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 +1,811 @@
+---
+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: ITEM 7. MANAGEMENT’S DISCUSSION AND ANALYSIS OF FINANCIAL CONDITION
+    AND RESULTS OF OPERATIONS The following discussion and analysis should be read
+    in conjunction with the consolidated financial statements and the related notes
+    included elsewhere in this Annual Report on Form 10-K. For further discussion
+    of our products and services, technology and competitive strengths, refer to Item
+    1- Business.
+  sentences:
+  - What was the total net automotive cash provided by investing activities in 2023?
+  - What is the purpose of the Management's Discussion and Analysis of Financial Condition
+    and Results of Operations section in the Annual Report on Form 10-K?
+  - What are the components included in the management discussion and analysis of
+    financial condition and results of operations?
+- source_sentence: Kroger is committed to maintaining a net total debt to adjusted
+    EBITDA ratio target range of 2.30 to 2.50.
+  sentences:
+  - What was the remaining available amount of the share repurchase authorization
+    as of January 29, 2023?
+  - What range does Kroger aim for its net total debt to adjusted EBITDA ratio?
+  - What was the starting wage for all entry-level positions in the U.S. as of September
+    2023?
+- source_sentence: Google Cloud operating income of $1.7 billion for 2023.
+  sentences:
+  - What was the operating income for Google Cloud in 2023?
+  - What types of products are offered in Garmin's Fitness segment?
+  - What was the net sales of the company in fiscal 2022?
+- source_sentence: The effective income tax rate for Alphabet Inc. at the end of the
+    year 2023 was 13.9%.
+  sentences:
+  - What was the percentage change in Compute & Networking revenue from fiscal year
+    2022 to 2023?
+  - What factors primarily contributed to the increase in non-interest revenues across
+    all revenue categories?
+  - What was the effective income tax rate for Alphabet Inc. at the end of the year
+    2023?
+- source_sentence: State legislation increasingly requires PBMs to conduct audits
+    of network pharmacies regarding claims submitted for payment. Non-compliance could
+    prevent the recoupment of overpaid amounts, potentially causing financial and
+    legal repercussions.
+  sentences:
+  - What are the potential consequences for a company if its PBMs fail to comply with
+    pharmacy audit regulations?
+  - What pages do the Consolidated Financial Statements and their accompanying Notes
+    and reports appear on in the document?
+  - What are the primary services provided by the company under the Xfinity, Comcast
+    Business, and Sky brands?
+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: 0.6785714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8342857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.88
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9085714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6785714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2780952380952381
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.176
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09085714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6785714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8342857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9085714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7995179593313807
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7638202947845802
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7674168947978975
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6685714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8271428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8685714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9128571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6685714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2757142857142857
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1737142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09128571428571428
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6685714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8271428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8685714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9128571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7954721927324272
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7574353741496596
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7606771546726785
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6728571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8142857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6728571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09042857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6728571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8142857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7916203877025221
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7552613378684805
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7590698804335085
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6528571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8114285714285714
+      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: 0.6528571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2704761904761904
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08885714285714286
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6528571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8114285714285714
+      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: 0.7754227314755763
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.738630385487528
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7431237490151862
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6157142857142858
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7614285714285715
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.81
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8642857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6157142857142858
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2538095238095238
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16199999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08642857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6157142857142858
