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 +1,733 @@
+---
+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: Americas | $ | 7,631,647 | | | $ | 6,817,454 | | 79.3 | % | 84.1
+    | %
+  sentences:
+  - What therapeutic area does the folate receptor alpha antibody drug conjugate MBK-103
+    target?
+  - What was the proportion of Americas' net revenue to the company's total net revenue
+    in 2023, and how did it change from 2022?
+  - What was the Company's income tax provision for the year ended December 31, 2022?
+- source_sentence: The Company establishes SSP based on observable prices of products
+    or services sold or priced separately in comparable circumstances to similar customers.
+  sentences:
+  - What were the lease terms and discount rates for operating leases as of March
+    31, 2023 and 2022?
+  - What factors influence the Company's ability to establish Standalone Selling Prices
+    (SSP) based on observable prices?
+  - What number is associated with Item 8 in the document?
+- source_sentence: Our effective tax rates could be affected by numerous factors,
+    such as changes in our business operations, acquisitions, investments, entry into
+    new businesses and geographies, intercompany transactions, the relative amount
+    of our foreign earnings, including earnings being lower than anticipated in jurisdictions
+    where we have lower statutory rates and higher than anticipated in jurisdictions
+    where we have higher statutory rates, losses incurred in jurisdictions for which
+    we are not able to realize related tax benefits, the applicability of special
+    tax regimes, changes in foreign exchange rates, changes in our stock price, changes
+    to our forecasts of income and loss and the mix of jurisdictions to which they
+    relate, changes in our deferred tax assets and liabilities and their valuation,
+    changes in the laws, regulations, administrative practices, principles, and interpretations
+    related to tax, including changes to the global tax framework, competition, and
+    other laws and accounting rules in various jurisdictions.
+  sentences:
+  - What impact do tax laws and economic conditions have on the company's effective
+    tax rates?
+  - What is the purpose of Alphabet Inc.'s annual review of methodologies used in
+    monitoring advertising metrics?
+  - From which sources does Apple obtain certain essential components?
+- source_sentence: (Decrease) increase in cash, cash equivalents and restricted cash
+    for fiscal year 2023 was a decrease of $182 million, starting with $4,763 million
+    at the beginning and ending with $4,581 million.
+  sentences:
+  - What is the minimum project cost for the development described in the Second Development
+    Agreement involving MBS?
+  - What does the No Surprises Act require providers to develop and disclose?
+  - What was the change in cash and cash equivalents for Hewlett Packard Enterprise
+    from the beginning to the end of the fiscal year 2023?
+- source_sentence: The total amount of gross unrecognized tax benefits as of December
+    30, 2023 was $13,571.
+  sentences:
+  - What was the total amount of gross unrecognized tax benefits as of December 30,
+    2023?
+  - What percentage of Kenvue Common Stock did Johnson & Johnson own as of the closing
+    of the IPO?
+  - What was the percentage change in sales from 2022 to 2023 for the Trauma segment
+    in the U.S.?
