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 +1,807 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+datasets: []
+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
+widget:
+- source_sentence: FedEx supports the mental health and well-being of its employees
+    and their household members by providing 24/7 confidential counseling services
+    and frequently communicating with employees on how to access these resources,
+    with an increased focus on mental health resources in recent years.
+  sentences:
+  - What are some of the key elements that management considers when making critical
+    accounting estimates for Garmin?
+  - How does FedEx support the mental health and well-being of its employees and their
+    household members?
+  - What was AbbVie's strategy for achieving its financial performance in 2023?
+- source_sentence: Our tax returns are routinely audited and settlements of issues
+    raised in these audits sometimes affect our tax provisions.
+  sentences:
+  - What was the total long-term debt, including the current portion, for AbbVie as
+    of December 31, 2023?
+  - How are tax returns affecting the company's tax provisions when audited?
+  - What are the effective dates for the main provisions and additional data collection
+    and reporting requirements of the final rule impacting AENB's compliance obligations?
+- source_sentence: In 2023, Machinery, Energy & Transportation held cash and cash
+    equivalents amounting to $6,106 million, compared to $6,042 million in 2022.
+  sentences:
+  - How much cash and cash equivalents did Machinery, Energy & Transportation hold
+    in 2023 compared to 2022?
+  - As of the report's date, how does the company view the necessity of disclosing
+    pending legal proceedings?
+  - What strategies does the company use to mitigate increasing shipping costs?
+- source_sentence: As of December 31, 2023, the total amortized cost, net of valuation
+    allowance, for non-U.S. government securities amounted to $14,516 million.
+  sentences:
+  - How did the combined ratio change from 2022 to 2023?
+  - What changes occurred in the valuation of equity warrants from 2021 to 2023?
+  - What was the total amortized cost, net of valuation allowance, for non-U.S. government
+    securities as of December 31, 2023?
+- source_sentence: Personal Systems net revenue was $35,684 million for the fiscal
+    year 2023.
+  sentences:
+  - What was the total net revenue for the Personal Systems segment in the fiscal
+    year 2023?
+  - What are the revised maximum leverage ratios under the Senior Credit Facilities
+    for the periods specified and in connection with certain material acquisitions?
+  - What was the total net sales for the Dollar Tree segment in the year ended January
+    28, 2023?
+pipeline_tag: sentence-similarity
+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: 0.7071428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8285714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8657142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7071428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27619047619047615
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17314285714285713
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09042857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7071428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8285714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8657142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8089576129709927
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7781173469387753
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7818167550402533
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8357142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8671428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9114285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2785714285714286
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1734285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09114285714285712
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8357142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8671428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9114285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8092516903954083
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7763032879818597
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7797147792125239
+      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: 0.8357142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8628571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9014285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7028571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2785714285714286
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17257142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09014285714285714
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7028571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8357142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8628571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9014285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8068517806127258
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7762273242630382
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7800735216126475
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.69
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8171428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8457142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8971428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.69
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2723809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16914285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0897142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.69
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8171428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8457142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8971428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7940646861464341
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7611541950113375
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7650200641460506
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6428571428571429
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7785714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.82
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.86
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6428571428571429
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2595238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16399999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.086
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6428571428571429
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7785714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.82
