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 +1,803 @@
+---
+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 net interest income for the first quarter of 2023 was $14,448
+    million.
+  sentences:
+  - What was the fair value of investments in fixed maturity securities at the end
+    of 2023 after a hypothetical 100 basis point increase in interest rates?
+  - What was the net interest income for the first quarter of 2023?
+  - What are the expected consequences of the EMIR 3.0 proposals for ICE Futures Europe
+    and ICE Clear Europe?
+- source_sentence: The consolidated financial statements and accompanying notes are
+    listed in Part IV, Item 15(a)(1) of the Annual Report on Form 10-K
+  sentences:
+  - What was the total amount invested in purchases from Vebu during the year ended
+    December 31, 2023?
+  - What section of the Annual Report on Form 10-K includes the consolidated financial
+    statements and accompanying notes?
+  - What is the purpose of using constant currency to measure financial performance?
+- source_sentence: Cash provided by operating activities was impacted by the provision
+    from the Tax Cuts and Jobs Act of 2017 which became effective in fiscal 2023 and
+    requires the capitalization and amortization of research and development costs.
+    The change increased our cash taxes paid in fiscal 2023.
+  sentences:
+  - How much did the provision from the Tax Cuts and Jobs Act increase the cash taxes
+    paid in fiscal 2023?
+  - What is the principal amount of debt maturing in fiscal year 2023?
+  - What is the projected increase in effective tax rate starting from fiscal 2024?
+- source_sentence: Item 8. Financial Statements and Supplementary Data.
+  sentences:
+  - How does FedEx Express primarily fulfill its jet fuel needs?
+  - What legislative act in the United States established a new corporate alternative
+    minimum tax of 15% on large corporations?
+  - What is the title of Item 8 that covers financial data in the report?
+- source_sentence: Electronic Arts paid cash dividends totaling $210 million during
+    the fiscal year ended March 31, 2023.
+  sentences:
+  - What was the total cash dividend paid by Electronic Arts in the fiscal year ended
+    March 31, 2023?
+  - What was the SRO's accrued amount as a receivable for CAT implementation expenses
+    as of December 31, 2023?
+  - What percentage of our total U.S. dialysis patients in 2023 was covered under
+    some form of government-based program?
+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: 0.6842857142857143
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8128571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.86
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6842857142857143
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27095238095238094
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.172
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6842857142857143
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8128571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.86
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7929325221389678
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7588820861678003
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7629563080276819
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6857142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8585714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9057142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6857142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1717142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09057142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6857142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8585714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9057142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7963845502294126
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7614115646258502
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7648837754793252
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6771428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8042857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8571428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.89
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6771428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2680952380952381
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17142857142857137
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08899999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6771428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8042857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8571428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.89
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.784627431591255
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7506218820861676
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7549970210504993
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6614285714285715
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7957142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8271428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.88
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6614285714285715
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2652380952380952
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1654285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.088
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6614285714285715
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7957142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8271428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.88
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7728766261768507
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7384614512471652
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.74301468254304
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6128571428571429
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7628571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7957142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8471428571428572
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6128571428571429
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2542857142857143
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15914285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0847142857142857
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6128571428571429
