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 +1,851 @@
+---
+datasets: []
+language: []
+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
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:14593
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+widget:
+- source_sentence: 'Macro ingredients needed to cook Poha: Orange Carrot, French Bean,
+    Fresh Green Pea, Medium Poha, Red Onion, Curry Leaf, Green Chili Pepper'
+  sentences:
+  - Can you list recipes that contain canned chickpea and canned black bean?
+  - What are the leading macro ingredients in Pigeon Pea Curry (Toor Dal)?
+  - What macro ingredients form the base of Poha?
+- source_sentence: 'I do have some good recommendations for you! Here are few good
+    alternatives to kashmiri pulao:
+
+    Kashmiri Dum Aloo, Shivani''s Kashmiri Dum Aloo, Chicken Pulao, Chicken Rezala,
+    Chicken Kheema Masala, Hyderabadi Chicken Masala, Masala Khichdi, Lentils and
+    Rice (Dal Chawal), Homestyle Vegetable Pulao'
+  sentences:
+  - What recipes are comparable to kashmiri pulao in flavor profile?
+  - Can you give me step-by-step instructions to cook Hariyali Chicken Curry?
+  - What are some recipes that utilize baking soda and olive oil effectively?
+- source_sentence: 'Garnishing tip for Yellow Rice: Sprinkle with chopped cilantro.'
+  sentences:
+  - How can I make Yellow Rice look appealing with garnishes?
+  - Describe General Tso's Tofu for me.
+  - What are the best garnishing tips for Paneer Tikka Masala?
+- source_sentence: 'Recipes that can be made using green chili pepper and grated coconut:
+    Kerala Mix Vegetables (Aviyal), Carrot Poriyal, Cauliflower Poriyal, Beetroot
+    Poriyal, Maithilee''s Fish Curry, Mix Vegetable Poriyal, Ivy Gourd Curry (Tindora
+    Masala), Spiced Indian Moth Beans (Matki Usal), Fish Curry, Andhra Garlic Chicken'
+  sentences:
+  - What are the culinary uses of ground pork and chayote?
+  - What are the dishes prepared using green cardamom and clove?
+  - Can you suggest recipes that include green chili pepper and grated coconut?
+- source_sentence: 'Recipes that can be made using red onion and paprika: Breakfast
+    Potatoes with Sausage, Peri Peri Chicken Pasta, Scrambled Egg Curry, Chili Mac
+    & Cheese, Tomato Chicken Curry'
+  sentences:
+  - Are there dishes that closely resemble spiced potatoes & fenugreek (aloo methi)?
+  - What recipes incorporate black pepper and habanero chili in their ingredients?
+  - What are some ways to use red onion and paprika in recipes?
+model-index:
+- name: SentenceTransformer
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 384
+      type: dim_384
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9704069050554871
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9926017262638718
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.998766954377312
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9993834771886559
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9704069050554871
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.33086724208795726
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1997533908754624
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09993834771886559
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9704069050554871
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9926017262638718
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.998766954377312
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9993834771886559
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9865445143406266
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9822089131583582
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9822089131583582
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9728729963008631
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9932182490752158
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.998766954377312
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9993834771886559
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9728729963008631
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3310727496917386
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1997533908754624
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09993834771886559
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9728729963008631
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9932182490752158
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.998766954377312
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9993834771886559
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9875922381599775
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9836107685984382
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9836107685984381
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9722564734895192
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9944512946979038
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9993834771886559
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9993834771886559
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9722564734895192
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.33148376489930126
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19987669543773118
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09993834771886559
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9722564734895192
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9944512946979038
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9993834771886559
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9993834771886559
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9873346466071089
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9832511302918208
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9832511302918209
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9704069050554871
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9944512946979038
