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 +1,749 @@
+---
+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: 'The fair value of consideration transferred of $212.1 million
+    consisted of: (1) cash consideration paid of $211.3 million, net of cash acquired,
+    and (2) non-cash consideration of $0.8 million representing the portion of the
+    replacement equity awards issued in connection with the acquisition that was associated
+    with services rendered through the date of the acquisition.'
+  sentences:
+  - What is the monthly cost of a Connected Fitness Subscription if it includes a
+    combination of a Bike, Tread, Guide, or Row product in the same household as of
+    June 2022?
+  - What was the fair value of the total consideration transferred for the acquisition
+    discussed, and how was it composed?
+  - How did the Tax Court rule on November 18, 2020, regarding the company's dispute
+    with the IRS?
+- source_sentence: Each of the UK LSA members has agreed, on a several and not joint
+    basis, to compensate the Company for certain losses which may be incurred by the
+    Company, Visa Europe or their affiliates as a result of certain existing and potential
+    litigation relating to the setting and implementation of domestic multilateral
+    interchange fee rates in the United Kingdom prior to the closing of the Visa Europe
+    acquisition (Closing), subject to the terms and conditions set forth therein and,
+    with respect to each UK LSA member, up to a maximum amount of the up-front cash
+    consideration received by such UK LSA member. The UK LSA members’ obligations
+    under the UK loss sharing agreement are conditional upon, among other things,
+    either (a) losses valued in excess of the sterling equivalent on June 21, 2016
+    of €1.0 billion having arisen in UK covered claims (and such losses having reduced
+    the conversion rate of the series B preferred stock accordingly), or (b) the conversion
+    rate of the series B preferred stock having been reduced to zero pursuant to losses
+    arising in claims...
+  sentences:
+  - Are AbbVie's corporate governance materials available to the public, and if so,
+    where?
+  - What conditions must be met for the UK loss sharing agreement to compensate for
+    losses?
+  - How much did Delta Air Lines recognize in government grants from the Payroll Support
+    Programs during the year ended December 31, 2021?
+- source_sentence: We provide our customers with an opportunity to trade-in their
+    pre-owned gaming, mobility, and other products at our stores in exchange for cash
+    or credit which can be applied towards the purchase of other products.
+  sentences:
+  - What is GameStop's trade-in program?
+  - What were the total unrealized losses on U.S. Treasury securities as of the last
+    reporting date?
+  - What methods can a refinery use to meet its Environmental Protection Agency (EPA)
+    requirements for blending renewable fuels?
+- source_sentence: Diluted earnings per share is calculated using our weighted-average
+    outstanding common shares including the dilutive effect of stock awards as determined
+    under the treasury stock method.
+  sentences:
+  - How do changes in the assumed long-term rate of return affect AbbVie's net periodic
+    benefit cost for pension plans?
+  - What are the primary factors discussed in the Management’s Discussion and Analysis
+    that affect the financial statements year-to-year changes?
+  - What is the method used to calculate diluted earnings per share?
+- source_sentence: Item 8 in the document covers 'Financial Statements and Supplementary
+    Data'.
+  sentences:
+  - What type of information does Item 8 in the document cover?
+  - What are some of the potential consequences for Meta Platforms, Inc. from inquiries
+    or investigations as noted in the provided text?
+  - How is the take rate calculated and what does it represent?
