |
+| cosine_recall@1     | 0.0204     |
+| cosine_recall@3     | 0.0247     |
+| cosine_recall@5     | 0.0253     |
+| cosine_recall@10    | 0.0259     |
+| cosine_ndcg@10      | 0.1858     |
+| cosine_mrr@10       | 0.8144     |
+| **cosine_map@100**  | **0.0227** |
+
+#### 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   | 0.6972     |
+| cosine_accuracy@3   | 0.8494     |
+| cosine_accuracy@5   | 0.8831     |
+| cosine_accuracy@10  | 0.9132     |
+| cosine_precision@1  | 0.6972     |
+| cosine_precision@3  | 0.2831     |
+| cosine_precision@5  | 0.1766     |
+| cosine_precision@10 | 0.0913     |
+| cosine_recall@1     | 0.0194     |
+| cosine_recall@3     | 0.0236     |
+| cosine_recall@5     | 0.0245     |
+| cosine_recall@10    | 0.0254     |
+| cosine_ndcg@10      | 0.1788     |
+| cosine_mrr@10       | 0.7793     |
+| **cosine_map@100**  | **0.0217** |
+
+#### Information Retrieval
+* Dataset: `dim_32`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.5974     |
+| cosine_accuracy@3   | 0.7523     |
+| cosine_accuracy@5   | 0.797      |
+| cosine_accuracy@10  | 0.8448     |
+| cosine_precision@1  | 0.5974     |
+| cosine_precision@3  | 0.2508     |
+| cosine_precision@5  | 0.1594     |
+| cosine_precision@10 | 0.0845     |
+| cosine_recall@1     | 0.0166     |
+| cosine_recall@3     | 0.0209     |
+| cosine_recall@5     | 0.0221     |
+| cosine_recall@10    | 0.0235     |
+| cosine_ndcg@10      | 0.1593     |
+| cosine_mrr@10       | 0.685      |
+| **cosine_map@100**  | **0.0191** |
+
+<!--
+## 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: 11,863 training samples
+* Columns: <code>context</code> and <code>question</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | context                                                                             | question                                                                          |
+  |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                            |
+  | details | <ul><li>min: 13 tokens</li><li>mean: 40.74 tokens</li><li>max: 277 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 24.4 tokens</li><li>max: 62 tokens</li></ul> |
+* Samples:
+  | context                                                                                                                                                             | question                                                                                                                                                      |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The engagement with key stakeholders involves various topics and methods throughout the year</code>                                                           | <code>Question: What does the engagement with key stakeholders involve throughout the year?</code>                                                            |
+  | <code>For unitholders and analysts, the focus is on business and operations, the release of financial results, and the overall performance and announcements</code> | <code>Question: What is the focus for unitholders and analysts in terms of business and operations, financial results, performance, and announcements?</code> |
+  | <code>These are communicated through press releases and other required disclosures via SGXNet and NetLink's website</code>                                          | <code>What platform is used to communicate press releases and required disclosures for NetLink?</code>                                                        |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          384,
+          256,
+          128,
+          64,
+          32
+      ],
+      "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`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: 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_32_cosine_map@100 | dim_384_cosine_map@100 | dim_64_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|:---------------------:|
+| 0.4313     | 10     | 5.2501        | -                      | -                      | -                     | -                      | -                     |
+| 0.8625     | 20     | 3.4967        | -                      | -                      | -                     | -                      | -                     |
+| 1.0350     | 24     | -             | 0.0221                 | 0.0224                 | 0.0185                | 0.0226                 | 0.0210                |
+| 1.2264     | 30     | 3.1196        | -                      | -                      | -                     | -                      | -                     |
+| 1.6577     | 40     | 2.4428        | -                      | -                      | -                     | -                      | -                     |
+| 2.0458     | 49     | -             | 0.0226                 | 0.0229                 | 0.0189                | 0.0230                 | 0.0215                |
+| 2.0216     | 50     | 2.2222        | -                      | -                      | -                     | -                      | -                     |
+| 2.4528     | 60     | 2.3441        | -                      | -                      | -                     | -                      | -                     |
+| 2.8841     | 70     | 2.0096        | -                      | -                      | -                     | -                      | -                     |
+| 3.0566     | 74     | -             | 0.0227                 | 0.0230                 | 0.0191                | 0.0231                 | 0.0217                |
+| 3.2480     | 80     | 2.3019        | -                      | -                      | -                     | -                      | -                     |
+| 3.6792     | 90     | 1.9538        | -                      | -                      | -                     | -                      | -                     |
+| **3.7655** | **92** | **-**         | **0.0227**             | **0.023**              | **0.0191**            | **0.0231**             | **0.0217**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.21.0
+- 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 +1,31 @@
+{
+  "_name_or_path": "TaylorAI/bge-micro-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "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": "4.42.4",
+    "pytorch": "2.4.0+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 sha256:702b99b04e570422feb4a5884e8062bd9c9e51b450ab5f62bdc3bed3751c4557
+size 69565312

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "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 +1,71 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}