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 +1,816 @@
+---
+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: As of December 31, 2023, deferred revenues for unsatisfied performance
+    obligations consisted of $769 million related to Hilton Honors that will be recognized
+    as revenue over approximately the next two years.
+  sentences:
+  - How many shares of common stock were issued in both 2022 and 2023?
+  - What is the projected timeline for recognizing revenue from deferred revenues
+    related to Hilton Honors as of December 31, 2023?
+  - What acquisitions did CVS Health Corporation complete in 2023 to enhance their
+    care delivery strategy?
+- source_sentence: If a good or service does not qualify as distinct, it is combined
+    with the other non-distinct goods or services within the arrangement and these
+    combined goods or services are treated as a single performance obligation for
+    accounting purposes. The arrangement's transaction price is then allocated to
+    each performance obligation based on the relative standalone selling price of
+    each performance obligation.
+  sentences:
+  - What does the summary table indicate about the company's activities at the end
+    of 2023?
+  - What governs the treatment of goods or services that are not distinct within a
+    contractual arrangement?
+  - What is the basis for the Company to determine the Standalone Selling Price (SSP)
+    for each distinct performance obligation in contracts with multiple performance
+    obligations?
+- source_sentence: As of January 2023, the maximum daily borrowing capacity under
+    the commercial paper program was approximately $2.75 billion.
+  sentences:
+  - What is the maximum daily borrowing capacity under the commercial paper program
+    as of January 2023?
+  - When does the Company's fiscal year end?
+  - How much cash did acquisition activities use in 2023?
+- source_sentence: Federal Home Loan Bank borrowings had an interest rate of 4.59%
+    in 2022, which increased to 5.14% in 2023.
+  sentences:
+  - By what percentage did the company's capital expenditures increase in fiscal 2023
+    compared to fiscal 2022?
+  - What is the significance of Note 13 in the context of legal proceedings described
+    in the Annual Report on Form 10-K?
+  - How much did the Federal Home Loan Bank borrowings increase in terms of interest
+    rates from 2022 to 2023?
+- source_sentence: The design of the Annual Report, with the consolidated financial
+    statements placed immediately after Part IV, enhances the integration of financial
+    data by maintaining a coherent structure.
+  sentences:
+  - How does the structure of the Annual Report on Form 10-K facilitate the integration
+    of the consolidated financial statements?
+  - Where can one find the Glossary of Terms and Acronyms in Item 8?
+  - What part of the annual report contains the consolidated financial statements
+    and accompanying notes?
+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: 0.6957142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8171428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8628571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6957142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2723809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17257142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08999999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6957142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8171428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8628571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7971144469297426
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7641831065759639
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7681728985040082
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6942857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.81
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8514285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6942857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17028571428571426
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6942857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.81
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8514285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7951260604161544
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7617998866213151
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7658003405075238
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7971428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.85
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8885714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26571428571428574
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08885714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7971428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.85
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8885714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.793266992460996
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7629580498866213
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7678096436855835
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6957142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8014285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8357142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8842857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6957142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2671428571428571
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16714285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08842857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6957142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8014285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8357142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8842857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.787378246207931
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7566984126984126
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7613545312565108
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6571428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7871428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8285714285714286
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8757142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6571428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2623809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1657142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08757142857142856