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7614285714285715
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.81
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8642857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7413954849024657
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.701954648526077
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.707051130510896
+      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("gauravsirola/bge-base-financial-matryoshka-v1")
+# Run inference
+sentences = [
+    'State legislation increasingly requires PBMs to conduct audits of network pharmacies regarding claims submitted for payment. Non-compliance could prevent the recoupment of overpaid amounts, potentially causing financial and legal repercussions.',
+    'What are the potential consequences for a company if its PBMs fail to comply with pharmacy audit regulations?',
+    'What pages do the Consolidated Financial Statements and their accompanying Notes and reports appear on in the document?',
+]
+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   | 0.6786     |
+| cosine_accuracy@3   | 0.8343     |
+| cosine_accuracy@5   | 0.88       |
+| cosine_accuracy@10  | 0.9086     |
+| cosine_precision@1  | 0.6786     |
+| cosine_precision@3  | 0.2781     |
+| cosine_precision@5  | 0.176      |
+| cosine_precision@10 | 0.0909     |
+| cosine_recall@1     | 0.6786     |
+| cosine_recall@3     | 0.8343     |
+| cosine_recall@5     | 0.88       |
+| cosine_recall@10    | 0.9086     |
+| cosine_ndcg@10      | 0.7995     |
+| cosine_mrr@10       | 0.7638     |
+| **cosine_map@100**  | **0.7674** |
+
+#### 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   | 0.6686     |
+| cosine_accuracy@3   | 0.8271     |
+| cosine_accuracy@5   | 0.8686     |
+| cosine_accuracy@10  | 0.9129     |
+| cosine_precision@1  | 0.6686     |
+| cosine_precision@3  | 0.2757     |
+| cosine_precision@5  | 0.1737     |
+| cosine_precision@10 | 0.0913     |
+| cosine_recall@1     | 0.6686     |
+| cosine_recall@3     | 0.8271     |
+| cosine_recall@5     | 0.8686     |
+| cosine_recall@10    | 0.9129     |
+| cosine_ndcg@10      | 0.7955     |
+| cosine_mrr@10       | 0.7574     |
+| **cosine_map@100**  | **0.7607** |
+
+#### 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   | 0.6729     |
+| cosine_accuracy@3   | 0.8143     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9043     |
+| cosine_precision@1  | 0.6729     |
+| cosine_precision@3  | 0.2714     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0904     |
+| cosine_recall@1     | 0.6729     |
+| cosine_recall@3     | 0.8143     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9043     |
+| cosine_ndcg@10      | 0.7916     |
+| cosine_mrr@10       | 0.7553     |
+| **cosine_map@100**  | **0.7591** |
+
+#### 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   | 0.6529     |
+| cosine_accuracy@3   | 0.8114     |
+| cosine_accuracy@5   | 0.85       |
+| cosine_accuracy@10  | 0.8886     |
+| cosine_precision@1  | 0.6529     |
+| cosine_precision@3  | 0.2705     |
+| cosine_precision@5  | 0.17       |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.6529     |
+| cosine_recall@3     | 0.8114     |
+| cosine_recall@5     | 0.85       |
+| cosine_recall@10    | 0.8886     |
+| cosine_ndcg@10      | 0.7754     |
+| cosine_mrr@10       | 0.7386     |
+| **cosine_map@100**  | **0.7431** |
+
+#### 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   | 0.6157     |
+| cosine_accuracy@3   | 0.7614     |
+| cosine_accuracy@5   | 0.81       |
+| cosine_accuracy@10  | 0.8643     |
+| cosine_precision@1  | 0.6157     |
+| cosine_precision@3  | 0.2538     |
+| cosine_precision@5  | 0.162      |
+| cosine_precision@10 | 0.0864     |
+| cosine_recall@1     | 0.6157     |
+| cosine_recall@3     | 0.7614     |
+| cosine_recall@5     | 0.81       |
+| cosine_recall@10    | 0.8643     |
+| cosine_ndcg@10      | 0.7414     |
+| cosine_mrr@10       | 0.702      |
+| **cosine_map@100**  | **0.7071** |
+
+<!--
+## 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: 7 tokens</li><li>mean: 44.73 tokens</li><li>max: 301 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.57 tokens</li><li>max: 41 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                   | anchor                                                                                                                                |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Net loss was $396.6 million and $973.6 million during the years ended December 31, 2023, and December 31, 2022, respectively.</code>                                                 | <code>What was the net loss for the year ended December 31, 2022?</code>                                                              |
+  | <code>Under the 2023 IDA agreement, the service fee on client cash deposits held at the TD Depository Institutions remains at 15 basis points, as it was in the 2019 IDA agreement.</code> | <code>How much is the service fee on client cash deposits held at the TD Depository Institutions under the 2023 IDA agreement?</code> |
+  | <code>The total shareholders’ deficit is listed as $7,994.8 million in the latest financial statement.</code>                                                                              | <code>What is the total shareholder's deficit according to the latest financial statement?</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     | 1.5585        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7207                 | 0.7441                 | 0.7510                 | 0.6857                | 0.7493                 |
+| 1.6244     | 20     | 0.6691        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7392                 | 0.7564                 | 0.7601                 | 0.7006                | 0.7661                 |
+| 2.4365     | 30     | 0.4702        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7430                 | 0.7600                 | 0.7619                 | 0.7065                | 0.7685                 |
+| 3.2487     | 40     | 0.407         | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7431**             | **0.7591**             | **0.7607**             | **0.7071**            | **0.7674**             |
+
+* 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 sha256:5a67196d3011d37bc9f9afed11daca33f98d4c71379c9a611c2d4ad0770e3427
+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]"
+}