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 +1,814 @@
+---
+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: The sales contracts for Israel contain formulas that generally
+    reflect an initial base price subject to price indexation, Brent-linked or other,
+    over the life of the contract.
+  sentences:
+  - What was the change in HP's net deferred tax assets from 2022 to 2023?
+  - What are the pricing mechanisms for crude oil sales contracts in Israel?
+  - What was the total net income tax benefit HP received related to foreign tax audit
+    matters?
+- source_sentence: The FCA imposes severe penalties for the knowing and improper retention
+    of overpayments from government programs. In addition, the defendant must follow
+    certain notification and repayment processes within 60 days of identifying and
+    quantifying an overpayment.
+  sentences:
+  - What does Note 21 pertain to in this report?
+  - What types of penalties does the FCA impose for the knowing and improper retention
+    of overpayments from government payors?
+  - What impact did discrete tax items have on the tax provision in 2023 compared
+    to 2022?
+- source_sentence: The expected long-term rate of return is evaluated on an annual
+    basis. We consider a number of factors when setting assumptions with respect to
+    the long-term rate of return, including current and expected asset allocation
+    and historical and expected returns on the plan asset categories. Actual asset
+    allocations are regularly reviewed and periodically rebalanced to the targeted
+    allocations when considered appropriate.
+  sentences:
+  - How is the expected long-term rate of return on plan assets determined?
+  - What is the accumulated benefit obligation for AT&T's pension plans as of December
+    31, 2023?
+  - What is the management philosophy of Johnson & Johnson known as?
+- source_sentence: The functional currency of our foreign entities is the currency
+    of the primary economic environment in which the entity operates.
+  sentences:
+  - By what percent did Other Income (Expense) change in 2023 compared to 2022?
+  - What are the Canadian class actions against Equifax seeking in relation to the
+    2017 cybersecurity incident?
+  - What is the functional currency for a company's foreign entities?
+- source_sentence: Our products compete with other commercially available products
+    based primarily on efficacy, safety, tolerability, acceptance by doctors, ease
+    of patient compliance, ease of use, price, insurance and other reimbursement coverage,
+    distribution and marketing.
+  sentences:
+  - What are the main factors influencing competition for the company's products?
+  - What was the impact of restructuring charges in 2022 on the company and what changes
+    occurred in 2023?
+  - What are the penalties for non-compliance with Brazil's data protection laws?
+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: 0.6985714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.83
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.88
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9257142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27666666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.176
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09257142857142854
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.83
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.88
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9257142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8141629079228132
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7782318594104309
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7807867705374557
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7014285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8328571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8857142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9228571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7014285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2776190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17714285714285713
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09228571428571428
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7014285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8328571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8857142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9228571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8133531244983723
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7781366213151925
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7808747462599953
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.84
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8714285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9085714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17428571428571427
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09085714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.84
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8714285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9085714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8077154994184018
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7749937641723353
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7785241448057054
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6942857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8557142857142858
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9028571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6942857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17114285714285712
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09028571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6942857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8557142857142858
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9028571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7990640908671799
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7658554421768706
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7697199109144424
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6614285714285715
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7842857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8271428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8885714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6614285714285715
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26142857142857145
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1654285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08885714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6614285714285715
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7842857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8271428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8885714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7730930913085324
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7365589569160996
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7404183138657333