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6571428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7871428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8285714285714286
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8757142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7655516319615892
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7303951247165531
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7349875161463472
+      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("rbhatia46/bge-base-financial-nvidia-matryoshka")
+# Run inference
+sentences = [
+    'The design of the Annual Report, with the consolidated financial statements placed immediately after Part IV, enhances the integration of financial data by maintaining a coherent structure.',
+    'How does the structure of the Annual Report on Form 10-K facilitate the integration of the consolidated financial statements?',
+    'Where can one find the Glossary of Terms and Acronyms in Item 8?',
+]
+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   | 0.6957     |
+| cosine_accuracy@3   | 0.8171     |
+| cosine_accuracy@5   | 0.8629     |
+| cosine_accuracy@10  | 0.9        |
+| cosine_precision@1  | 0.6957     |
+| cosine_precision@3  | 0.2724     |
+| cosine_precision@5  | 0.1726     |
+| cosine_precision@10 | 0.09       |
+| cosine_recall@1     | 0.6957     |
+| cosine_recall@3     | 0.8171     |
+| cosine_recall@5     | 0.8629     |
+| cosine_recall@10    | 0.9        |
+| cosine_ndcg@10      | 0.7971     |
+| cosine_mrr@10       | 0.7642     |
+| **cosine_map@100**  | **0.7682** |
+
+#### 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   | 0.6943     |
+| cosine_accuracy@3   | 0.81       |
+| cosine_accuracy@5   | 0.8514     |
+| cosine_accuracy@10  | 0.9        |
+| cosine_precision@1  | 0.6943     |
+| cosine_precision@3  | 0.27       |
+| cosine_precision@5  | 0.1703     |
+| cosine_precision@10 | 0.09       |
+| cosine_recall@1     | 0.6943     |
+| cosine_recall@3     | 0.81       |
+| cosine_recall@5     | 0.8514     |
+| cosine_recall@10    | 0.9        |
+| cosine_ndcg@10      | 0.7951     |
+| cosine_mrr@10       | 0.7618     |
+| **cosine_map@100**  | **0.7658** |
+
+#### 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   | 0.7014     |
+| cosine_accuracy@3   | 0.7971     |
+| cosine_accuracy@5   | 0.85       |
+| cosine_accuracy@10  | 0.8886     |
+| cosine_precision@1  | 0.7014     |
+| cosine_precision@3  | 0.2657     |
+| cosine_precision@5  | 0.17       |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.7014     |
+| cosine_recall@3     | 0.7971     |
+| cosine_recall@5     | 0.85       |
+| cosine_recall@10    | 0.8886     |
+| cosine_ndcg@10      | 0.7933     |
+| cosine_mrr@10       | 0.763      |
+| **cosine_map@100**  | **0.7678** |
+
+#### 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   | 0.6957     |
+| cosine_accuracy@3   | 0.8014     |
+| cosine_accuracy@5   | 0.8357     |
+| cosine_accuracy@10  | 0.8843     |
+| cosine_precision@1  | 0.6957     |
+| cosine_precision@3  | 0.2671     |
+| cosine_precision@5  | 0.1671     |
+| cosine_precision@10 | 0.0884     |
+| cosine_recall@1     | 0.6957     |
+| cosine_recall@3     | 0.8014     |
+| cosine_recall@5     | 0.8357     |
+| cosine_recall@10    | 0.8843     |
+| cosine_ndcg@10      | 0.7874     |
+| cosine_mrr@10       | 0.7567     |
+| **cosine_map@100**  | **0.7614** |
+
+#### 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   | 0.6571    |
+| cosine_accuracy@3   | 0.7871    |
+| cosine_accuracy@5   | 0.8286    |
+| cosine_accuracy@10  | 0.8757    |
+| cosine_precision@1  | 0.6571    |
+| cosine_precision@3  | 0.2624    |
+| cosine_precision@5  | 0.1657    |
+| cosine_precision@10 | 0.0876    |
+| cosine_recall@1     | 0.6571    |
+| cosine_recall@3     | 0.7871    |
+| cosine_recall@5     | 0.8286    |
+| cosine_recall@10    | 0.8757    |
+| cosine_ndcg@10      | 0.7656    |
+| cosine_mrr@10       | 0.7304    |
+| **cosine_map@100**  | **0.735** |
+
+<!--
+## 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: 6 tokens</li><li>mean: 45.53 tokens</li><li>max: 222 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.3 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                   | anchor                                                                                                         |
+  |:---------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------|
+  | <code>Acquisition activity used cash of $765 million in 2023, primarily related to a Beauty acquisition.</code>            | <code>How much cash did acquisition activities use in 2023?</code>                                             |
+  | <code>In a financial report, Part IV Item 15 includes Exhibits and Financial Statement Schedules as mentioned.</code>      | <code>What content can be expected under Part IV Item 15 in a financial report?</code>                         |
+  | <code>we had more than 8.3 million fiber consumer wireline broadband customers, adding 1.1 million during the year.</code> | <code>How many fiber consumer wireline broadband customers did the company have at the end of the year?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8122     | 10     | 1.5751        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | -                      | -                      | -                      | -                     | 0.7580                 |
+| 0.8122     | 10     | 0.6362        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7503                 | 0.7576                 | 0.7653                 | 0.7282                | 0.7638                 |
+| 1.6244     | 20     | 0.4426        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7544                 | 0.7662                 | 0.7640                 | 0.7311                | 0.7676                 |
+| 2.4365     | 30     | 0.3217        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7608                 | 0.7684                 | 0.7662                 | 0.7341                | 0.7686                 |
+| 3.2487     | 40     | 0.2761        | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7614**             | **0.7678**             | **0.7658**             | **0.735**             | **0.7682**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.6
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ee77dd85e39da697ac6ea5955d7b9021f1702b9c004a9a90d9ee3d9bde56ed
+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]"
+}