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9993834771886559
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9993834771886559
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9704069050554871
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.33148376489930126
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19987669543773118
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09993834771886559
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9704069050554871
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9944512946979038
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9993834771886559
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9993834771886559
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9867057287670639
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9823982737361283
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9823982737361281
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 32
+      type: dim_32
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.971023427866831
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9950678175092479
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9993834771886559
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9993834771886559
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.971023427866831
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.3316892725030826
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19987669543773118
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09993834771886559
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.971023427866831
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9950678175092479
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9993834771886559
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9993834771886559
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9872988931953259
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9831689272503082
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9831689272503081
+      name: Cosine Map@100
+---
+
+# SentenceTransformer
+
+This is a [sentence-transformers](https://www.SBERT.net) model trained. 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:** [Unknown](https://huggingface.co/unknown) -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **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': 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("Adi-0-0-Gupta/Embedding-v1")
+# Run inference
+sentences = [
+    'Recipes that can be made using red onion and paprika: Breakfast Potatoes with Sausage, Peri Peri Chicken Pasta, Scrambled Egg Curry, Chili Mac & Cheese, Tomato Chicken Curry',
+    'What are some ways to use red onion and paprika in recipes?',
+    'Are there dishes that closely resemble spiced potatoes & fenugreek (aloo methi)?',
+]
+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_384`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9704     |
+| cosine_accuracy@3   | 0.9926     |
+| cosine_accuracy@5   | 0.9988     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.9704     |
+| cosine_precision@3  | 0.3309     |
+| cosine_precision@5  | 0.1998     |
+| cosine_precision@10 | 0.0999     |
+| cosine_recall@1     | 0.9704     |
+| cosine_recall@3     | 0.9926     |
+| cosine_recall@5     | 0.9988     |
+| cosine_recall@10    | 0.9994     |
+| cosine_ndcg@10      | 0.9865     |
+| cosine_mrr@10       | 0.9822     |
+| **cosine_map@100**  | **0.9822** |
+
+#### Information Retrieval
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9729     |
+| cosine_accuracy@3   | 0.9932     |
+| cosine_accuracy@5   | 0.9988     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.9729     |
+| cosine_precision@3  | 0.3311     |
+| cosine_precision@5  | 0.1998     |
+| cosine_precision@10 | 0.0999     |
+| cosine_recall@1     | 0.9729     |
+| cosine_recall@3     | 0.9932     |
+| cosine_recall@5     | 0.9988     |
+| cosine_recall@10    | 0.9994     |
+| cosine_ndcg@10      | 0.9876     |
+| cosine_mrr@10       | 0.9836     |
+| **cosine_map@100**  | **0.9836** |
+
+#### Information Retrieval
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9723     |
+| cosine_accuracy@3   | 0.9945     |
+| cosine_accuracy@5   | 0.9994     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.9723     |
+| cosine_precision@3  | 0.3315     |
+| cosine_precision@5  | 0.1999     |
+| cosine_precision@10 | 0.0999     |
+| cosine_recall@1     | 0.9723     |
+| cosine_recall@3     | 0.9945     |
+| cosine_recall@5     | 0.9994     |
+| cosine_recall@10    | 0.9994     |
+| cosine_ndcg@10      | 0.9873     |
+| cosine_mrr@10       | 0.9833     |
+| **cosine_map@100**  | **0.9833** |
+
+#### Information Retrieval
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9704     |
+| cosine_accuracy@3   | 0.9945     |
+| cosine_accuracy@5   | 0.9994     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.9704     |
+| cosine_precision@3  | 0.3315     |
+| cosine_precision@5  | 0.1999     |
+| cosine_precision@10 | 0.0999     |
+| cosine_recall@1     | 0.9704     |
+| cosine_recall@3     | 0.9945     |
+| cosine_recall@5     | 0.9994     |
+| cosine_recall@10    | 0.9994     |
+| cosine_ndcg@10      | 0.9867     |
+| cosine_mrr@10       | 0.9824     |
+| **cosine_map@100**  | **0.9824** |
+
+#### Information Retrieval
+* Dataset: `dim_32`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.971      |
+| cosine_accuracy@3   | 0.9951     |
+| cosine_accuracy@5   | 0.9994     |
+| cosine_accuracy@10  | 0.9994     |
+| cosine_precision@1  | 0.971      |
+| cosine_precision@3  | 0.3317     |
+| cosine_precision@5  | 0.1999     |
+| cosine_precision@10 | 0.0999     |
+| cosine_recall@1     | 0.971      |
+| cosine_recall@3     | 0.9951     |
+| cosine_recall@5     | 0.9994     |
+| cosine_recall@10    | 0.9994     |
+| cosine_ndcg@10      | 0.9873     |
+| cosine_mrr@10       | 0.9832     |
