Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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 +1,713 @@
+---
+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-small-en-v1.5
+widget:
+- source_sentence: During the year ended December 31, 2023, cash flows used in investing
+    activities also included proceeds from the sale of our investment in Saudi Cinema
+    Company, LLC of $30.0 million.
+  sentences:
+  - What are some of the risks associated with the company's ability to maintain its
+    concession in Macao and gaming license in Singapore?
+  - What were the proceeds from the sale of investment in Saudi Cinema Company, LLC
+    during 2023?
+  - What financial impact did the change in accounting estimate regarding server and
+    network equipment have on Microsoft in fiscal year 2023?
+- source_sentence: During 2023, U.S. sales of natural gas averaged 4.7 billion cubic
+    feet per day.
+  sentences:
+  - What constitutes a material weakness in internal control over financial reporting,
+    according to the criteria set by COSO?
+  - What was Chevron's total average daily sales of natural gas in the U.S. in 2023?
+  - What total amount of assets were measured at fair value as of January 31, 2022,
+    and how is this divided across the fair value hierarchy levels?
+- source_sentence: The net cash provided by operating activities during fiscal 2023
+    was related to net income of $208 million, adjusted for non-cash items including
+    $3.8 billion of depreciation and amortization and $3.3 billion related to stock-based
+    compensation expense.
+  sentences:
+  - What was the net cash provided by operating activities for fiscal 2023?
+  - How does Nike protect its intellectual property rights against infringement?
+  - What specific feature does the Peloton Bike+ offer regarding workout experience?
+- source_sentence: Year-over-Year Changes in Operating Results for 2023 compared to
+    2022 showed a decrease of $1,858 million for FedEx Express, an increase of $498
+    million for FedEx Ground, and an increase of $262 million for FedEx Freight.
+  sentences:
+  - How did comparable sales growth, including fuel, contribute to net sales for Sam's
+    Club in fiscal 2023?
+  - What is the role of Level 1, Level 2, and Level 3 inputs in the fair value hierarchy
+    according to ASC 820?
+  - What were the operating results changes year-over-year for the FedEx Express,
+    Ground, and Freight segments in 2023 compared to 2022?
+- source_sentence: Caterpillar Insurance Co. Ltd. is registered as a Class 2 (General
+    Business) and Class B (Long-Term) insurer with the Bermuda Monetary Authority.
+  sentences:
+  - What types of insurance licenses does Caterpillar Insurance Co. Ltd. hold in Bermuda?
+  - What is indicated by 'Item 8' in a financial document?
+  - What does Gross Merchandise Volume (GMV) represent in financial terms?
+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 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.6985714285714286
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8314285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8728571428571429
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9171428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6985714285714286
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.27714285714285714
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17457142857142854
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09171428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6985714285714286
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8314285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8728571428571429
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9171428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8091312862711041
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7744716553287979
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.778107400978576
+      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: 0.8171428571428572
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8642857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9171428571428571
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.6771428571428572
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2723809523809524
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17285714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09171428571428569
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.6771428571428572
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8171428571428572
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8642857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9171428571428571
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7978178514618532
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7596043083900226
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7625576612954725
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.66
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.8014285714285714
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8542857142857143
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9028571428571428
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.66
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2671428571428571
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.17085714285714285
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09028571428571427
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.66
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.8014285714285714
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8542857142857143
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9028571428571428
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7797125058125993
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7404512471655325
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.7439184556821083
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) on the json dataset. It maps sentences & paragraphs to a 384-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-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) <!-- at revision 5c38ec7c405ec4b44b94cc5a9bb96e735b38267a -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 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': 384, '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("MistyDragon/bge-small-financial-matryoshka")
+# Run inference
+sentences = [
+    'Caterpillar Insurance Co. Ltd. is registered as a Class 2 (General Business) and Class B (Long-Term) insurer with the Bermuda Monetary Authority.',
+    'What types of insurance licenses does Caterpillar Insurance Co. Ltd. hold in Bermuda?',
+    "What is indicated by 'Item 8' in a financial document?",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# 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
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6986     |
+| cosine_accuracy@3   | 0.8314     |
+| cosine_accuracy@5   | 0.8729     |
+| cosine_accuracy@10  | 0.9171     |
+| cosine_precision@1  | 0.6986     |
+| cosine_precision@3  | 0.2771     |
+| cosine_precision@5  | 0.1746     |
+| cosine_precision@10 | 0.0917     |
+| cosine_recall@1     | 0.6986     |
+| cosine_recall@3     | 0.8314     |
+| cosine_recall@5     | 0.8729     |
+| cosine_recall@10    | 0.9171     |
+| **cosine_ndcg@10**  | **0.8091** |
+| cosine_mrr@10       | 0.7745     |
+| cosine_map@100      | 0.7781     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.6771     |
+| cosine_accuracy@3   | 0.8171     |
+| cosine_accuracy@5   | 0.8643     |
+| cosine_accuracy@10  | 0.9171     |
+| cosine_precision@1  | 0.6771     |
+| cosine_precision@3  | 0.2724     |
+| cosine_precision@5  | 0.1729     |
+| cosine_precision@10 | 0.0917     |
+| cosine_recall@1     | 0.6771     |
+| cosine_recall@3     | 0.8171     |
+| cosine_recall@5     | 0.8643     |
+| cosine_recall@10    | 0.9171     |
+| **cosine_ndcg@10**  | **0.7978** |
+| cosine_mrr@10       | 0.7596     |
+| cosine_map@100      | 0.7626     |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.66       |
