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 +1,730 @@
+---
+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: As of December 30, 2023, about 92% of securities in the Company's
+    portfolio were at an unrealized loss position.
+  sentences:
+  - What additional document is included in the financial document apart from the
+    Consolidated Financial Statements?
+  - What percentage of the Company's portfolio of securities was in an unrealized
+    loss position as of December 30, 2023?
+  - What was the total loss the company incurred in association with the sale of the
+    eOne Music business in 2021?
+- source_sentence: Revenue Recognition Product Sales We recognize revenue from product
+    sales when control of the product transfers to the customer, which is generally
+    upon shipment or delivery, or in certain cases, upon the corresponding sales by
+    our customer to a third party. Revenues are recognized net of estimated rebates
+    and chargebacks, patient co-pay assistance, prompt pay discounts, distributor
+    fees, sales return provisions and other related deductions. These deductions to
+    product sales are referred to as gross-to-net deductions and are estimated and
+    recorded in the period in which the related product sales occur.
+  sentences:
+  - What is the expiration date for the federal research and development tax credits
+    as of 2023?
+  - How are revenue recognition and Gross-to-Net deductions related in the context
+    of product sales?
+  - What is the approval status of Tirzepatide (Mounjaro, Zepbound®) for the treatment
+    of obesity as of 2023?
+- source_sentence: The expected long-term rate of return assumption used in computing
+    2023 net periodic benefit income for the U.S. pension plans was 6.75%.
+  sentences:
+  - What is the expected long-term rate of return on plan assets used in computing
+    the 2023 net periodic benefit income for U.S. pension plans?
+  - What was the increase in postpaid phone subscribers at AT&T Inc. from 2021 to
+    2023?
+  - How does Chipotle ensure pay equity among its employees?
+- source_sentence: In an Annual Report on Form 10-K, 'Litigation and Other Legal Matters'
+    are detailed under 'Note 13 — Commitments and Contingencies' in Part IV, Item
+    15 of the consolidated financial statements.
+  sentences:
+  - What is Apple's commitment to workplace practices and policies concerning harassment
+    or discrimination?
+  - By what percentage did net income increase in 2023 compared to 2022?
+  - In the structure of an Annual Report on Form 10-K, where does one find details
+    about 'Litigation and Other Legal Matters'?
+- source_sentence: Any such inquiries or investigations (including the IDPC proceedings)
+    could subject us to substantial fines and costs, require us to change our business
+    practices, divert resources and the attention of management from our business,
+    or adversely affect our business.
+  sentences:
+  - What are some of the potential consequences for Meta Platforms, Inc. from inquiries
+    or investigations as noted in the provided text?
+  - What was the quarterly dividend declared by Bank of America's board of directors
+    on January 31, 2024?
+  - What recent technological advancements has the company implemented in set-top
+    box (STB) solutions?
+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: 0.7357142857142858
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8557142857142858
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8957142857142857
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9285714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7357142857142858
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28523809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1791428571428571
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09285714285714286
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7357142857142858
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8557142857142858
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8957142857142857
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9285714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8337852464509243
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8032046485260771
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8062343226371107
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7271428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8628571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.89
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9328571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7271428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2876190476190476
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17799999999999996
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09328571428571426
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7271428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8628571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.89
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9328571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8315560673246299
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7989370748299317
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.801544102570532
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.73
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8428571428571429
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8842857142857142
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9242857142857143
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.73
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28095238095238095
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17685714285714282
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09242857142857142
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.73
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8428571428571429
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8842857142857142
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9242857142857143
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8268873311527957
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7956485260770971
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.798561528530067
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.7157142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8414285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8671428571428571
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9185714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.7157142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.28047619047619043
