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 +1,725 @@
+---
+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 cumulative basis adjustments associated with these hedging
+    relationships are a reduction of the amortized cost basis of the closed portfolios
+    of $19 million.
+  sentences:
+  - What are the main factors that influence the timing and cost of the company's
+    inventory purchases?
+  - What was the reduction in the amortized cost basis of the closed portfolios due
+    to cumulative basis adjustments in these hedging relationships?
+  - What was Garmin Ltd.'s net income for the fiscal year ended December 30, 2023?
+- source_sentence: 'The components of the provision for income taxes were as follows:
+    U.S. Federal $ (314,757), U.S. State and Local $ (85,355), Foreign $ (1,162).
+    Effective income tax rate | 24.2% | | 23.9% | |  ''19.7% | for the years 2021,
+    2022, and 2023.'
+  sentences:
+  - How much of the lease obligations is payable within 12 months as of December 31,
+    2023?
+  - What are the components and the effective tax rates for the year 2023 as reported
+    in the financial statements?
+  - How many Dollar Tree Plus stores were there as of January 28, 2023?
+- source_sentence: The Company may receive advanced royalty payments from licensees,
+    either in advance of a licensee’s subsequent sales to customers or, prior to the
+    completion of the Company’s performance obligation. The Wizards of the Coast and
+    Digital Gaming segment may also receive advanced payments from end users of its
+    digital games at the time of the initial purchase, through in-application purchases,
+    or through subscription services. Revenues on all licensee and digital gaming
+    advanced payments are deferred until the respective performance obligations are
+    satisfied, and these digital gaming revenues are recognized over a period of time,
+    determined based on either player usage patterns or the estimated playing life
+    of the user, or when additional downloadable content is made available, or as
+    with subscription services, ratably over the subscription term.
+  sentences:
+  - How does the Company recognize revenue from advanced royalty payments and digital
+    game purchases?
+  - What is the primary role of Canopy technology in the Health Services segment?
+  - Which section of a financial document provides an index to Financial Statements
+    and Supplementary Data?
+- source_sentence: Item 8 covers Financial Statements and Supplementary Data.
+  sentences:
+  - How much did the prepaid expenses increase from 2022 to 2023?
+  - What strategies are outlined in the Company's human capital management?
+  - What type of data does Item 8 cover in the company's filing?
+- source_sentence: When points are issued as a result of a stay by a Hilton Honors
+    member at an owned or leased hotel, we recognize a reduction in owned and leased
+    hotels revenues, since we are also the program sponsor.
+  sentences:
+  - What financial impact does the redemption of Hilton Honors points have on the
+    revenue of owned and leased hotels?
+  - What original companies formed IBM in 1911?
+  - What was the global gender equity status at Meta in July 2023?
+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: 0.6714285714285714
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8114285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8485714285714285
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6714285714285714
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2704761904761904
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16971428571428568
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6714285714285714
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8114285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8485714285714285
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7869239024966277
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7507120181405897
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7550416257512982
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6657142857142857
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.81
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8542857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8928571428571429
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6657142857142857
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17085714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08928571428571426
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6657142857142857
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.81
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8542857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8928571428571429
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7812019485050782
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7451230158730157
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7500357971583163
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6628571428571428
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7928571428571428
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8428571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8842857142857142
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6628571428571428
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2642857142857143
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16857142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08842857142857141
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6628571428571428
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7928571428571428
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8428571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8842857142857142
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7743199196082401
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7389903628117913
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7442531468911058
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6671428571428571
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.77
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8228571428571428
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8685714285714285
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6671428571428571
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25666666666666665
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16457142857142856