+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: 0.68
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8242857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8571428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8985714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.68
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27476190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1714285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08985714285714284
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.68
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8242857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8571428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8985714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7931022011968226
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.759021541950113
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7627727073081649
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6685714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.82
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.86
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9042857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6685714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2733333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.172
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09042857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6685714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.82
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.86
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9042857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7907009828560375
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7540430839002267
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7572918009226873
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6771428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8142857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8571428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8857142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6771428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1714285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08857142857142855
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6771428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8142857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8571428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8857142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7870155634206691
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7548027210884352
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7592885578023618
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6542857142857142
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8071428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8514285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8857142857142857
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6542857142857142
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26904761904761904
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17028571428571426
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08857142857142856
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6542857142857142
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8071428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8514285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8857142857142857
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7751084647376248
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.73912925170068
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7430473786684797
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6157142857142858
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7771428571428571
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8214285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8728571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6157142857142858
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.259047619047619
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16428571428571428
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08728571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6157142857142858
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7771428571428571
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8214285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8728571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7472883962433147
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7067517006802716
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7111439006196084
+      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("Shivam1311/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    "Item 8 in the document covers 'Financial Statements and Supplementary Data'.",
+    'What type of information does Item 8 in the document cover?',
+    'What are some of the potential consequences for Meta Platforms, Inc. from inquiries or investigations as noted in the provided 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
+
+* 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   | 0.68       | 0.6686     | 0.6771    | 0.6543     | 0.6157     |
+| cosine_accuracy@3   | 0.8243     | 0.82       | 0.8143    | 0.8071     | 0.7771     |
+| cosine_accuracy@5   | 0.8571     | 0.86       | 0.8571    | 0.8514     | 0.8214     |
+| cosine_accuracy@10  | 0.8986     | 0.9043     | 0.8857    | 0.8857     | 0.8729     |
+| cosine_precision@1  | 0.68       | 0.6686     | 0.6771    | 0.6543     | 0.6157     |
+| cosine_precision@3  | 0.2748     | 0.2733     | 0.2714    | 0.269      | 0.259      |
+| cosine_precision@5  | 0.1714     | 0.172      | 0.1714    | 0.1703     | 0.1643     |
+| cosine_precision@10 | 0.0899     | 0.0904     | 0.0886    | 0.0886     | 0.0873     |
+| cosine_recall@1     | 0.68       | 0.6686     | 0.6771    | 0.6543     | 0.6157     |
+| cosine_recall@3     | 0.8243     | 0.82       | 0.8143    | 0.8071     | 0.7771     |
+| cosine_recall@5     | 0.8571     | 0.86       | 0.8571    | 0.8514     | 0.8214     |
+| cosine_recall@10    | 0.8986     | 0.9043     | 0.8857    | 0.8857     | 0.8729     |
+| **cosine_ndcg@10**  | **0.7931** | **0.7907** | **0.787** | **0.7751** | **0.7473** |
+| cosine_mrr@10       | 0.759      | 0.754      | 0.7548    | 0.7391     | 0.7068     |
+| cosine_map@100      | 0.7628     | 0.7573     | 0.7593    | 0.743      | 0.7111     |
+
+<!--
+## 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: 46.61 tokens</li><li>max: 439 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.72 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                       | anchor                                                                                             |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|
+  | <code>Operating costs and expenses increased $80.3 million, or 7.1%, during the year ended December 31, 2023, compared to the year ended December 31, 2022 primarily due to increases in film exhibition and food and beverage costs.</code>                   | <code>What factors contributed to the escalation in operating costs and expenses in 2023?</code>   |
+  | <code>In the United States, the company purchases HFCS to meet its and its bottlers’ requirements with the assistance of Coca-Cola Bottlers’ Sales & Services Company LLC, which is a procurement service provider for their North American operations.</code> | <code>How does the company source high fructose corn syrup (HFCS) in the United States?</code>     |
+  | <code>Item 8. Financial Statements and Supplementary Data The index to Financial Statements and Supplementary Data is presented</code>                                                                                                                         | <code>What is presented in Item 8 according to Financial Statements and Supplementary Data?</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`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: 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`: 16
+- `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
+- `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`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: 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 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.4061  | 10     | 16.0873       | -                      | -                      | -                      | -                      | -                     |
+| 0.8122  | 20     | 8.3282        | -                      | -                      | -                      | -                      | -                     |
+| 1.0     | 25     | -             | 0.7841                 | 0.7796                 | 0.7774                 | 0.7631                 | 0.7320                |
+| 1.2030  | 30     | 5.1781        | -                      | -                      | -                      | -                      | -                     |
+| 1.6091  | 40     | 4.0947        | -                      | -                      | -                      | -                      | -                     |
+| 2.0     | 50     | 3.9824        | 0.7888                 | 0.7867                 | 0.7851                 | 0.7701                 | 0.7401                |
+| 2.4061  | 60     | 2.854         | -                      | -                      | -                      | -                      | -                     |
+| 2.8122  | 70     | 2.9878        | -                      | -                      | -                      | -                      | -                     |
+| **3.0** | **75** | **-**         | **0.7913**             | **0.7903**             | **0.7869**             | **0.7755**             | **0.7469**            |
+| 3.2030  | 80     | 2.5653        | -                      | -                      | -                      | -                      | -                     |
+| 3.6091  | 90     | 2.999         | -                      | -                      | -                      | -                      | -                     |
+| 3.8528  | 96     | -             | 0.7931                 | 0.7907                 | 0.7870                 | 0.7751                 | 0.7473                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.3
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.3.2
+- 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": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.3",
+    "pytorch": "2.5.1+cu124"
+  },
+  "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:ab357b2c5529fbd0569919e37e50a17b8913c664d77f54b172586ebfece97501
+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]"
+}