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 +1,740 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6300
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: For example, brands based on major motion picture releases generally
+    require less advertising as a result of the promotional activities around the
+    motion picture release.
+  sentences:
+  - How many new hotels did Hilton open in the year ended December 31, 2023?
+  - What impact do major motion picture releases have on Hasbro's advertising expenditures?
+  - In which item of the report can the details of Legal proceedings be found by referencing?
+- source_sentence: Our retail stores are generally located in strip centers, shopping
+    malls and pedestrian areas...  We target strip centers that are conveniently located,
+    have a mass merchant or supermarket anchor tenant and have a high volume of customers.
+  sentences:
+  - What is the range of pages in IBM’s 2023 Annual Report to Stockholders where the
+    Financial Statements and Supplementary Data are located?
+  - How does GameStop's store location choice impact its business strategy?
+  - In which part of the financial documents can detailed information about legal
+    proceedings be found according to Item 3?
+- source_sentence: The increase in fulfillment costs in absolute dollars in 2023,
+    compared to the prior year, is primarily due to increased sales and investments
+    in our fulfillment network, partially offset by fulfillment network efficiencies.
+  sentences:
+  - What led to the increase in fulfillment costs in 2023?
+  - Where in the Form 10-K can one find Note 15 which discusses legal proceedings?
+  - What accounting method does the company use to account for investments in subsidiaries
+    and partnerships where it does not control but has significant influence?
+- source_sentence: 'In December 2023, the FASB issued ASU No. 2023-09, ‘Income Taxes
+    (Topic 740): Improvements to Income Tax Disclosures.’ The ASU includes amendments
+    requiring enhanced income tax disclosures, primarily related to standardization
+    and disaggregation of rate reconciliation categories and income taxes paid by
+    jurisdiction.'
+  sentences:
+  - What are the total noncancelable purchase commitments as of December 31, 2023,
+    and how are they distributed over different time periods?
+  - What are the primary objectives of the Company's investment policy?
+  - What are the required amendments in the ASU No. 2023-09 regarding income tax disclosures?
+- source_sentence: Income Taxes We are subject to income taxes in the U.S. and in
+    many foreign jurisdictions. Significant judgment is required in determining our
+    provision for income taxes, our deferred tax assets and liabilities and any valuation
+    allowance recorded against our net deferred tax assets that are not more likely
+    than not to be realized.
+  sentences:
+  - How does the company treat income taxes in its financial reports?
+  - How does YouTube contribute to users' experience according to the company's statement?
+  - When did The Charles Schwab Corporation change its corporate headquarters from
+    San Francisco to Westlake, Texas?
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+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
+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: 0.7028571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8185714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.85
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8914285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7028571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2728571428571428
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08914285714285713
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7028571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8185714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.85
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8914285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.798341878406338
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7685107709750566
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7724628591268551
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6985714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8157142857142857
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8528571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27190476190476187
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17057142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8157142857142857
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8528571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7981564446782999
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7661643990929705
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7695965865934244
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6971428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8085714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8428571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8885714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6971428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2695238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16857142857142857
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08885714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6971428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8085714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8428571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8885714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7917977544361884
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7611133786848071
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.765197446517495
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6871428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8028571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8342857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8857142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6871428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2676190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16685714285714284
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08857142857142856
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6871428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8028571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8342857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8857142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7844783501102325
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7524892290249433
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.756590766205664
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6571428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7814285714285715
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8114285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8585714285714285
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6571428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2604761904761905
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16228571428571428
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08585714285714285
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6571428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7814285714285715
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8114285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8585714285714285
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7570464835011314
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7245481859410431
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.729409564724743
+      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) on the json dataset. 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 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **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("ethanteh/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Income Taxes We are subject to income taxes in the U.S. and in many foreign jurisdictions. Significant judgment is required in determining our provision for income taxes, our deferred tax assets and liabilities and any valuation allowance recorded against our net deferred tax assets that are not more likely than not to be realized.',