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08685714285714285
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6671428571428571
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.77
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8228571428571428
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8685714285714285
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7655373626539865
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7328270975056688
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7378874490017019
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6285714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.75
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7842857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8285714285714286
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6285714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.25
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15685714285714283
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08285714285714285
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6285714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.75
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7842857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8285714285714286
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7300345502506145
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6984109977324261
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7040560866496234
+      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("Ram934/bge-base-financial-matryoshka")
+# Run inference
+sentences = [
+    'When points are issued as a result of a stay by a Hilton Honors member at an owned or leased hotel, we recognize a reduction in owned and leased hotels revenues, since we are also the program sponsor.',
+    'What financial impact does the redemption of Hilton Honors points have on the revenue of owned and leased hotels?',
+    'What original companies formed IBM in 1911?',
+]
+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   | 0.6714     | 0.6657     | 0.6629     | 0.6671     | 0.6286   |
+| cosine_accuracy@3   | 0.8114     | 0.81       | 0.7929     | 0.77       | 0.75     |
+| cosine_accuracy@5   | 0.8486     | 0.8543     | 0.8429     | 0.8229     | 0.7843   |
+| cosine_accuracy@10  | 0.9        | 0.8929     | 0.8843     | 0.8686     | 0.8286   |
+| cosine_precision@1  | 0.6714     | 0.6657     | 0.6629     | 0.6671     | 0.6286   |
+| cosine_precision@3  | 0.2705     | 0.27       | 0.2643     | 0.2567     | 0.25     |
+| cosine_precision@5  | 0.1697     | 0.1709     | 0.1686     | 0.1646     | 0.1569   |
+| cosine_precision@10 | 0.09       | 0.0893     | 0.0884     | 0.0869     | 0.0829   |
+| cosine_recall@1     | 0.6714     | 0.6657     | 0.6629     | 0.6671     | 0.6286   |
+| cosine_recall@3     | 0.8114     | 0.81       | 0.7929     | 0.77       | 0.75     |
+| cosine_recall@5     | 0.8486     | 0.8543     | 0.8429     | 0.8229     | 0.7843   |
+| cosine_recall@10    | 0.9        | 0.8929     | 0.8843     | 0.8686     | 0.8286   |
+| **cosine_ndcg@10**  | **0.7869** | **0.7812** | **0.7743** | **0.7655** | **0.73** |
+| cosine_mrr@10       | 0.7507     | 0.7451     | 0.739      | 0.7328     | 0.6984   |
+| cosine_map@100      | 0.755      | 0.75       | 0.7443     | 0.7379     | 0.7041   |
+
+<!--
+## 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: 9 tokens</li><li>mean: 46.56 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.58 tokens</li><li>max: 51 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                          | anchor                                                                                                |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|
+  | <code>All of our Company’s facilities and other operations in the United States and elsewhere around the world are subject to various environmental protection statutes and regulations, including those relating to the use and treatment of water resources, discharge of wastewater, and air emissions.</code> | <code>What types of environmental regulations does the company need to comply with?</code>            |
+  | <code>Domestically, diesel fuel prices were higher in fiscal 2022 than in the prior year and may increase further in fiscal 2023 because of international tensions.</code>                                                                                                                                        | <code>How did diesel fuel prices affect the company’s freight costs in fiscal 2022?</code>            |
+  | <code>Our common stock trades on the NASDAQ Global Select Market, under the symbol “COST.”</code>                                                                                                                                                                                                                 | <code>What is the trading symbol for Costco's common stock on the NASDAQ Global Select Market?</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
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `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 |
+|:--------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.96     | 3      | -             | 0.7681                 | 0.7635                 | 0.7543                 | 0.7381                 | 0.6883                |
+| 1.92     | 6      | -             | 0.7812                 | 0.7747                 | 0.7706                 | 0.7602                 | 0.7197                |
+| 2.88     | 9      | -             | 0.7848                 | 0.7806                 | 0.7744                 | 0.7635                 | 0.7286                |
+| 3.2      | 10     | 3.2955        | -                      | -                      | -                      | -                      | -                     |
+| **3.84** | **12** | **-**         | **0.7869**             | **0.7812**             | **0.7743**             | **0.7655**             | **0.73**              |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.3.1
+- Transformers: 4.41.2
+- PyTorch: 2.4.1+cu121
+- Accelerate: 1.1.1
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

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

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.4.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ceb4f236b27c3fde1e26fdae17df3f72174a2b64674befebd2b53da1d12224e
+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]"
+}