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1734285714285714
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09185714285714283
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.7157142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8414285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8671428571428571
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9185714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8170171494742537
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.784555555555555
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7871835671545038
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6928571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8171428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8471428571428572
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8928571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6928571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2723809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16942857142857143
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08928571428571426
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6928571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8171428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8471428571428572
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8928571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7945818011619106
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7630130385487527
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7667826657397622
+      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("sintuk/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'Any such inquiries or investigations (including the IDPC proceedings) could subject us to substantial fines and costs, require us to change our business practices, divert resources and the attention of management from our business, or adversely affect our business.',
+    'What are some of the potential consequences for Meta Platforms, Inc. from inquiries or investigations as noted in the provided text?',
+    "What was the quarterly dividend declared by Bank of America's board of directors on January 31, 2024?",
+]
+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   | 0.7357     | 0.7271     | 0.73       | 0.7157    | 0.6929     |
+| cosine_accuracy@3   | 0.8557     | 0.8629     | 0.8429     | 0.8414    | 0.8171     |
+| cosine_accuracy@5   | 0.8957     | 0.89       | 0.8843     | 0.8671    | 0.8471     |
+| cosine_accuracy@10  | 0.9286     | 0.9329     | 0.9243     | 0.9186    | 0.8929     |
+| cosine_precision@1  | 0.7357     | 0.7271     | 0.73       | 0.7157    | 0.6929     |
+| cosine_precision@3  | 0.2852     | 0.2876     | 0.281      | 0.2805    | 0.2724     |
+| cosine_precision@5  | 0.1791     | 0.178      | 0.1769     | 0.1734    | 0.1694     |
+| cosine_precision@10 | 0.0929     | 0.0933     | 0.0924     | 0.0919    | 0.0893     |
+| cosine_recall@1     | 0.7357     | 0.7271     | 0.73       | 0.7157    | 0.6929     |
+| cosine_recall@3     | 0.8557     | 0.8629     | 0.8429     | 0.8414    | 0.8171     |
+| cosine_recall@5     | 0.8957     | 0.89       | 0.8843     | 0.8671    | 0.8471     |
+| cosine_recall@10    | 0.9286     | 0.9329     | 0.9243     | 0.9186    | 0.8929     |
+| **cosine_ndcg@10**  | **0.8338** | **0.8316** | **0.8269** | **0.817** | **0.7946** |
+| cosine_mrr@10       | 0.8032     | 0.7989     | 0.7956     | 0.7846    | 0.763      |
+| cosine_map@100      | 0.8062     | 0.8015     | 0.7986     | 0.7872    | 0.7668     |
+
+<!--
+## 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: 6 tokens</li><li>mean: 45.64 tokens</li><li>max: 301 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 20.4 tokens</li><li>max: 42 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                | anchor                                                                                                    |
+  |:----------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------|
+  | <code>We later began working with commercial enterprises, who often faced fundamentally similar challenges in working with data.</code> | <code>What type of software solutions did Palantir later provide to commercial enterprises?</code>        |
+  | <code>General Motors Company was incorporated as a Delaware corporation in 2009.</code>                                                 | <code>What year was General Motors Company incorporated?</code>                                           |
+  | <code>Companies with which we have strategic partnerships in some areas may be competitors in other areas.</code>                       | <code>What is the nature of IBM's relationship with its strategic partners in competitional terms?</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `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     | 1.6103        | -                      | -                      | -                      | -                      | -                     |
+| 0.9746     | 12     | -             | 0.8290                 | 0.8247                 | 0.8184                 | 0.8110                 | 0.7726                |
+| 1.6244     | 20     | 0.6597        | -                      | -                      | -                      | -                      | -                     |
+| 1.9492     | 24     | -             | 0.8313                 | 0.8290                 | 0.8264                 | 0.8161                 | 0.7849                |
+| 2.4365     | 30     | 0.5016        | -                      | -                      | -                      | -                      | -                     |
+| 2.9239     | 36     | -             | 0.8340                 | 0.8323                 | 0.8265                 | 0.8170                 | 0.7943                |
+| 3.2487     | 40     | 0.4629        | -                      | -                      | -                      | -                      | -                     |
+| **3.8985** | **48** | **-**         | **0.8338**             | **0.8316**             | **0.8269**             | **0.817**              | **0.7946**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 3.4.1
+- Transformers: 4.41.2
+- PyTorch: 2.2.2
+- Accelerate: 1.5.2
+- 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": "3.4.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.2.2"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675d99cd1caeef299a2570581e271d4bb9b8b53be79955a094ab03ce77f476a5
+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]"
+}