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 +1,667 @@
+---
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:200000
+- loss:MultipleNegativesRankingLoss
+- loss:ContrastiveLoss
+base_model: BAAI/bge-base-en-v1.5
+widget:
+- source_sentence: What is the best sushi restaurant in Los Angeles, aside from Urasawa
+    which is impractical for regular visits?
+  sentences:
+  - How do I stop feeling sorry for ignorant and arrogant people?
+  - What are the best sushi restaurants in Los Angeles?
+  - Why do people flirt on Quora?
+- source_sentence: Why are many Quora writers lonely and/ or unemployed?
+  sentences:
+  - Are writers on Quora mostly lonely or have no job (unemployed)?
+  - What are the attributes of monkeys belongs to Japanese-macaque monkey Family?
+  - I want to change the education system in India. How can I have such power?
+- source_sentence: What is the best, and painless way to kill myself?
+  sentences:
+  - What is a way to commit suicide and not damaging your organs so that they can
+    be donated?
+  - How do I beat insomnia?
+  - What is the most painless way to commit suicide?
+- source_sentence: What are ETF'S and what is the difference between ETF'S and mutual
+    funds?
+  sentences:
+  - What is the difference between ETF and mutual funds?
+  - What's better, an index ETF or an index mutual fund?
+  - 'Income Tax: How to check pan card status?'
+- source_sentence: For what reasons can't the Olympics be held in India?
+  sentences:
+  - What are the best hotels to stay in Goa?
+  - When will Olympics be held in India?
+  - When will India qualify for the FIFA World Cup?
+datasets:
+- sentence-transformers/quora-duplicates
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- cosine_mcc
+- average_precision
+- f1
+- precision
+- recall
+- threshold
+- 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: SentenceTransformer based on BAAI/bge-base-en-v1.5
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: quora duplicates
+      type: quora-duplicates
+    metrics:
+    - type: cosine_accuracy
+      value: 0.833
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.8065301179885864
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.7630522088353413
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.745335042476654
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.6705882352941176
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8850931677018633
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8120519897128382
+      name: Cosine Ap
+    - type: cosine_mcc
+      value: 0.641402259734116
+      name: Cosine Mcc
+  - task:
+      type: paraphrase-mining
+      name: Paraphrase Mining
+    dataset:
+      name: quora duplicates dev
+      type: quora-duplicates-dev
+    metrics:
+    - type: average_precision
+      value: 0.6286866338232051
+      name: Average Precision
+    - type: f1
+      value: 0.6032452480296708
+      name: F1
+    - type: precision
+      value: 0.5627297495999654
+      name: Precision
+    - type: recall
+      value: 0.6500474596592896
+      name: Recall
+    - type: threshold
+      value: 0.7944510877132416
+      name: Threshold
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9732
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9944
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9958
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9994
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9732
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.432
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.27652
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.14606
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.8392449568046333
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9654790046130339
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9826052435636259
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9955256342023989
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9852328208350886
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.983879365079365
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9794253454223505
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on BAAI/bge-base-en-v1.5
+
+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 [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) datasets. 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 Datasets:**
+    - [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+    - [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### 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("manestay/bge-base-en-v1.5-mnrl-cl-multi")
+# Run inference
+sentences = [
+    "For what reasons can't the Olympics be held in India?",
+    'When will Olympics be held in India?',
+    'When will India qualify for the FIFA World Cup?',
+]
+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
+
+#### Binary Classification
+
+* Dataset: `quora-duplicates`
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                    | Value      |
+|:--------------------------|:-----------|
+| cosine_accuracy           | 0.833      |
+| cosine_accuracy_threshold | 0.8065     |
+| cosine_f1                 | 0.7631     |
+| cosine_f1_threshold       | 0.7453     |
+| cosine_precision          | 0.6706     |
+| cosine_recall             | 0.8851     |
+| **cosine_ap**             | **0.8121** |
+| cosine_mcc                | 0.6414     |
+
+#### Paraphrase Mining
+
+* Dataset: `quora-duplicates-dev`
+* Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator) with these parameters:
+  ```json
+  {'add_transitive_closure': <function ParaphraseMiningEvaluator.add_transitive_closure at 0x7f26a89802c0>, 'max_pairs': 500000, 'top_k': 100}
+  ```
+
+| Metric                | Value      |
+|:----------------------|:-----------|
+| **average_precision** | **0.6287** |
+| f1                    | 0.6032     |
+| precision             | 0.5627     |
+| recall                | 0.65       |
+| threshold             | 0.7945     |
+
+#### Information Retrieval
+
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9732     |
+| cosine_accuracy@3   | 0.9944     |
+| cosine_accuracy@5   | 0.9958     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.9732     |
+| cosine_precision@3  | 0.432      |
+| cosine_precision@5  | 0.2765     |
+| cosine_precision@10 | 0.1461     |
+| cosine_recall@1     | 0.8392     |
+| cosine_recall@3     | 0.9655     |
+| cosine_recall@5     | 0.9826     |
+| cosine_recall@10    | 0.9955     |
+| **cosine_ndcg@10**  | **0.9852** |
+| cosine_mrr@10       | 0.9839     |
+| cosine_map@100      | 0.9794     |
+
+<!--
+## 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 Datasets
+
+#### mnrl
+
+* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 100,000 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                          | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | string                                                                            |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 13.85 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.65 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.76 tokens</li><li>max: 64 tokens</li></ul> |
+* Samples:
+  | anchor                                                                          | positive                                                                                       | negative                                                                                                         |
+  |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|
+  | <code>Why in India do we not have one on one political debate as in USA?</code> | <code>Why cant we have a public debate between politicians in India like the one in US?</code> | <code>Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?</code> |
+  | <code>What is OnePlus One?</code>                                               | <code>How is oneplus one?</code>                                                               | <code>Why is OnePlus One so good?</code>                                                                         |
+  | <code>Does our mind control our emotions?</code>                                | <code>How do smart and successful people control their emotions?</code>                        | <code>How can I control my positive emotions for the people whom I love but they don't care about me?</code>     |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### cl
+
+* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 100,000 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                        | sentence2                                                                         | label                                           |
+  |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                           | string                                                                            | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 15.3 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.66 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> |
+* Samples:
+  | sentence1                                                                              | sentence2                                                                                             | label          |
+  |:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>What is the step by step guide to invest in share market in india?</code>        | <code>What is the step by step guide to invest in share market?</code>                                | <code>0</code> |
+  | <code>What is the story of Kohinoor (Koh-i-Noor) Diamond?</code>                       | <code>What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?</code> | <code>0</code> |
+  | <code>How can I increase the speed of my internet connection while using a VPN?</code> | <code>How can Internet speed be increased by hacking through DNS?</code>                              | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Datasets
+
+#### mnrl
+
+* Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 1,000 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                         | negative                                                                          |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 7 tokens</li><li>mean: 13.84 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.8 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.71 tokens</li><li>max: 56 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                   | positive                                                                         | negative                                                                                                                                                                                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Which programming language is best for developing low-end games?</code>                            | <code>What coding language should I learn first for making games?</code>         | <code>I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages ​​I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms?</code> |
+  | <code>Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump?</code> | <code>Should Meryl Streep be using her position to attack the president?</code>  | <code>Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?</code>                                                                                                                                                                                       |
+  | <code>Where can I found excellent commercial fridges in Sydney?</code>                                   | <code>Where can I found impressive range of commercial fridges in Sydney?</code> | <code>What is the best grocery delivery service in Sydney?</code>                                                                                                                                                                                                                 |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim"
+  }
+  ```
+
+#### cl
+
+* Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 1,000 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                         | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 15.59 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>0: ~63.40%</li><li>1: ~36.60%</li></ul> |
+* Samples:
+  | sentence1                                                                 | sentence2                                                                                                | label          |
+  |:--------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>What should I ask my friend to get from UK to India?</code>         | <code>What is the process of getting a surgical residency in UK after completing MBBS from India?</code> | <code>0</code> |
+  | <code>How can I learn hacking for free?</code>                            | <code>How can I learn to hack seriously?</code>                                                          | <code>1</code> |
+  | <code>Which is the best website to learn programming language C++?</code> | <code>Which is the best website to learn C++ Programming language for free?</code>                       | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 400
+- `per_device_eval_batch_size`: 400
+- `num_train_epochs`: 100
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `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`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 400
+- `per_device_eval_batch_size`: 400
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-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`: 100
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `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`: None
+- `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`: 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 | mnrl loss  | cl loss    | quora-duplicates_cosine_ap | quora-duplicates-dev_average_precision | cosine_ndcg@10 |
+|:-------:|:-------:|:-------------:|:----------:|:----------:|:--------------------------:|:--------------------------------------:|:--------------:|
+| 0       | 0       | -             | -          | -          | 0.7461                     | 0.5988                                 | 0.9831         |
+| 0.2     | 100     | 0.2804        | -          | -          | -                          | -                                      | -              |
+| 0.4     | 200     | 0.2006        | -          | -          | -                          | -                                      | -              |
+| **0.5** | **250** | **-**         | **0.1153** | **0.0157** | **0.7661**                 | **0.6165**                             | **0.9839**     |
+| 0.6     | 300     | 0.1704        | -          | -          | -                          | -                                      | -              |
+| 0.8     | 400     | 0.1459        | -          | -          | -                          | -                                      | -              |
+| 1.0     | 500     | 0.1296        | 0.0835     | 0.0146     | 0.7860                     | 0.6238                                 | 0.9843         |
+| 1.2     | 600     | 0.1344        | -          | -          | -                          | -                                      | -              |
+| 1.4     | 700     | 0.1181        | -          | -          | -                          | -                                      | -              |
+| 1.5     | 750     | -             | 0.0737     | 0.0139     | 0.7983                     | 0.6263                                 | 0.9847         |
+| 1.6     | 800     | 0.1176        | -          | -          | -                          | -                                      | -              |
+| 1.8     | 900     | 0.119         | -          | -          | -                          | -                                      | -              |
+| 2.0     | 1000    | 0.1127        | 0.0682     | 0.0133     | 0.8121                     | 0.6287                                 | 0.9852         |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.9
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- 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",
+}
+```
+
+#### 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}
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,31 @@
+{
+  "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": "4.52.4",
+  "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": "2.7.0+cu126"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6510da6087f7e7976b49ffaa9f4ab1f43d7334dad1a8c8ff392184ad61761c51
+size 437951328

modules.json

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

sentence_bert_config.json

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

special_tokens_map.json

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

tokenizer_config.json

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