+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: 0.6928571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8142857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8471428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9014285714285715
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6928571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1694285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09014285714285714
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6928571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8142857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8471428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9014285714285715
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7960400928582716
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7625391156462585
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7656459931357954
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8142857142857143
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.85
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8928571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16999999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08928571428571426
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8142857142857143
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.85
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8928571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7962092633155669
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7652437641723353
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7690571344301111
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6885714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8085714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8485714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8928571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6885714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2695238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16971428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08928571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6885714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8085714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8485714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8928571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.790294082455236
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7575634920634915
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7608461966590305
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6771428571428572
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7971428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.83
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.89
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6771428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.26571428571428574
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16599999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.089
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6771428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7971428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.83
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.89
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7811390356263523
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7466921768707482
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7500930927741866
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6457142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7685714285714286
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8114285714285714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8628571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6457142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2561904761904762
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16228571428571428
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08628571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6457142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7685714285714286
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8114285714285714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8628571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7526448867884948
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7175549886621314
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.721601645358737
+      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("michalwilkosz/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'The total amount of gross unrecognized tax benefits as of December 30, 2023 was $13,571.',
+    'What was the total amount of gross unrecognized tax benefits as of December 30, 2023?',
+    'What percentage of Kenvue Common Stock did Johnson & Johnson own as of the closing of the IPO?',
+]
+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   | 0.6929    | 0.7        | 0.6886     | 0.6771     | 0.6457     |
+| cosine_accuracy@3   | 0.8143    | 0.8143     | 0.8086     | 0.7971     | 0.7686     |
+| cosine_accuracy@5   | 0.8471    | 0.85       | 0.8486     | 0.83       | 0.8114     |
+| cosine_accuracy@10  | 0.9014    | 0.8929     | 0.8929     | 0.89       | 0.8629     |
+| cosine_precision@1  | 0.6929    | 0.7        | 0.6886     | 0.6771     | 0.6457     |
+| cosine_precision@3  | 0.2714    | 0.2714     | 0.2695     | 0.2657     | 0.2562     |
+| cosine_precision@5  | 0.1694    | 0.17       | 0.1697     | 0.166      | 0.1623     |
+| cosine_precision@10 | 0.0901    | 0.0893     | 0.0893     | 0.089      | 0.0863     |
+| cosine_recall@1     | 0.6929    | 0.7        | 0.6886     | 0.6771     | 0.6457     |
+| cosine_recall@3     | 0.8143    | 0.8143     | 0.8086     | 0.7971     | 0.7686     |
+| cosine_recall@5     | 0.8471    | 0.85       | 0.8486     | 0.83       | 0.8114     |
+| cosine_recall@10    | 0.9014    | 0.8929     | 0.8929     | 0.89       | 0.8629     |
+| **cosine_ndcg@10**  | **0.796** | **0.7962** | **0.7903** | **0.7811** | **0.7526** |
+| cosine_mrr@10       | 0.7625    | 0.7652     | 0.7576     | 0.7467     | 0.7176     |
+| cosine_map@100      | 0.7656    | 0.7691     | 0.7608     | 0.7501     | 0.7216     |
+
+<!--
+## 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: 2 tokens</li><li>mean: 45.43 tokens</li><li>max: 301 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 20.34 tokens</li><li>max: 46 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                             | anchor                                                                                             |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|
+  | <code>Almost all FedEx Office locations provide local pickup-and-delivery service for print jobs completed by FedEx Office. A FedEx courier picks up a customer’s print job at the customer’s location and then returns the finished product to the customer.</code> | <code>What service does almost all FedEx Office locations provide for completed print jobs?</code> |
+  | <code>Non-compliance with government laws and regulations may result in fines, limits on the ability to sell products, suspension of business activities, reputational damage, and legal liabilities.</code>                                                         | <code>What are the consequences of failing to comply with government laws and regulations?</code>  |
+  | <code>Item 8 is labeled as Financial Statements and Supplementary Data.</code>                                                                                                                                                                                       | <code>What is the title of Item 8 in the financial document?</code>                                |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `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 |
+|:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.8122     | 10     | 1.5678        | -                      | -                      | -                      | -                      | -                     |
+| 0.9746     | 12     | -             | 0.7840                 | 0.7835                 | 0.7763                 | 0.7656                 | 0.7360                |
+| 1.6244     | 20     | 0.6336        | -                      | -                      | -                      | -                      | -                     |
+| 1.9492     | 24     | -             | 0.7960                 | 0.7950                 | 0.7903                 | 0.7783                 | 0.7500                |
+| 2.4365     | 30     | 0.464         | -                      | -                      | -                      | -                      | -                     |
+| **2.9239** | **36** | **-**         | **0.7965**             | **0.7969**             | **0.7912**             | **0.7825**             | **0.7525**            |
+| 3.2487     | 40     | 0.3768        | -                      | -                      | -                      | -                      | -                     |
+| 3.8985     | 48     | -             | 0.7960                 | 0.7962                 | 0.7903                 | 0.7811                 | 0.7526                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.3.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 1.2.0
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "BAAI/bge-base-en-v1.5",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+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 sha256:9d478e3868e32dfa9681f79758b84b12d51cbf73f2511c62724a2970341bc444
+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]"
+}