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.86
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7522449699920628
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7175958049886619
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7226733508592172
+      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("Nishanth7803/bge-base-finetuned-financial")
+# Run inference
+sentences = [
+    'Personal Systems net revenue was $35,684 million for the fiscal year 2023.',
+    'What was the total net revenue for the Personal Systems segment in the fiscal year 2023?',
+    'What are the revised maximum leverage ratios under the Senior Credit Facilities for the periods specified and in connection with certain material acquisitions?',
+]
+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   | 0.7071     |
+| cosine_accuracy@3   | 0.8286     |
+| cosine_accuracy@5   | 0.8657     |
+| cosine_accuracy@10  | 0.9043     |
+| cosine_precision@1  | 0.7071     |
+| cosine_precision@3  | 0.2762     |
+| cosine_precision@5  | 0.1731     |
+| cosine_precision@10 | 0.0904     |
+| cosine_recall@1     | 0.7071     |
+| cosine_recall@3     | 0.8286     |
+| cosine_recall@5     | 0.8657     |
+| cosine_recall@10    | 0.9043     |
+| cosine_ndcg@10      | 0.809      |
+| cosine_mrr@10       | 0.7781     |
+| **cosine_map@100**  | **0.7818** |
+
+#### Information Retrieval
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.7        |
+| cosine_accuracy@3   | 0.8357     |
+| cosine_accuracy@5   | 0.8671     |
+| cosine_accuracy@10  | 0.9114     |
+| cosine_precision@1  | 0.7        |
+| cosine_precision@3  | 0.2786     |
+| cosine_precision@5  | 0.1734     |
+| cosine_precision@10 | 0.0911     |
+| cosine_recall@1     | 0.7        |
+| cosine_recall@3     | 0.8357     |
+| cosine_recall@5     | 0.8671     |
+| cosine_recall@10    | 0.9114     |
+| cosine_ndcg@10      | 0.8093     |
+| cosine_mrr@10       | 0.7763     |
+| **cosine_map@100**  | **0.7797** |
+
+#### 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   | 0.8357     |
+| cosine_accuracy@5   | 0.8629     |
+| cosine_accuracy@10  | 0.9014     |
+| cosine_precision@1  | 0.7029     |
+| cosine_precision@3  | 0.2786     |
+| cosine_precision@5  | 0.1726     |
+| cosine_precision@10 | 0.0901     |
+| cosine_recall@1     | 0.7029     |
+| cosine_recall@3     | 0.8357     |
+| cosine_recall@5     | 0.8629     |
+| cosine_recall@10    | 0.9014     |
+| cosine_ndcg@10      | 0.8069     |
+| cosine_mrr@10       | 0.7762     |
+| **cosine_map@100**  | **0.7801** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.69      |
+| cosine_accuracy@3   | 0.8171    |
+| cosine_accuracy@5   | 0.8457    |
+| cosine_accuracy@10  | 0.8971    |
+| cosine_precision@1  | 0.69      |
+| cosine_precision@3  | 0.2724    |
+| cosine_precision@5  | 0.1691    |
+| cosine_precision@10 | 0.0897    |
+| cosine_recall@1     | 0.69      |
+| cosine_recall@3     | 0.8171    |
+| cosine_recall@5     | 0.8457    |
+| cosine_recall@10    | 0.8971    |
+| cosine_ndcg@10      | 0.7941    |
+| cosine_mrr@10       | 0.7612    |
+| **cosine_map@100**  | **0.765** |
+
+#### 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   | 0.6429     |
+| cosine_accuracy@3   | 0.7786     |
+| cosine_accuracy@5   | 0.82       |
+| cosine_accuracy@10  | 0.86       |
+| cosine_precision@1  | 0.6429     |
+| cosine_precision@3  | 0.2595     |
+| cosine_precision@5  | 0.164      |
+| cosine_precision@10 | 0.086      |
+| cosine_recall@1     | 0.6429     |
+| cosine_recall@3     | 0.7786     |
+| cosine_recall@5     | 0.82       |
+| cosine_recall@10    | 0.86       |
+| cosine_ndcg@10      | 0.7522     |
+| cosine_mrr@10       | 0.7176     |
+| **cosine_map@100**  | **0.7227** |
+
+<!--
+## 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: 46.23 tokens</li><li>max: 289 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.38 tokens</li><li>max: 41 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                            | anchor                                                                                                                      |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------|
+  | <code>In addition, most group health plans and issuers of group or individual health insurance coverage are required to disclose personalized pricing information to their participants, beneficiaries, and enrollees through an online consumer tool, by phone, or in paper form, upon request. Cost estimates must be provided in real-time based on cost-sharing information that is accurate at the time of the request.</code> | <code>What are the requirements for health insurers and group health plans in providing cost estimates to consumers?</code> |
+  | <code>Gross profit energy generation and storage segment | $ | 1,141</code>                                                                                                                                                                                                                                                                                                                                                         | <code>What was the gross profit of the energy generation and storage segment in the year ended December 31, 2023?</code>    |
+  | <code>In addition, eBay authenticates eligible luxury and collectible items in five categories through “Authenticity Guarantee”, an independent authentication service available in the United States, the United Kingdom, Germany, Australia and Canada.</code>                                                                                                                                                                    | <code>What does eBay's Authenticity Guarantee service offer?</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
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8122     | 10     | 1.5914        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7520                 | 0.7713                 | 0.7706                 | 0.6969                | 0.7753                 |
+| 1.6244     | 20     | 0.6901        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7616                 | 0.7821                 | 0.7799                 | 0.7173                | 0.7795                 |
+| 2.4365     | 30     | 0.4967        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7643                 | 0.7815                 | 0.7801                 | 0.7219                | 0.7817                 |
+| 3.2487     | 40     | 0.3894        | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.765**              | **0.7801**             | **0.7797**             | **0.7227**            | **0.7818**             |
+
+* 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: 0.31.0
+- Datasets: 2.19.2
+- 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:df93bb31149afb125a9df3140e97ced89e6e855e743858bb2b38b86a2fb1f899
+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]"
+}