+    'How does the company treat income taxes in its financial reports?',
+    "How does YouTube contribute to users' experience according to the company's statement?",
+]
+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
+
+* Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | dim_768    | dim_512    | dim_256    | dim_128    | dim_64    |
+|:--------------------|:-----------|:-----------|:-----------|:-----------|:----------|
+| cosine_accuracy@1   | 0.7029     | 0.6986     | 0.6971     | 0.6871     | 0.6571    |
+| cosine_accuracy@3   | 0.8186     | 0.8157     | 0.8086     | 0.8029     | 0.7814    |
+| cosine_accuracy@5   | 0.85       | 0.8529     | 0.8429     | 0.8343     | 0.8114    |
+| cosine_accuracy@10  | 0.8914     | 0.8986     | 0.8886     | 0.8857     | 0.8586    |
+| cosine_precision@1  | 0.7029     | 0.6986     | 0.6971     | 0.6871     | 0.6571    |
+| cosine_precision@3  | 0.2729     | 0.2719     | 0.2695     | 0.2676     | 0.2605    |
+| cosine_precision@5  | 0.17       | 0.1706     | 0.1686     | 0.1669     | 0.1623    |
+| cosine_precision@10 | 0.0891     | 0.0899     | 0.0889     | 0.0886     | 0.0859    |
+| cosine_recall@1     | 0.7029     | 0.6986     | 0.6971     | 0.6871     | 0.6571    |
+| cosine_recall@3     | 0.8186     | 0.8157     | 0.8086     | 0.8029     | 0.7814    |
+| cosine_recall@5     | 0.85       | 0.8529     | 0.8429     | 0.8343     | 0.8114    |
+| cosine_recall@10    | 0.8914     | 0.8986     | 0.8886     | 0.8857     | 0.8586    |
+| **cosine_ndcg@10**  | **0.7983** | **0.7982** | **0.7918** | **0.7845** | **0.757** |
+| cosine_mrr@10       | 0.7685     | 0.7662     | 0.7611     | 0.7525     | 0.7245    |
+| cosine_map@100      | 0.7725     | 0.7696     | 0.7652     | 0.7566     | 0.7294    |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 6,300 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                           | anchor                                                                            |
+  |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                            |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 46.74 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.52 tokens</li><li>max: 39 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                     | anchor                                                                                                                                                                            |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>During 2021, as a result of the enactment of a tax law and the closing of various acquisitions, the company concluded that it is no longer its intention to reinvest its undistributed earnings of its foreign TRSs indefinitely outside the United States.</code>                                                                                     | <code>What is the impact of a tax law change and acquisition closings on the company's intention regarding the reinvestment of undistributed earnings of its foreign TRSs?</code> |
+  | <code>In the year ended December 31, 2023, EBIT-adjusted decreased primarily due to: (1) increased Cost primarily due to increased campaigns and other warranty-related costs of $2.0 billion, increased EV-related charges of $1.9 billion primarily due to $1.6 billion in inventory adjustments to reflect the net realizable value at period end.</code> | <code>What factors contributed to the decrease in GM North America's EBIT-adjusted in 2023?</code>                                                                                |
+  | <code>Peloton's e-commerce platform offers a range of products and services, including Peloton Bikes, Bike+, Tread, and Row products, along with one-on-one sales consultations.</code>                                                                                                                                                                      | <code>What types of products and services does Peloton offer through its e-commerce platform?</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
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 8
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `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`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `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
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch     | Step    | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:---------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.2030    | 10      | 9.6119        | -                      | -                      | -                      | -                      | -                     |
+| 0.4061    | 20      | 6.108         | -                      | -                      | -                      | -                      | -                     |
+| 0.6091    | 30      | 3.9303        | -                      | -                      | -                      | -                      | -                     |
+| 0.8122    | 40      | 3.4657        | -                      | -                      | -                      | -                      | -                     |
+| 1.0       | 50      | 3.6929        | 0.7928                 | 0.7891                 | 0.7849                 | 0.7732                 | 0.7465                |
+| 1.2030    | 60      | 1.86          | -                      | -                      | -                      | -                      | -                     |
+| 1.4061    | 70      | 1.3879        | -                      | -                      | -                      | -                      | -                     |
+| 1.6091    | 80      | 1.4367        | -                      | -                      | -                      | -                      | -                     |
+| 1.8122    | 90      | 1.1032        | -                      | -                      | -                      | -                      | -                     |
+| 2.0       | 100     | 1.696         | 0.7996                 | 0.7966                 | 0.7899                 | 0.7815                 | 0.7563                |
+| 2.2030    | 110     | 1.0769        | -                      | -                      | -                      | -                      | -                     |
+| 2.4061    | 120     | 0.6618        | -                      | -                      | -                      | -                      | -                     |
+| 2.6091    | 130     | 0.912         | -                      | -                      | -                      | -                      | -                     |
+| 2.8122    | 140     | 0.6271        | -                      | -                      | -                      | -                      | -                     |
+| 3.0       | 150     | 0.9949        | 0.7984                 | 0.7973                 | 0.7925                 | 0.7835                 | 0.7574                |
+| 3.2030    | 160     | 0.5734        | -                      | -                      | -                      | -                      | -                     |
+| 3.4061    | 170     | 0.4934        | -                      | -                      | -                      | -                      | -                     |
+| 3.6091    | 180     | 0.6593        | -                      | -                      | -                      | -                      | -                     |
+| 3.8122    | 190     | 0.5452        | -                      | -                      | -                      | -                      | -                     |
+| **3.934** | **196** | **-**         | **0.7983**             | **0.7982**             | **0.7918**             | **0.7845**             | **0.757**             |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.1
+- PyTorch: 2.5.1+cu121
+- Accelerate: 1.2.1
+- Datasets: 2.19.1
+- Tokenizers: 0.21.0
+
+## 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": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.48.1",
+    "pytorch": "2.5.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cd99213455f4a2f449f735c20410c29cef2355e4cba5058d5ffd2dd55c1624
+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 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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]"
+}