+      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("felipehsilveira/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Our products compete with other commercially available products based primarily on efficacy, safety, tolerability, acceptance by doctors, ease of patient compliance, ease of use, price, insurance and other reimbursement coverage, distribution and marketing.',
+    "What are the main factors influencing competition for the company's products?",
+    'What was the impact of restructuring charges in 2022 on the company and what changes occurred in 2023?',
+]
+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   | 0.6986     |
+| cosine_accuracy@3   | 0.83       |
+| cosine_accuracy@5   | 0.88       |
+| cosine_accuracy@10  | 0.9257     |
+| cosine_precision@1  | 0.6986     |
+| cosine_precision@3  | 0.2767     |
+| cosine_precision@5  | 0.176      |
+| cosine_precision@10 | 0.0926     |
+| cosine_recall@1     | 0.6986     |
+| cosine_recall@3     | 0.83       |
+| cosine_recall@5     | 0.88       |
+| cosine_recall@10    | 0.9257     |
+| cosine_ndcg@10      | 0.8142     |
+| cosine_mrr@10       | 0.7782     |
+| **cosine_map@100**  | **0.7808** |
+
+#### 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   | 0.7014     |
+| cosine_accuracy@3   | 0.8329     |
+| cosine_accuracy@5   | 0.8857     |
+| cosine_accuracy@10  | 0.9229     |
+| cosine_precision@1  | 0.7014     |
+| cosine_precision@3  | 0.2776     |
+| cosine_precision@5  | 0.1771     |
+| cosine_precision@10 | 0.0923     |
+| cosine_recall@1     | 0.7014     |
+| cosine_recall@3     | 0.8329     |
+| cosine_recall@5     | 0.8857     |
+| cosine_recall@10    | 0.9229     |
+| cosine_ndcg@10      | 0.8134     |
+| cosine_mrr@10       | 0.7781     |
+| **cosine_map@100**  | **0.7809** |
+
+#### 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   | 0.7        |
+| cosine_accuracy@3   | 0.84       |
+| cosine_accuracy@5   | 0.8714     |
+| cosine_accuracy@10  | 0.9086     |
+| cosine_precision@1  | 0.7        |
+| cosine_precision@3  | 0.28       |
+| cosine_precision@5  | 0.1743     |
+| cosine_precision@10 | 0.0909     |
+| cosine_recall@1     | 0.7        |
+| cosine_recall@3     | 0.84       |
+| cosine_recall@5     | 0.8714     |
+| cosine_recall@10    | 0.9086     |
+| cosine_ndcg@10      | 0.8077     |
+| cosine_mrr@10       | 0.775      |
+| **cosine_map@100**  | **0.7785** |
+
+#### 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   | 0.6943     |
+| cosine_accuracy@3   | 0.82       |
+| cosine_accuracy@5   | 0.8557     |
+| cosine_accuracy@10  | 0.9029     |
+| cosine_precision@1  | 0.6943     |
+| cosine_precision@3  | 0.2733     |
+| cosine_precision@5  | 0.1711     |
+| cosine_precision@10 | 0.0903     |
+| cosine_recall@1     | 0.6943     |
+| cosine_recall@3     | 0.82       |
+| cosine_recall@5     | 0.8557     |
+| cosine_recall@10    | 0.9029     |
+| cosine_ndcg@10      | 0.7991     |
+| cosine_mrr@10       | 0.7659     |
+| **cosine_map@100**  | **0.7697** |
+
+#### 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   | 0.6614     |
+| cosine_accuracy@3   | 0.7843     |
+| cosine_accuracy@5   | 0.8271     |
+| cosine_accuracy@10  | 0.8886     |
+| cosine_precision@1  | 0.6614     |
+| cosine_precision@3  | 0.2614     |
+| cosine_precision@5  | 0.1654     |
+| cosine_precision@10 | 0.0889     |
+| cosine_recall@1     | 0.6614     |
+| cosine_recall@3     | 0.7843     |
+| cosine_recall@5     | 0.8271     |
+| cosine_recall@10    | 0.8886     |
+| cosine_ndcg@10      | 0.7731     |
+| cosine_mrr@10       | 0.7366     |
+| **cosine_map@100**  | **0.7404** |
+
+<!--
+## 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: 45.44 tokens</li><li>max: 301 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.3 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                   | anchor                                                                                                                             |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------|
+  | <code>The Centers for Medicare & Medicaid Services issued a final rule in October 2023 for the calendar year 2024, estimating a productivity-adjusted market basket increase of 2.1% in average reimbursement to ESRD facilities.</code>                                                   | <code>What is the projected impact on average reimbursement to ESRD facilities in 2024 due to the final rule issued by CMS?</code> |
+  | <code>Company Adjusted EBIT Margin is derived by dividing the Company adjusted EBIT by Company revenue, which is a non-GAAP measure useful for evaluating the company's operating results.</code>                                                                                          | <code>How is the Company Adjusted EBIT Margin calculated?</code>                                                                   |
+  | <code>The provision for credit losses was $4 million for the year ended December 31, 202 serviLists of account holders responsible for and the state of the economy, our credit standards, our risk assessments, and the judgment of our employees responsible for granting credit.</code> | <code>What factors influence the provision for credit losses at Las Vegas Sands Corp.?</code>                                      |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `eval_use_gather_object`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step   | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.8122     | 10     | 1.5176        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7500                 | 0.7642                 | 0.7680                 | 0.7079                | 0.7708                 |
+| 1.6244     | 20     | 0.6868        | -                      | -                      | -                      | -                     | -                      |
+| 1.9492     | 24     | -             | 0.7657                 | 0.7746                 | 0.7784                 | 0.7323                | 0.7816                 |
+| 2.4365     | 30     | 0.4738        | -                      | -                      | -                      | -                     | -                      |
+| 2.9239     | 36     | -             | 0.7691                 | 0.7780                 | 0.7790                 | 0.7402                | 0.7796                 |
+| 3.2487     | 40     | 0.3934        | -                      | -                      | -                      | -                     | -                      |
+| **3.8985** | **48** | **-**         | **0.7697**             | **0.7785**             | **0.7809**             | **0.7404**            | **0.7808**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.9
+- Sentence Transformers: 3.0.1
+- Transformers: 4.44.2
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.33.0
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "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": "4.44.2",
+    "pytorch": "2.4.0+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e05458dbfbaecef6a097a69fad45a69cb2fef1d03a839ef58338dbc049b42c0
+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]"
+}