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 +1,806 @@
+---
+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:9600
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: The median home value in San Carlos, CA is $2,350,000.
+  sentences:
+  - What does the console property of the WorkerGlobalScope interface provide access
+    to?
+  - What is the last sold price and date for the property at 4372 W 14th Street Dr,
+    Greeley, CO 80634?
+  - What is the median home value in San Carlos, CA?
+- source_sentence: The four new principals hired by Superintendent of Schools Ken
+    Kenworthy for the Okeechobee school system are Joseph Stanley at Central Elementary,
+    Jody Hays at Yearling Middle School, Tuuli Robinson at North Elementary, and Dr.
+    Thelma Jackson at Seminole Elementary School.
+  sentences:
+  - Who won the gold medal in the men's 1,500m final at the speed skating World Cup?
+  - What is the purpose of the 1,2,3 bowling activity for toddlers?
+  - Who are the four new principals hired by Superintendent of Schools Ken Kenworthy
+    for the Okeechobee school system?
+- source_sentence: Twitter Audit is used to scan your followers and find out what
+    percentage of them are real people.
+  sentences:
+  - What is the main product discussed in the context of fair trade?
+  - What is the software mentioned in the context suitable for?
+  - What is the purpose of the Twitter Audit tool?
+- source_sentence: Michael Czysz made the 2011 E1pc lighter and more powerful than
+    the 2010 version, and also improved the software controlling the bike’s D1g1tal
+    powertrain.
+  sentences:
+  - What changes did Michael Czysz make to the 2011 E1pc compared to the 2010 version?
+  - What is the author's suggestion for leaving a legacy for future generations?
+  - What is the most affordable and reliable option to fix a MacBook according to
+    the technician?
+- source_sentence: HTC called the Samsung Galaxy S4 “mainstream”.
+  sentences:
+  - What is the essential aspect of the vocation to marriage according to Benedict
+    XVI's message on the 40th Anniversary of Humanae Vitae?
+  - What did HTC announce about the Samsung Galaxy S4?
+  - What was Allan Cox's First Class Delivery launched on for his Level 1 certification
+    flight?
+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: 0.9675
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9791666666666666
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9829166666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.98875
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9675
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3263888888888889
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1965833333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09887499999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9675
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9791666666666666
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9829166666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.98875
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9776735843960416
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9741727843915341
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.974471752833939
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9641666666666666
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9775
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9816666666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.98875
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9641666666666666
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3258333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1963333333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09887499999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9641666666666666
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9775
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9816666666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.98875
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9758504869144781
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9717977843915344
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9720465527215371
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9620833333333333
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9741666666666666
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9804166666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.98625
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9620833333333333
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.32472222222222225
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1960833333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09862499999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9620833333333333
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9741666666666666
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9804166666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.98625
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9737941784937224
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9698406084656085
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9702070899963996
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9554166666666667
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.97
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9766666666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.98375
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9554166666666667
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3233333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1953333333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09837499999999999
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9554166666666667
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.97
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9766666666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.98375
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.969307497603498
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9647410714285715
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9652034022263717
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9391666666666667
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9616666666666667
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9666666666666667
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9758333333333333
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9391666666666667
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3205555555555556
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1933333333333333
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09758333333333333
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9391666666666667
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9616666666666667
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9666666666666667
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9758333333333333
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9577277779716886
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9519417989417989
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9525399354798056
+      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("juanpablomesa/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'HTC called the Samsung Galaxy S4 “mainstream”.',