+| **cosine_map@100**  | **0.9832** |
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+
+* Size: 14,593 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: 11 tokens</li><li>mean: 53.46 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.83 tokens</li><li>max: 32 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                   | anchor                                                                            |
+  |:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | <code>Calories information of Hyderabadi Chicken Masala, based on different serving sizes: Serving 1 - 345 calories, Serving 2 - 580 calories, Serving 3 - 1220 calories, Serving 4 - 1450 calories</code> | <code>What’s the calorie content of Hyderabadi Chicken Masala?</code>             |
+  | <code>Recipes that can be made using dried herb mix and onion powder: Chorizo Queso Soup, Cheesy Chicken & Broccoli</code>                                                                                 | <code>What are some food items made using dried herb mix and onion powder?</code> |
+  | <code>Recipes that can be made using roasted semolina/bombay rava and saffron: Rashmi's Kesari Bath, Pineapple Kesari Bath</code>                                                                          | <code>What recipes have roasted semolina/bombay rava and saffron in them?</code>  |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          384,
+          256,
+          128,
+          64,
+          32
+      ],
+      "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`: 32
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 1e-05
+- `num_train_epochs`: 20
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `learning_rate`: 1e-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`: 20
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch   | Step | Training Loss | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_32_cosine_map@100 | dim_384_cosine_map@100 | dim_64_cosine_map@100 |
+|:-------:|:----:|:-------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:|:---------------------:|
+| 0.3501  | 10   | 0.0066        | -                      | -                      | -                     | -                      | -                     |
+| 0.7002  | 20   | 0.0056        | -                      | -                      | -                     | -                      | -                     |
+| 0.9803  | 28   | -             | 0.9746                 | 0.9771                 | 0.9776                | 0.9758                 | 0.9763                |
+| 1.0503  | 30   | 0.0057        | -                      | -                      | -                     | -                      | -                     |
+| 1.4004  | 40   | 0.0048        | -                      | -                      | -                     | -                      | -                     |
+| 1.7505  | 50   | 0.0039        | -                      | -                      | -                     | -                      | -                     |
+| 1.9956  | 57   | -             | 0.9783                 | 0.9787                 | 0.9815                | 0.9788                 | 0.9793                |
+| 2.1007  | 60   | 0.0046        | -                      | -                      | -                     | -                      | -                     |
+| 2.4508  | 70   | 0.0035        | -                      | -                      | -                     | -                      | -                     |
+| 2.8009  | 80   | 0.0028        | -                      | -                      | -                     | -                      | -                     |
+| 2.9759  | 85   | -             | 0.9818                 | 0.9811                 | 0.9836                | 0.9803                 | 0.9823                |
+| 3.1510  | 90   | 0.0036        | -                      | -                      | -                     | -                      | -                     |
+| 3.5011  | 100  | 0.0033        | -                      | -                      | -                     | -                      | -                     |
+| 3.8512  | 110  | 0.0026        | -                      | -                      | -                     | -                      | -                     |
+| 3.9912  | 114  | -             | 0.9814                 | 0.9818                 | 0.9844                | 0.9814                 | 0.9821                |
+| 4.2013  | 120  | 0.0025        | -                      | -                      | -                     | -                      | -                     |
+| 4.5514  | 130  | 0.003         | -                      | -                      | -                     | -                      | -                     |
+| 4.9015  | 140  | 0.0027        | -                      | -                      | -                     | -                      | -                     |
+| 4.9716  | 142  | -             | 0.9825                 | 0.9819                 | 0.9844                | 0.9823                 | 0.9825                |
+| 5.2516  | 150  | 0.0024        | -                      | -                      | -                     | -                      | -                     |
+| 5.6018  | 160  | 0.0023        | -                      | -                      | -                     | -                      | -                     |
+| 5.9519  | 170  | 0.0024        | -                      | -                      | -                     | -                      | -                     |
+| 5.9869  | 171  | -             | 0.9831                 | 0.9826                 | 0.9846                | 0.9818                 | 0.9831                |
+| 6.3020  | 180  | 0.0025        | -                      | -                      | -                     | -                      | -                     |
