| --- |
| language: |
| - nep |
| license: apache-2.0 |
| tags: |
| - sentence-transformers |
| - sentence-similarity |
| - feature-extraction |
| - generated_from_trainer |
| - dataset_size:1046 |
| - loss:MatryoshkaLoss |
| - loss:MultipleNegativesRankingLoss |
| base_model: jangedoo/all-MiniLM-L6-v2-nepali |
| widget: |
| - source_sentence: राहदानीको लागि कागजात सत्यापनमा कस्तो मनोनयनपत्र चाहिन्छ? |
| sentences: |
| - सिम्यान्स अभिलेख किताबको लागि निवेदन फाराम अनुसूची-२क बमोजिमको ढाँचामा आधारित |
| हुन्छ। |
| - कुटनीतिक वा विशेष राहदानीको लागि कागजात सत्यापनमा सम्बन्धित पदमा नियुक्तिको मनोनयनपत्रको |
| प्रमाणित प्रतिलिपि चाहिन्छ। |
| - राहदानी रद्द गर्न महानिर्देशकले स्वीकृति दिन्छ। |
| - source_sentence: राहदानी वितरणमा त्रुटि सच्याउन कति समय लाग्छ? |
| sentences: |
| - राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपीलको |
| नतिजाको कार्यान्वयनको अभिलेख बाह्र वर्षसम्म राखिन्छ। |
| - राहदानी वितरणमा त्रुटि सच्याउन सामान्यतः सात कार्यदिन लाग्छ, तर प्रक्रिया जटिल |
| भएमा बढी समय लाग्न सक्छ। |
| - राहदानीको लागि निवेदनमा जाँच गर्ने अधिकारीको नाम, सही, पद, र मिति उल्लेख गर्नुपर्छ। |
| - source_sentence: राहदानीको लागि निवेदनमा कस्तो आवेदन स्रोत उल्लेख गर्नुपर्छ? |
| sentences: |
| - राहदानीको लागि निवेदनमा आवेदन स्रोत (विभाग, जिल्ला, वा नियोग) उल्लेख गर्नुपर्छ। |
| - राहदानी बुझाउने प्रक्रियामा त्रुटि सच्याउन सामान्यतः सात कार्यदिन लाग्छ, तर प्रक्रिया |
| जटिल भएमा बढी समय लाग्न सक्छ। |
| - राहदानीको लिए अनलाइन निवेदनमा निकटतम व्यक्तिसँगको सम्बन्ध (Relationship) उल्लेख |
| गर्नुपर्छ। |
| - source_sentence: विशेष राहदानी कसलाई जारी गरिन्छ? |
| sentences: |
| - राहदानी रद्द गर्न बाहक वा सम्बन्धित निकायको लिखित निवेदन चाहिन्छ। |
| - राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपीलको |
| लागि जाँच गर्ने अधिकारीको नाम, सही, पद, र मिति उल्लेख गर्नुपर्छ। |
| - विशेष राहदानी नगरपालिकाका प्रमुख, सहसचिव, जिल्ला न्यायाधीश, प्रदेश लोकसेवा आयोगका |
| सदस्य, लगायतका पदाधिकारीलाई जारी गरिन्छ। |
| - source_sentence: कुटनीतिक राहदानीको लागि निवेदनमा कस्तो ठेगाना विवरण चाहिन्छ? |
| sentences: |
| - कुटनीतिक राहदानीको लागि निवेदनमा जिल्ला, गाउँ/नगरपालिका, वडा नम्बर, गाउँ/सडक, |
| र घर नम्बरको ठेगाना विवरण चाहिन्छ। |
| - राहदानीको लागि कागजात धुल्याउने प्रक्रिया महानिर्देशकको स्वीकृतिमा हुन्छ। |
| - राहदानीको विद्युतीय अभिलेख अनुसूची-७ बमोजिमको ढाँचामा आधारित हुन्छ। |
| 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: sentenceTransformer_nepali_embedding |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 384 |
| type: dim_384 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.41025641025641024 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.6581196581196581 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.7350427350427351 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.8461538461538461 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.41025641025641024 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.21937321937321935 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.14700854700854699 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.0846153846153846 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.41025641025641024 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.6581196581196581 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.7350427350427351 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.8461538461538461 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.6218282635615644 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.5504409171075837 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.5571750406212126 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 256 |
| type: dim_256 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.42735042735042733 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.6410256410256411 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.717948717948718 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.8290598290598291 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.42735042735042733 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.21367521367521364 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.14358974358974358 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.08290598290598289 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.42735042735042733 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.6410256410256411 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.717948717948718 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.8290598290598291 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.6159996592171239 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.5487959571292905 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.5563599760664051 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 128 |
| type: dim_128 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.39316239316239315 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.5811965811965812 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.6752136752136753 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.8034188034188035 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.39316239316239315 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.19373219373219372 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.135042735042735 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.08034188034188033 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.39316239316239315 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.5811965811965812 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.6752136752136753 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.8034188034188035 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.5799237272193319 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.5100054266720935 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.5176470843483384 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 64 |
