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 +1,772 @@
+---
+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:700
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: Workforce Solutions is our largest reportable segment, contributing
+    44% of total operating revenue for 2023.
+  sentences:
+  - How much did GameStop Corp's valuation allowances increase during fiscal 2022?
+  - What percentage of total operating revenue for 2023 was represented by the Workforce
+    Solutions segment?
+  - Where are the majority of NIKE's footwear and apparel products manufactured?
+- source_sentence: The effects of actual results differing from our assumptions and
+    the effects of changing assumptions are considered actuarial gains or losses.
+    We utilize a mark-to-market approach in recognizing actuarial gains or losses
+    immediately through earnings upon the annual remeasurement in the fourth quarter,
+    or on an interim basis as triggering events warrant remeasurement.
+  sentences:
+  - How are the company's postretirement benefit plan actuarial gains or losses recognized?
+  - What specific procedures did the auditors perform related to the Critical Audit
+    Matter of medical care services Incurred but not Reported (IBNR)?
+  - What strategies does the company use to manage product costs and supply?
+- source_sentence: To improve the in-store shopping experience, the company invested
+    in wayfinding signage, store refresh packages, self-service lockers, and enhanced
+    checkout areas, aiming to provide easier navigation and increased convenience.
+  sentences:
+  - What are the expectations the company has for its employees in aligning with the
+    Code of Conduct?
+  - What strategies are employed to improve the in-store shopping experience?
+  - Where does the 10-K filing direct readers for specifics on legal proceedings involving
+    the company?
+- source_sentence: In 2023, under pre-approved share repurchase programs, The Hershey
+    Company repurchased shares valued at $27.4 million.
+  sentences:
+  - What is the value of shares repurchased under the pre-approved program as stated
+    in The Hershey Company's 2023 Form 10-K, for the year 2023?
+  - What critical accounting estimates were identified as having the greatest potential
+    impact on the financial statements?
+  - What was the total net sales in fiscal 2022?
+- source_sentence: During September 2023, the Company entered into a third amended
+    and restated revolving credit agreement with Bank of America, N.A., as administrative
+    agent, swing line lender and a letter of credit issuer and lender and certain
+    other financial institutions, as lenders thereto (the 'Amended Revolving Credit
+    Agreement'), which provides the Company with commitments having a maximum aggregate
+    principal amount of $1.25 billion, effective as of September 5, 2023. The Amended
+    Revolving Credit Agreement also provides for a potential additional incremental
+    commitment increase of up to $500.0 million subject to agreement of the lenders.
+    The Amended Revolving Credit Agreement contains certain financial covenants setting
+    forth leverage and coverage requirements, and certain other limitations typical
+    of an investment grade facility, including with respect to liens, mergers and
+    incurrence of indebtedness. The Amended Revolving Credit Agreement extends through
+    September 5, 2028.
+  sentences:
+  - What constitutes the largest expense in the company's various expense categories?
+  - What is the function of the amended revolving credit agreement that the Company
+    entered into with Bank of America in September 2023?
+  - What position does Brad D. Smith currently hold?
+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: 0.6617460317460317
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7933333333333333
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8365079365079365
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8850793650793651
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6617460317460317
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2644444444444444
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1673015873015873
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08850793650793651
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6617460317460317
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7933333333333333
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8365079365079365
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8850793650793651
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7731048434378245
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.737306437389771
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7413478623467549
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.660952380952381
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7880952380952381
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8352380952380952
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8834920634920634
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.660952380952381
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2626984126984127
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16704761904761903
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08834920634920633
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.660952380952381
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7880952380952381
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8352380952380952
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8834920634920634
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7712996524525622
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7355047871000246
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7396551248138244
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6507936507936508
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7795238095238095
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.823968253968254
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.873968253968254
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6507936507936508
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2598412698412698
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16479365079365077
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08739682539682538
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6507936507936508
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7795238095238095
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.823968253968254
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.873968253968254
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7614205489576108
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7255282186948864
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.729844180658852
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6217460317460317
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7541269841269841
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7987301587301587
