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 +1,809 @@
+---
+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: Tesla has implemented various remedial measures, including conducting
+    training and audits, and enhancements to its site waste management programs, and
+    settlement discussions are ongoing.
+  sentences:
+  - What regulatory body primarily regulates product safety, efficacy, and other aspects
+    in the U.S.?
+  - What remedial measures has Tesla implemented in response to the investigation
+    of its waste segregation practices?
+  - What were the main drivers behind the sales growth of TREMFYA?
+- source_sentence: Sales of Alphagan/Combigan in the United States decreased by 40.1%
+    from $373 million in 2021 to $121 million in 2023.
+  sentences:
+  - What were the total revenues from unaffiliated customers in 2021?
+  - What was the percentage decrease in sales for Alphagan/Combigan in the United
+    States from 2021 to 2023?
+  - What percent excess of fair value over carrying value did the Compute reporting
+    unit have as of the annual test date in 2023?
+- source_sentence: Long-lived and intangible assets are reviewed for impairment based
+    on indicators of impairment and the evaluation involves estimating the future
+    undiscounted cash flows attributable to the asset groups.
+  sentences:
+  - How are long-lived and intangible assets evaluated for impairment?
+  - What strategies are being adopted to enhance revenue through acquisition according
+    to the business plans described?
+  - How is impairment evaluated for long-lived assets such as leases, property, and
+    equipment?
+- source_sentence: Our 2023 operating income was $5.5 billion, an improvement of $1.9
+    billion compared to 2022.
+  sentences:
+  - What was the total unrecognized compensation cost related to unvested stock-based
+    awards as of October 29, 2023?
+  - What significant financial activity occurred in continuing investing activities
+    in 2023?
+  - What was the operating income for 2023, and how did it compare to 2022?
+- source_sentence: We use raw materials that are subject to price volatility caused
+    by weather, supply conditions, political and economic variables and other unpredictable
+    factors. We may use futures, options and swap contracts to manage the volatility
+    related to the above exposures.
+  sentences:
+  - What financial instruments does the company use to manage commodity price exposure?
+  - What types of legal proceedings is the company currently involved in?
+  - What was the net impact of fair value hedging instruments on earnings in 2023?
+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: 0.6814285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8614285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8942857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6814285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17228571428571426
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08942857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6814285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8614285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8942857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7922308461157294
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7589693877551015
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7633405151451278
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.68
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8214285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8614285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8957142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.68
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2738095238095238
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17228571428571426
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08957142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.68
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8214285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8614285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8957142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7914243245771438
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7576258503401355
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7617439775393929
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.69
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8571428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8928571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.69
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1714285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08928571428571426
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.69
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8571428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8928571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7943028094464931
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7623684807256232
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7661836876217925
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6657142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8042857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8457142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8871428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6657142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2680952380952381
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16914285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08871428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6657142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8042857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8457142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8871428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7784460550829944
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7434297052154194
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.74745032636981
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6342857142857142
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7771428571428571
+      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: 0.6342857142857142
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.259047619047619
+      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: 0.6342857142857142
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7771428571428571
+      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: 0.7508028784634385
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7143225623582764
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7188596090649563