+| 6.6521  | 190  | 0.0025        | -                      | -                      | -                     | -                      | -                     |
+| 6.9672  | 199  | -             | 0.9830                 | 0.9825                 | 0.9844                | 0.9823                 | 0.9831                |
+| 7.0022  | 200  | 0.0019        | -                      | -                      | -                     | -                      | -                     |
+| 7.3523  | 210  | 0.0022        | -                      | -                      | -                     | -                      | -                     |
+| 7.7024  | 220  | 0.0026        | -                      | -                      | -                     | -                      | -                     |
+| 7.9825  | 228  | -             | 0.9828                 | 0.9825                 | 0.9836                | 0.9821                 | 0.9821                |
+| 8.0525  | 230  | 0.0022        | -                      | -                      | -                     | -                      | -                     |
+| 8.4026  | 240  | 0.0021        | -                      | -                      | -                     | -                      | -                     |
+| 8.7527  | 250  | 0.0021        | -                      | -                      | -                     | -                      | -                     |
+| 8.9978  | 257  | -             | 0.9827                 | 0.9826                 | 0.9848                | 0.9827                 | 0.9827                |
+| 9.1028  | 260  | 0.0025        | -                      | -                      | -                     | -                      | -                     |
+| 9.4530  | 270  | 0.0022        | -                      | -                      | -                     | -                      | -                     |
+| 9.8031  | 280  | 0.0019        | -                      | -                      | -                     | -                      | -                     |
+| 9.9781  | 285  | -             | 0.9832                 | 0.9833                 | 0.9858                | 0.9825                 | 0.9834                |
+| 10.1532 | 290  | 0.0021        | -                      | -                      | -                     | -                      | -                     |
+| 10.5033 | 300  | 0.0019        | -                      | -                      | -                     | -                      | -                     |
+| 10.8534 | 310  | 0.0024        | -                      | -                      | -                     | -                      | -                     |
+| 10.9934 | 314  | -             | 0.9830                 | 0.9827                 | 0.9850                | 0.9825                 | 0.9829                |
+| 11.2035 | 320  | 0.0017        | -                      | -                      | -                     | -                      | -                     |
+| 11.5536 | 330  | 0.0017        | -                      | -                      | -                     | -                      | -                     |
+| 11.9037 | 340  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 11.9737 | 342  | -             | 0.9827                 | 0.9835                 | 0.9841                | 0.9826                 | 0.9827                |
+| 12.2538 | 350  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 12.6039 | 360  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 12.9540 | 370  | 0.0023        | -                      | -                      | -                     | -                      | -                     |
+| 12.9891 | 371  | -             | 0.9828                 | 0.9834                 | 0.9832                | 0.9826                 | 0.9823                |
+| 13.3042 | 380  | 0.0017        | -                      | -                      | -                     | -                      | -                     |
+| 13.6543 | 390  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 13.9694 | 399  | -             | 0.9830                 | 0.9831                 | 0.9838                | 0.9820                 | 0.9826                |
+| 14.0044 | 400  | 0.0016        | -                      | -                      | -                     | -                      | -                     |
+| 14.3545 | 410  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 14.7046 | 420  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 14.9847 | 428  | -             | 0.9827                 | 0.9825                 | 0.9832                | 0.9816                 | 0.9826                |
+| 15.0547 | 430  | 0.0018        | -                      | -                      | -                     | -                      | -                     |
+| 15.4048 | 440  | 0.0015        | -                      | -                      | -                     | -                      | -                     |
+| 15.7549 | 450  | 0.0017        | -                      | -                      | -                     | -                      | -                     |
+| 16.0    | 457  | -             | 0.9833                 | 0.9836                 | 0.9832                | 0.9822                 | 0.9824                |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.41.2
+- PyTorch: 2.1.2+cu121
+- Accelerate: 0.31.0
+- Datasets: 2.19.1
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning}, 
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "../Output/Finetuned/checkpoint-457/",
+  "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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.41.2",
+    "pytorch": "2.1.2+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc55e025fd21dbda8e1dc0872cf532ab0b0a5cc8677cac20ac605d3efd996d96
+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 +1,64 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}