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8546031746031746
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6217460317460317
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25137566137566136
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15974603174603175
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08546031746031746
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6217460317460317
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7541269841269841
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7987301587301587
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8546031746031746
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7368786132926283
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6994103048626867
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.704308796361143
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.5647619047619048
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7026984126984127
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7477777777777778
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8012698412698412
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.5647619047619048
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2342328042328042
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14955555555555555
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08012698412698412
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.5647619047619048
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7026984126984127
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7477777777777778
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8012698412698412
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6817715934378692
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6436686192995734
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6495479778469232
+      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("IlhamEbdesk/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    "During September 2023, the Company entered into a third amended and restated revolving credit agreement with Bank of America, N.A., as administrative agent, swing line lender and a letter of credit issuer and lender and certain other financial institutions, as lenders thereto (the 'Amended Revolving Credit Agreement'), which provides the Company with commitments having a maximum aggregate principal amount of $1.25 billion, effective as of September 5, 2023. The Amended Revolving Credit Agreement also provides for a potential additional incremental commitment increase of up to $500.0 million subject to agreement of the lenders. The Amended Revolving Credit Agreement contains certain financial covenants setting forth leverage and coverage requirements, and certain other limitations typical of an investment grade facility, including with respect to liens, mergers and incurrence of indebtedness. The Amended Revolving Credit Agreement extends through September 5, 2028.",
+    'What is the function of the amended revolving credit agreement that the Company entered into with Bank of America in September 2023?',
+    'What position does Brad D. Smith currently hold?',
+]
+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   | 0.6617     |
+| cosine_accuracy@3   | 0.7933     |
+| cosine_accuracy@5   | 0.8365     |
+| cosine_accuracy@10  | 0.8851     |
+| cosine_precision@1  | 0.6617     |
+| cosine_precision@3  | 0.2644     |
+| cosine_precision@5  | 0.1673     |
+| cosine_precision@10 | 0.0885     |
+| cosine_recall@1     | 0.6617     |
+| cosine_recall@3     | 0.7933     |
+| cosine_recall@5     | 0.8365     |
+| cosine_recall@10    | 0.8851     |
+| cosine_ndcg@10      | 0.7731     |
+| cosine_mrr@10       | 0.7373     |
+| **cosine_map@100**  | **0.7413** |
+
+#### 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   | 0.661      |
+| cosine_accuracy@3   | 0.7881     |
+| cosine_accuracy@5   | 0.8352     |
+| cosine_accuracy@10  | 0.8835     |
+| cosine_precision@1  | 0.661      |
+| cosine_precision@3  | 0.2627     |
+| cosine_precision@5  | 0.167      |
+| cosine_precision@10 | 0.0883     |
+| cosine_recall@1     | 0.661      |
+| cosine_recall@3     | 0.7881     |
+| cosine_recall@5     | 0.8352     |
+| cosine_recall@10    | 0.8835     |
+| cosine_ndcg@10      | 0.7713     |
+| cosine_mrr@10       | 0.7355     |
+| **cosine_map@100**  | **0.7397** |
+
+#### 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   | 0.6508     |
+| cosine_accuracy@3   | 0.7795     |
+| cosine_accuracy@5   | 0.824      |
+| cosine_accuracy@10  | 0.874      |
+| cosine_precision@1  | 0.6508     |
+| cosine_precision@3  | 0.2598     |
+| cosine_precision@5  | 0.1648     |
+| cosine_precision@10 | 0.0874     |
+| cosine_recall@1     | 0.6508     |
+| cosine_recall@3     | 0.7795     |
+| cosine_recall@5     | 0.824      |
+| cosine_recall@10    | 0.874      |
+| cosine_ndcg@10      | 0.7614     |
+| cosine_mrr@10       | 0.7255     |
+| **cosine_map@100**  | **0.7298** |
+
+#### 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   | 0.6217     |
+| cosine_accuracy@3   | 0.7541     |
+| cosine_accuracy@5   | 0.7987     |
+| cosine_accuracy@10  | 0.8546     |
+| cosine_precision@1  | 0.6217     |
+| cosine_precision@3  | 0.2514     |
+| cosine_precision@5  | 0.1597     |
+| cosine_precision@10 | 0.0855     |
+| cosine_recall@1     | 0.6217     |
+| cosine_recall@3     | 0.7541     |
+| cosine_recall@5     | 0.7987     |
+| cosine_recall@10    | 0.8546     |
+| cosine_ndcg@10      | 0.7369     |
+| cosine_mrr@10       | 0.6994     |
+| **cosine_map@100**  | **0.7043** |
+
+#### 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   | 0.5648     |
+| cosine_accuracy@3   | 0.7027     |
+| cosine_accuracy@5   | 0.7478     |
+| cosine_accuracy@10  | 0.8013     |
+| cosine_precision@1  | 0.5648     |
+| cosine_precision@3  | 0.2342     |
+| cosine_precision@5  | 0.1496     |
+| cosine_precision@10 | 0.0801     |
+| cosine_recall@1     | 0.5648     |
+| cosine_recall@3     | 0.7027     |
+| cosine_recall@5     | 0.7478     |
+| cosine_recall@10    | 0.8013     |
+| cosine_ndcg@10      | 0.6818     |
+| cosine_mrr@10       | 0.6437     |
+| **cosine_map@100**  | **0.6495** |
+
+<!--
+## 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 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
+- `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 |
+|:----------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|
+| 0.7273     | 1     | 0.6707                 | 0.7045                 | 0.7171                 | 0.6067                | 0.7188                 |
+| 1.4545     | 2     | 0.6912                 | 0.7205                 | 0.7302                 | 0.6313                | 0.7327                 |
+| **2.9091** | **4** | **0.7043**             | **0.7298**             | **0.7397**             | **0.6495**            | **0.7413**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.32.1
+- 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:abba52620898479e0292699af6b62eff35f5d31a7200c08987f7d719e4bd337f
+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]"
+}