+      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("korruz/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'We use raw materials that are subject to price volatility caused by weather, supply conditions, political and economic variables and other unpredictable factors. We may use futures, options and swap contracts to manage the volatility related to the above exposures.',
+    'What financial instruments does the company use to manage commodity price exposure?',
+    'What types of legal proceedings is the company currently involved in?',
+]
+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   | 0.6814     |
+| cosine_accuracy@3   | 0.82       |
+| cosine_accuracy@5   | 0.8614     |
+| cosine_accuracy@10  | 0.8943     |
+| cosine_precision@1  | 0.6814     |
+| cosine_precision@3  | 0.2733     |
+| cosine_precision@5  | 0.1723     |
+| cosine_precision@10 | 0.0894     |
+| cosine_recall@1     | 0.6814     |
+| cosine_recall@3     | 0.82       |
+| cosine_recall@5     | 0.8614     |
+| cosine_recall@10    | 0.8943     |
+| cosine_ndcg@10      | 0.7922     |
+| cosine_mrr@10       | 0.759      |
+| **cosine_map@100**  | **0.7633** |
+
+#### 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   | 0.68       |
+| cosine_accuracy@3   | 0.8214     |
+| cosine_accuracy@5   | 0.8614     |
+| cosine_accuracy@10  | 0.8957     |
+| cosine_precision@1  | 0.68       |
+| cosine_precision@3  | 0.2738     |
+| cosine_precision@5  | 0.1723     |
+| cosine_precision@10 | 0.0896     |
+| cosine_recall@1     | 0.68       |
+| cosine_recall@3     | 0.8214     |
+| cosine_recall@5     | 0.8614     |
+| cosine_recall@10    | 0.8957     |
+| cosine_ndcg@10      | 0.7914     |
+| cosine_mrr@10       | 0.7576     |
+| **cosine_map@100**  | **0.7617** |
+
+#### 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   | 0.69       |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.8571     |
+| cosine_accuracy@10  | 0.8929     |
+| cosine_precision@1  | 0.69       |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.1714     |
+| cosine_precision@10 | 0.0893     |
+| cosine_recall@1     | 0.69       |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.8571     |
+| cosine_recall@10    | 0.8929     |
+| cosine_ndcg@10      | 0.7943     |
+| cosine_mrr@10       | 0.7624     |
+| **cosine_map@100**  | **0.7662** |
+
+#### 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   | 0.6657     |
+| cosine_accuracy@3   | 0.8043     |
+| cosine_accuracy@5   | 0.8457     |
+| cosine_accuracy@10  | 0.8871     |
+| cosine_precision@1  | 0.6657     |
+| cosine_precision@3  | 0.2681     |
+| cosine_precision@5  | 0.1691     |
+| cosine_precision@10 | 0.0887     |
+| cosine_recall@1     | 0.6657     |
+| cosine_recall@3     | 0.8043     |
+| cosine_recall@5     | 0.8457     |
+| cosine_recall@10    | 0.8871     |
+| cosine_ndcg@10      | 0.7784     |
+| cosine_mrr@10       | 0.7434     |
+| **cosine_map@100**  | **0.7475** |
+
+#### 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   | 0.6343     |
+| cosine_accuracy@3   | 0.7771     |
+| cosine_accuracy@5   | 0.8157     |
+| cosine_accuracy@10  | 0.8643     |
+| cosine_precision@1  | 0.6343     |
+| cosine_precision@3  | 0.259      |
+| cosine_precision@5  | 0.1631     |
+| cosine_precision@10 | 0.0864     |
+| cosine_recall@1     | 0.6343     |
+| cosine_recall@3     | 0.7771     |
+| cosine_recall@5     | 0.8157     |
+| cosine_recall@10    | 0.8643     |
+| cosine_ndcg@10      | 0.7508     |
+| cosine_mrr@10       | 0.7143     |
+| **cosine_map@100**  | **0.7189** |
+
+<!--
+## 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: 45.15 tokens</li><li>max: 281 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.65 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                         | anchor                                                                                                                                         |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The sale and donation transactions closed in June 2022. Total proceeds from the sale were approximately $6,300 (net of transaction and closing costs), resulting in a loss of $13,568, which was recorded in the SM&A expense caption within the Consolidated Statements of Income.</code> | <code>What were Hershey's total proceeds from the sale of a building portion in June 2022, and what was the resulting financial impact?</code> |
+  | <code>Operating income margin increased to 7.9% in fiscal 2022 compared to 6.9% in fiscal 2021.</code>                                                                                                                                                                                           | <code>What was the operating income margin for fiscal year 2022 compared to fiscal year 2021?</code>                                           |
+  | <code>iPhone® is the Company’s line of smartphones based on its iOS operating system. The iPhone line includes iPhone 15 Pro, iPhone 15, iPhone 14, iPhone 13 and iPhone SE®.</code>                                                                                                             | <code>What operating system is used for the Company's iPhone line?</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
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: 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
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.9697     | 6      | -             | 0.7248                 | 0.7459                 | 0.7534                 | 0.6859                | 0.7549                 |
+| 1.6162     | 10     | 2.3046        | -                      | -                      | -                      | -                     | -                      |
+| 1.9394     | 12     | -             | 0.7456                 | 0.7601                 | 0.7590                 | 0.7111                | 0.7599                 |
+| 2.9091     | 18     | -             | 0.7470                 | 0.7652                 | 0.7618                 | 0.7165                | 0.7622                 |
+| 3.2323     | 20     | 1.0018        | -                      | -                      | -                      | -                     | -                      |
+| **3.8788** | **24** | **-**         | **0.7475**             | **0.7662**             | **0.7617**             | **0.7189**            | **0.7633**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.0
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.33.0
+- 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 +1,32 @@
+{
+  "_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": "4.44.0",
+  "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": "4.44.0",
+    "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 sha256:06dd6de9d8abfbeed2daa12e2db63dbf785020f2efd8a33237265690e07bf96d
+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]"
+}