+| cosine_accuracy@3   | 0.8014     |
+| cosine_accuracy@5   | 0.8543     |
+| cosine_accuracy@10  | 0.9029     |
+| cosine_precision@1  | 0.66       |
+| cosine_precision@3  | 0.2671     |
+| cosine_precision@5  | 0.1709     |
+| cosine_precision@10 | 0.0903     |
+| cosine_recall@1     | 0.66       |
+| cosine_recall@3     | 0.8014     |
+| cosine_recall@5     | 0.8543     |
+| cosine_recall@10    | 0.9029     |
+| **cosine_ndcg@10**  | **0.7797** |
+| cosine_mrr@10       | 0.7405     |
+| cosine_map@100      | 0.7439     |
+
+<!--
+## 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: 10 tokens</li><li>mean: 47.77 tokens</li><li>max: 439 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 20.48 tokens</li><li>max: 45 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                        | anchor                                                                                                                                                   |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Return on investment (ROI) | 12.7 | % | | 14.9 | %</code>                                                                                                                                                                 | <code>What was the return on investment (ROI) for the average invested capital in the latest period and how did this compare to the prior period?</code> |
+  | <code>According to the terms of the Senior Credit Facilities, cash amounts exceeding $175 million can be deducted from the total debt in the leverage ratio calculation, though this is subject to certain restrictions.</code> | <code>How does the Senior Credit Facilities' treatment of cash affect the calculation of the leverage ratio?</code>                                      |
+  | <code>In 2023, approximately 67% of the total U.S. dialysis patient service revenues were generated from government-based programs.</code>                                                                                      | <code>What percentage of the total U.S. dialysis patient service revenues were generated from government-based programs in 2023?</code>                  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 8
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: False
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 8
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 8
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 4
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: False
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step    | Training Loss | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:-------:|:-------------:|:----------------------:|:----------------------:|:---------------------:|
+| 0.1015  | 10      | 4.9287        | -                      | -                      | -                     |
+| 0.2030  | 20      | 3.7753        | -                      | -                      | -                     |
+| 0.3046  | 30      | 2.7807        | -                      | -                      | -                     |
+| 0.4061  | 40      | 2.6642        | -                      | -                      | -                     |
+| 0.5076  | 50      | 1.8158        | -                      | -                      | -                     |
+| 0.6091  | 60      | 1.2895        | -                      | -                      | -                     |
+| 0.7107  | 70      | 1.356         | -                      | -                      | -                     |
+| 0.8122  | 80      | 1.2217        | -                      | -                      | -                     |
+| 0.9137  | 90      | 1.2548        | -                      | -                      | -                     |
+| 1.0     | 99      | -             | 0.7949                 | 0.7853                 | 0.7609                |
+| 1.0102  | 100     | 1.1693        | -                      | -                      | -                     |
+| 1.1117  | 110     | 1.0828        | -                      | -                      | -                     |
+| 1.2132  | 120     | 0.9545        | -                      | -                      | -                     |
+| 1.3147  | 130     | 1.1774        | -                      | -                      | -                     |
+| 1.4162  | 140     | 0.55          | -                      | -                      | -                     |
+| 1.5178  | 150     | 0.891         | -                      | -                      | -                     |
+| 1.6193  | 160     | 0.9661        | -                      | -                      | -                     |
+| 1.7208  | 170     | 0.9355        | -                      | -                      | -                     |
+| 1.8223  | 180     | 0.9888        | -                      | -                      | -                     |
+| 1.9239  | 190     | 1.0157        | -                      | -                      | -                     |
+| 2.0     | 198     | -             | 0.8067                 | 0.7945                 | 0.7742                |
+| 2.0203  | 200     | 0.7944        | -                      | -                      | -                     |
+| 2.1218  | 210     | 0.5637        | -                      | -                      | -                     |
+| 2.2234  | 220     | 0.3895        | -                      | -                      | -                     |
+| 2.3249  | 230     | 1.0888        | -                      | -                      | -                     |
+| 2.4264  | 240     | 0.8784        | -                      | -                      | -                     |
+| 2.5279  | 250     | 0.5746        | -                      | -                      | -                     |
+| 2.6294  | 260     | 1.064         | -                      | -                      | -                     |
+| 2.7310  | 270     | 0.8036        | -                      | -                      | -                     |
+| 2.8325  | 280     | 0.6005        | -                      | -                      | -                     |
+| 2.9340  | 290     | 0.7571        | -                      | -                      | -                     |
+| **3.0** | **297** | **-**         | **0.81**               | **0.7982**             | **0.7785**            |
+| 3.0305  | 300     | 0.6178        | -                      | -                      | -                     |
+| 3.1320  | 310     | 0.5013        | -                      | -                      | -                     |
+| 3.2335  | 320     | 0.7171        | -                      | -                      | -                     |
+| 3.3350  | 330     | 0.5717        | -                      | -                      | -                     |
+| 3.4365  | 340     | 0.7031        | -                      | -                      | -                     |
+| 3.5381  | 350     | 0.8601        | -                      | -                      | -                     |
+| 3.6396  | 360     | 0.597         | -                      | -                      | -                     |
+| 3.7411  | 370     | 0.4611        | -                      | -                      | -                     |
+| 3.8426  | 380     | 0.6503        | -                      | -                      | -                     |
+| 3.9442  | 390     | 0.3176        | -                      | -                      | -                     |
+| 4.0     | 396     | -             | 0.8091                 | 0.7978                 | 0.7797                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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 +1,30 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "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": "4.52.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e895b05dd2bb1c9dfbe164f22b72586226b2a133265b0dde5d0630453d98b0
+size 133462128

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": true
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}