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7628571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7957142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8471428571428572
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7315764159717033
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6946094104308389
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7001749041654559
+      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("elsayovita/bge-base-financial-matryoshka-testing")
+# Run inference
+sentences = [
+    'Electronic Arts paid cash dividends totaling $210 million during the fiscal year ended March 31, 2023.',
+    'What was the total cash dividend paid by Electronic Arts in the fiscal year ended March 31, 2023?',
+    "What was the SRO's accrued amount as a receivable for CAT implementation expenses as of December 31, 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   | 0.6843    |
+| cosine_accuracy@3   | 0.8129    |
+| cosine_accuracy@5   | 0.86      |
+| cosine_accuracy@10  | 0.8986    |
+| cosine_precision@1  | 0.6843    |
+| cosine_precision@3  | 0.271     |
+| cosine_precision@5  | 0.172     |
+| cosine_precision@10 | 0.0899    |
+| cosine_recall@1     | 0.6843    |
+| cosine_recall@3     | 0.8129    |
+| cosine_recall@5     | 0.86      |
+| cosine_recall@10    | 0.8986    |
+| cosine_ndcg@10      | 0.7929    |
+| cosine_mrr@10       | 0.7589    |
+| **cosine_map@100**  | **0.763** |
+
+#### 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   | 0.6857     |
+| cosine_accuracy@3   | 0.82       |
+| cosine_accuracy@5   | 0.8586     |
+| cosine_accuracy@10  | 0.9057     |
+| cosine_precision@1  | 0.6857     |
+| cosine_precision@3  | 0.2733     |
+| cosine_precision@5  | 0.1717     |
+| cosine_precision@10 | 0.0906     |
+| cosine_recall@1     | 0.6857     |
+| cosine_recall@3     | 0.82       |
+| cosine_recall@5     | 0.8586     |
+| cosine_recall@10    | 0.9057     |
+| cosine_ndcg@10      | 0.7964     |
+| cosine_mrr@10       | 0.7614     |
+| **cosine_map@100**  | **0.7649** |
+
+#### 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   | 0.6771    |
+| cosine_accuracy@3   | 0.8043    |
+| cosine_accuracy@5   | 0.8571    |
+| cosine_accuracy@10  | 0.89      |
+| cosine_precision@1  | 0.6771    |
+| cosine_precision@3  | 0.2681    |
+| cosine_precision@5  | 0.1714    |
+| cosine_precision@10 | 0.089     |
+| cosine_recall@1     | 0.6771    |
+| cosine_recall@3     | 0.8043    |
+| cosine_recall@5     | 0.8571    |
+| cosine_recall@10    | 0.89      |
+| cosine_ndcg@10      | 0.7846    |
+| cosine_mrr@10       | 0.7506    |
+| **cosine_map@100**  | **0.755** |
+
+#### 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   | 0.6614    |
+| cosine_accuracy@3   | 0.7957    |
+| cosine_accuracy@5   | 0.8271    |
+| cosine_accuracy@10  | 0.88      |
+| cosine_precision@1  | 0.6614    |
+| cosine_precision@3  | 0.2652    |
+| cosine_precision@5  | 0.1654    |
+| cosine_precision@10 | 0.088     |
+| cosine_recall@1     | 0.6614    |
+| cosine_recall@3     | 0.7957    |
+| cosine_recall@5     | 0.8271    |
+| cosine_recall@10    | 0.88      |
+| cosine_ndcg@10      | 0.7729    |
+| cosine_mrr@10       | 0.7385    |
+| **cosine_map@100**  | **0.743** |
+
+#### 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   | 0.6129     |
+| cosine_accuracy@3   | 0.7629     |
+| cosine_accuracy@5   | 0.7957     |
+| cosine_accuracy@10  | 0.8471     |
+| cosine_precision@1  | 0.6129     |
+| cosine_precision@3  | 0.2543     |
+| cosine_precision@5  | 0.1591     |
+| cosine_precision@10 | 0.0847     |
+| cosine_recall@1     | 0.6129     |
+| cosine_recall@3     | 0.7629     |
+| cosine_recall@5     | 0.7957     |
+| cosine_recall@10    | 0.8471     |
+| cosine_ndcg@10      | 0.7316     |
+| cosine_mrr@10       | 0.6946     |
+| **cosine_map@100**  | **0.7002** |
+
+<!--
+## 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: 46.86 tokens</li><li>max: 252 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.5 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                          | anchor                                                                                                                |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------|
+  | <code>For the year ended December 31, 2023, the average balance for savings and transaction accounts was $86,102 and the interest expense for these accounts was $3,357.</code>                   | <code>What was the average balance and interest expense for savings and transaction accounts in the year 2023?</code> |
+  | <code>Limits are used at various levels and types to manage the size of liquidity exposures, relative to acceptable risk levels according the the organization's liquidity risk tolerance.</code> | <code>What is the purpose of the liquidity risk limits used by the organization?</code>                               |
+  | <code>Value-Based Care refers to the goal of incentivizing healthcare providers to simultaneously increase quality while lowering the cost of care for patients.</code>                           | <code>What is the primary goal of value-based care according to the company?</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`: 2
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: False
+- `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`: 2
+- `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`: False
+- `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
+- `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     | 1.4746        | -                      | -                      | -                      | -                     | -                      |
+| 0.9746     | 12     | -             | 0.7378                 | 0.7470                 | 0.7589                 | 0.6941                | 0.7563                 |
+| 1.6244     | 20     | 0.6694        | -                      | -                      | -                      | -                     | -                      |
+| **1.9492** | **24** | **-**         | **0.743**              | **0.755**              | **0.7649**             | **0.7002**            | **0.763**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.4.0+cu121
+- Accelerate: 0.32.1
+- 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": "4.42.4",
+  "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": "4.42.4",
+    "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 sha256:64e95119c7856c50b967dbd07dd458726fe0d01d49b5689025300fdd0b01cb74
+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]"
+}