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 +1,799 @@
+---
+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:196
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: The text refers to the preparation of a pre-trained model for data
+    set usage, which is a crucial step in machine learning projects. This suggests
+    that the project involves using a model that has already been trained on a dataset,
+    which can then be fine-tuned or used directly for specific tasks, potentially
+    saving time and computational resources.
+  sentences:
+  - What is the significance of preparing a pre-trained model in the data set for
+    the process described in the text?
+  - What is the purpose of the document?
+  - What are the developer AI developer's experiences in AI development and research?
+- source_sentence: The project manager has a degree from Vietnam National University
+    and has completed a Google TensorFlow certification.
+  sentences:
+  - How often are the training, evaluation, and re-training steps repeated in the
+    text?
+  - What is the project manager's educational background?
+  - What information should be shared via email when final product delivery is completed?
+- source_sentence: The text mentions that Docker for the deployment of a high NT Q
+    trained model was built between July 18 and July 19, 2024.
+  sentences:
+  - What is the role of "データベースベクトルとセマンティクス検索モジュール"?
+  - When was the Docker for the deployment of a high NT Q trained model built?
+  - What is the significance of Level 3 in the escalation process described in the
+    text?
+- source_sentence: The text spans from September 4th to October 16th, covering a total
+    of 33 days.
+  sentences:
+  - How many days are listed in the given text?
+  - How does the system support the current system and plan for future feature development?
+  - What are the two distinct products offered by NT Q?
+- source_sentence: After text generation, the process involves providing test data
+    to NT Q, which then undergoes article correction, including dealing with fragmented
+    articles and errors.
+  sentences:
+  - What is the process for providing test data to NT Q after text generation?
+  - When is the deadline for combining the API for the setting function?
+  - What is the significance of the dates in the text?
+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: 0.7755102040816326
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8775510204081632
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9591836734693877
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9795918367346939
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7755102040816326
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2925170068027211
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19183673469387752
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09795918367346937
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7755102040816326
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8775510204081632
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9591836734693877
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9795918367346939
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8776251324776435
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8447845804988664
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.846354439211582
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7959183673469388
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8979591836734694
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9591836734693877
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9795918367346939
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7959183673469388
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.29931972789115646
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19183673469387752
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09795918367346937
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7959183673469388
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8979591836734694
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9591836734693877
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9795918367346939
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.884559158446073
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8539358600583091
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8551363402503859
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6938775510204082
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9183673469387755
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9591836734693877
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9591836734693877
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6938775510204082
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3061224489795918
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19183673469387752
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09591836734693876
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6938775510204082
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9183673469387755
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9591836734693877
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9591836734693877
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8397332987260313
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7993197278911565
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8016520894071916
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6938775510204082
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9183673469387755
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9183673469387755
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9183673469387755
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6938775510204082
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3061224489795918
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1836734693877551
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09183673469387756
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6938775510204082
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9183673469387755
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9183673469387755
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9183673469387755
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8168105921282822
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7823129251700681
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7865583396195641
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5918367346938775
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7959183673469388
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8163265306122449
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9183673469387755
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5918367346938775
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26530612244897955
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16326530612244897
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09183673469387756
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5918367346938775
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7959183673469388