+    'What did HTC announce about the Samsung Galaxy S4?',
+    "What is the essential aspect of the vocation to marriage according to Benedict XVI's message on the 40th Anniversary of Humanae Vitae?",
+]
+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   | 0.9675     |
+| cosine_accuracy@3   | 0.9792     |
+| cosine_accuracy@5   | 0.9829     |
+| cosine_accuracy@10  | 0.9888     |
+| cosine_precision@1  | 0.9675     |
+| cosine_precision@3  | 0.3264     |
+| cosine_precision@5  | 0.1966     |
+| cosine_precision@10 | 0.0989     |
+| cosine_recall@1     | 0.9675     |
+| cosine_recall@3     | 0.9792     |
+| cosine_recall@5     | 0.9829     |
+| cosine_recall@10    | 0.9888     |
+| cosine_ndcg@10      | 0.9777     |
+| cosine_mrr@10       | 0.9742     |
+| **cosine_map@100**  | **0.9745** |
+
+#### 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   | 0.9642    |
+| cosine_accuracy@3   | 0.9775    |
+| cosine_accuracy@5   | 0.9817    |
+| cosine_accuracy@10  | 0.9888    |
+| cosine_precision@1  | 0.9642    |
+| cosine_precision@3  | 0.3258    |
+| cosine_precision@5  | 0.1963    |
+| cosine_precision@10 | 0.0989    |
+| cosine_recall@1     | 0.9642    |
+| cosine_recall@3     | 0.9775    |
+| cosine_recall@5     | 0.9817    |
+| cosine_recall@10    | 0.9888    |
+| cosine_ndcg@10      | 0.9759    |
+| cosine_mrr@10       | 0.9718    |
+| **cosine_map@100**  | **0.972** |
+
+#### 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   | 0.9621     |
+| cosine_accuracy@3   | 0.9742     |
+| cosine_accuracy@5   | 0.9804     |
+| cosine_accuracy@10  | 0.9862     |
+| cosine_precision@1  | 0.9621     |
+| cosine_precision@3  | 0.3247     |
+| cosine_precision@5  | 0.1961     |
+| cosine_precision@10 | 0.0986     |
+| cosine_recall@1     | 0.9621     |
+| cosine_recall@3     | 0.9742     |
+| cosine_recall@5     | 0.9804     |
+| cosine_recall@10    | 0.9862     |
+| cosine_ndcg@10      | 0.9738     |
+| cosine_mrr@10       | 0.9698     |
+| **cosine_map@100**  | **0.9702** |
+
+#### 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   | 0.9554     |
+| cosine_accuracy@3   | 0.97       |
+| cosine_accuracy@5   | 0.9767     |
+| cosine_accuracy@10  | 0.9838     |
+| cosine_precision@1  | 0.9554     |
+| cosine_precision@3  | 0.3233     |
+| cosine_precision@5  | 0.1953     |
+| cosine_precision@10 | 0.0984     |
+| cosine_recall@1     | 0.9554     |
+| cosine_recall@3     | 0.97       |
+| cosine_recall@5     | 0.9767     |
+| cosine_recall@10    | 0.9838     |
+| cosine_ndcg@10      | 0.9693     |
+| cosine_mrr@10       | 0.9647     |
+| **cosine_map@100**  | **0.9652** |
+
+#### 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   | 0.9392     |
+| cosine_accuracy@3   | 0.9617     |
+| cosine_accuracy@5   | 0.9667     |
+| cosine_accuracy@10  | 0.9758     |
+| cosine_precision@1  | 0.9392     |
+| cosine_precision@3  | 0.3206     |
+| cosine_precision@5  | 0.1933     |
+| cosine_precision@10 | 0.0976     |
+| cosine_recall@1     | 0.9392     |
+| cosine_recall@3     | 0.9617     |
+| cosine_recall@5     | 0.9667     |
+| cosine_recall@10    | 0.9758     |
+| cosine_ndcg@10      | 0.9577     |
+| cosine_mrr@10       | 0.9519     |
+| **cosine_map@100**  | **0.9525** |
+
+<!--
+## 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: 9,600 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: 3 tokens</li><li>mean: 50.19 tokens</li><li>max: 435 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 18.66 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                            | anchor                                                                                               |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------|
+  | <code>The Berry Export Summary 2028 is a dedicated export plan for the Australian strawberry, raspberry, and blackberry industries. It maps the sectors’ current position, where they want to be, high-opportunity markets, and next steps. The purpose of this plan is to grow their global presence over the next 10 years.</code>                                                                                                | <code>What is the Berry Export Summary 2028 and what is its purpose?</code>                          |
+  | <code>Benefits reported from having access to Self-supply water sources include convenience, less time spent for fetching water and access to more and better quality water. In some areas, Self-supply sources offer important added values such as water for productive use, income generation, family safety and improved food security.</code>                                                                                  | <code>What are some of the benefits reported from having access to Self-supply water sources?</code> |
+  | <code>The unique features of the Coolands for Twitter app include Real-Time updates without the need for a refresh button, Avatar Indicator which shows small avatars on the title bar for new messages, Direct Link for intuitive and convenient link opening, Smart Bookmark to easily return to previous reading position, and User Level Notification which allows customized notification settings for different users.</code> | <code>What are the unique features of the Coolands for Twitter app?</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 |
+|:--------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.5333   | 10     | 0.6065        | -                      | -                      | -                      | -                     | -                      |
+| 0.96     | 18     | -             | 0.9583                 | 0.9674                 | 0.9695                 | 0.9372                | 0.9708                 |
+| 1.0667   | 20     | 0.3313        | -                      | -                      | -                      | -                     | -                      |
+| 1.6      | 30     | 0.144         | -                      | -                      | -                      | -                     | -                      |
+| 1.9733   | 37     | -             | 0.9630                 | 0.9699                 | 0.9716                 | 0.9488                | 0.9745                 |
+| 2.1333   | 40     | 0.1317        | -                      | -                      | -                      | -                     | -                      |
+| 2.6667   | 50     | 0.0749        | -                      | -                      | -                      | -                     | -                      |
+| 2.9867   | 56     | -             | 0.9650                 | 0.9701                 | 0.9721                 | 0.9522                | 0.9747                 |
+| 3.2      | 60     | 0.088         | -                      | -                      | -                      | -                     | -                      |
+| 3.7333   | 70     | 0.0598        | -                      | -                      | -                      | -                     | -                      |
+| **3.84** | **72** | **-**         | **0.9652**             | **0.9702**             | **0.972**              | **0.9525**            | **0.9745**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.5
+- 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 sha256:28f7d007f8e0ab61c15a918b58edc7adaeb9abc74f0893704d8d842d83525358
+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]"
+}