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8163265306122449
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9183673469387755
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7471061057082727
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6929057337220603
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6978234213668709
+      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("cngcv/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'After text generation, the process involves providing test data to NT Q, which then undergoes article correction, including dealing with fragmented articles and errors.',
+    'What is the process for providing test data to NT Q after text generation?',
+    'What is the significance of the dates in the text?',
+]
+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   | 0.7755     |
+| cosine_accuracy@3   | 0.8776     |
+| cosine_accuracy@5   | 0.9592     |
+| cosine_accuracy@10  | 0.9796     |
+| cosine_precision@1  | 0.7755     |
+| cosine_precision@3  | 0.2925     |
+| cosine_precision@5  | 0.1918     |
+| cosine_precision@10 | 0.098      |
+| cosine_recall@1     | 0.7755     |
+| cosine_recall@3     | 0.8776     |
+| cosine_recall@5     | 0.9592     |
+| cosine_recall@10    | 0.9796     |
+| cosine_ndcg@10      | 0.8776     |
+| cosine_mrr@10       | 0.8448     |
+| **cosine_map@100**  | **0.8464** |
+
+#### 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   | 0.7959     |
+| cosine_accuracy@3   | 0.898      |
+| cosine_accuracy@5   | 0.9592     |
+| cosine_accuracy@10  | 0.9796     |
+| cosine_precision@1  | 0.7959     |
+| cosine_precision@3  | 0.2993     |
+| cosine_precision@5  | 0.1918     |
+| cosine_precision@10 | 0.098      |
+| cosine_recall@1     | 0.7959     |
+| cosine_recall@3     | 0.898      |
+| cosine_recall@5     | 0.9592     |
+| cosine_recall@10    | 0.9796     |
+| cosine_ndcg@10      | 0.8846     |
+| cosine_mrr@10       | 0.8539     |
+| **cosine_map@100**  | **0.8551** |
+
+#### 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   | 0.6939     |
+| cosine_accuracy@3   | 0.9184     |
+| cosine_accuracy@5   | 0.9592     |
+| cosine_accuracy@10  | 0.9592     |
+| cosine_precision@1  | 0.6939     |
+| cosine_precision@3  | 0.3061     |
+| cosine_precision@5  | 0.1918     |
+| cosine_precision@10 | 0.0959     |
+| cosine_recall@1     | 0.6939     |
+| cosine_recall@3     | 0.9184     |
+| cosine_recall@5     | 0.9592     |
+| cosine_recall@10    | 0.9592     |
+| cosine_ndcg@10      | 0.8397     |
+| cosine_mrr@10       | 0.7993     |
+| **cosine_map@100**  | **0.8017** |
+
+#### 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   | 0.6939     |
+| cosine_accuracy@3   | 0.9184     |
+| cosine_accuracy@5   | 0.9184     |
+| cosine_accuracy@10  | 0.9184     |
+| cosine_precision@1  | 0.6939     |
+| cosine_precision@3  | 0.3061     |
+| cosine_precision@5  | 0.1837     |
+| cosine_precision@10 | 0.0918     |
+| cosine_recall@1     | 0.6939     |
+| cosine_recall@3     | 0.9184     |
+| cosine_recall@5     | 0.9184     |
+| cosine_recall@10    | 0.9184     |
+| cosine_ndcg@10      | 0.8168     |
+| cosine_mrr@10       | 0.7823     |
+| **cosine_map@100**  | **0.7866** |
+
+#### 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   | 0.5918     |
+| cosine_accuracy@3   | 0.7959     |
+| cosine_accuracy@5   | 0.8163     |
+| cosine_accuracy@10  | 0.9184     |
+| cosine_precision@1  | 0.5918     |
+| cosine_precision@3  | 0.2653     |
+| cosine_precision@5  | 0.1633     |
+| cosine_precision@10 | 0.0918     |
+| cosine_recall@1     | 0.5918     |
+| cosine_recall@3     | 0.7959     |
+| cosine_recall@5     | 0.8163     |
+| cosine_recall@10    | 0.9184     |
+| cosine_ndcg@10      | 0.7471     |
+| cosine_mrr@10       | 0.6929     |
+| **cosine_map@100**  | **0.6978** |
+
+<!--
+## 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: 196 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: 15 tokens</li><li>mean: 46.58 tokens</li><li>max: 118 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 17.25 tokens</li><li>max: 43 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                              | anchor                                                                            |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>The document lists several tasks with their statuses, such as "Done", "In progress", and "To be done". These statuses indicate the current progress of each task within the project. For example, "Set up environment" and "Set up development environment" are marked as "Done", suggesting these tasks have been completed, while "Build translation data set" is marked as "In progress", indicating it is currently being worked on.</code> | <code>What is the status of the project tasks mentioned in the document?</code>   |
+  | <code>The 'Web Application Construction' task is mentioned to be completed by NT Q, with a duration from July 17, 2023, to July 28, 2023, and is marked as 'Done' with a completion of 10 tasks.</code>                                                                                                                                                                                                                                               | <code>What is the scope of the 'Web Application Construction' task?</code>        |
+  | <code>"RE F" could potentially stand for "Reference File" or "Record File," indicating that this text might be part of a larger dataset or document used for reference or record-keeping purposes.</code>                                                                                                                                                                                                                                             | <code>What is the significance of the "RE F" at the beginning of the text?</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
+- `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`: 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`: False
+- `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  | 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 |
+|:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 1.0     | 1     | 0.6908                 | 0.7097                 | 0.8111                 | 0.6240                | 0.8011                 |
+| 2.0     | 2     | 0.7292                 | 0.7692                 | 0.8177                 | 0.6634                | 0.8162                 |
+| 3.0     | 3     | 0.7555                 | 0.8014                 | 0.8541                 | 0.6992                | 0.8451                 |
+| **4.0** | **4** | **0.7866**             | **0.8017**             | **0.8551**             | **0.6978**            | **0.8464**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.13
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.3
+- PyTorch: 2.1.2
+- Accelerate: 0.32.1
+- Datasets: 2.20.0
+- 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": "4.42.3",
+  "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": "4.42.3",
+    "pytorch": "2.1.2"
+  },
+  "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:d453a59f4a0c266f4212d3ebf209fe24ab32875765f79f071b05b617ef1f3ac3
+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]"
+}