| type: dim_64 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.38461538461538464 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.5811965811965812 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.6410256410256411 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.7606837606837606 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.38461538461538464 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.1937321937321937 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.12820512820512817 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.07606837606837605 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.38461538461538464 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.5811965811965812 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.6410256410256411 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.7606837606837606 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.565217766093051 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.5036663953330621 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.5140223584530523 |
| name: Cosine Map@100 |
| --- |
| |
| # sentenceTransformer_nepali_embedding |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jangedoo/all-MiniLM-L6-v2-nepali](https://huggingface.co/jangedoo/all-MiniLM-L6-v2-nepali) 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:** [jangedoo/all-MiniLM-L6-v2-nepali](https://huggingface.co/jangedoo/all-MiniLM-L6-v2-nepali) <!-- at revision 418f7cf08ecbbc2ff0e8460bb6eb6457291102df --> |
| - **Maximum Sequence Length:** 256 tokens |
| - **Output Dimensionality:** 384 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - json |
| - **Language:** nep |
| - **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': 256, 'do_lower_case': False}) with Transformer model: BertModel |
| (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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("ritesh-07/fine_tuned_model_02") |
| # Run inference |
| sentences = [ |
| 'कुटनीतिक राहदानीको लागि निवेदनमा कस्तो ठेगाना विवरण चाहिन्छ?', |
| 'कुटनीतिक राहदानीको लागि निवेदनमा जिल्ला, गाउँ/नगरपालिका, वडा नम्बर, गाउँ/सडक, र घर नम्बरको ठेगाना विवरण चाहिन्छ।', |
| 'राहदानीको लागि कागजात धुल्याउने प्रक्रिया महानिर्देशकको स्वीकृतिमा हुन्छ।', |
| ] |
| 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) with these parameters: |
| ```json |
| { |
| "truncate_dim": 384 |
| } |
| ``` |
|
|
| | Metric | Value | |
| |:--------------------|:-----------| |
| | cosine_accuracy@1 | 0.4103 | |
| | cosine_accuracy@3 | 0.6581 | |
| | cosine_accuracy@5 | 0.735 | |
| | cosine_accuracy@10 | 0.8462 | |
| | cosine_precision@1 | 0.4103 | |
| | cosine_precision@3 | 0.2194 | |
| | cosine_precision@5 | 0.147 | |
| | cosine_precision@10 | 0.0846 | |
| | cosine_recall@1 | 0.4103 | |
| | cosine_recall@3 | 0.6581 | |
| | cosine_recall@5 | 0.735 | |
| | cosine_recall@10 | 0.8462 | |
| | **cosine_ndcg@10** | **0.6218** | |
| | cosine_mrr@10 | 0.5504 | |
| | cosine_map@100 | 0.5572 | |
| |
| #### 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 | 0.4274 | |
| | cosine_accuracy@3 | 0.641 | |
| | cosine_accuracy@5 | 0.7179 | |
| | cosine_accuracy@10 | 0.8291 | |
| | cosine_precision@1 | 0.4274 | |
| | cosine_precision@3 | 0.2137 | |
| | cosine_precision@5 | 0.1436 | |
| | cosine_precision@10 | 0.0829 | |
| | cosine_recall@1 | 0.4274 | |
| | cosine_recall@3 | 0.641 | |
| | cosine_recall@5 | 0.7179 | |
| | cosine_recall@10 | 0.8291 | |
| | **cosine_ndcg@10** | **0.616** | |
| | cosine_mrr@10 | 0.5488 | |
| | cosine_map@100 | 0.5564 | |
|
|
| #### 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 | 0.3932 | |
| | cosine_accuracy@3 | 0.5812 | |
| | cosine_accuracy@5 | 0.6752 | |
| | cosine_accuracy@10 | 0.8034 | |
| | cosine_precision@1 | 0.3932 | |
| | cosine_precision@3 | 0.1937 | |
| | cosine_precision@5 | 0.135 | |
| | cosine_precision@10 | 0.0803 | |
| | cosine_recall@1 | 0.3932 | |
| | cosine_recall@3 | 0.5812 | |
| | cosine_recall@5 | 0.6752 | |
| | cosine_recall@10 | 0.8034 | |
| | **cosine_ndcg@10** | **0.5799** | |
| | cosine_mrr@10 | 0.51 | |
| | cosine_map@100 | 0.5176 | |
| |
| #### 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 | 0.3846 | |
| | cosine_accuracy@3 | 0.5812 | |
| | cosine_accuracy@5 | 0.641 | |
| | cosine_accuracy@10 | 0.7607 | |
| | cosine_precision@1 | 0.3846 | |
| | cosine_precision@3 | 0.1937 | |
| | cosine_precision@5 | 0.1282 | |
| | cosine_precision@10 | 0.0761 | |
| | cosine_recall@1 | 0.3846 | |
| | cosine_recall@3 | 0.5812 | |
| | cosine_recall@5 | 0.641 | |
| | cosine_recall@10 | 0.7607 | |
| | **cosine_ndcg@10** | **0.5652** | |
| | cosine_mrr@10 | 0.5037 | |
| | cosine_map@100 | 0.514 | |
|
|
| <!-- |
| ## 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: 1,046 training samples |
| * Columns: <code>anchor</code> and <code>positive</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | anchor | positive | |
| |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| |
| | type | string | string | |
| | details | <ul><li>min: 18 tokens</li><li>mean: 40.9 tokens</li><li>max: 103 tokens</li></ul> | <ul><li>min: 23 tokens</li><li>mean: 65.74 tokens</li><li>max: 235 tokens</li></ul> | |
| * Samples: |
| | anchor | positive | |
| |:----------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------| |
| | <code>राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपील कसले जाँच गर्छ?</code> | <code>राहदानी नियमावली, २०७७ मा अभिलेखको गोपनीयताको उल्लङ्घनको जाँचको नतिजाको अपील मन्त्रालयले तोकेको समितिले जाँच गर्छ।</code> | |
| | <code>राहदानी नियमावली, २०७७ मा सत्यापनको लागि कस्तो सही चाहिन्छ?</code> | <code>राहदानी नियमावली, २०७७ मा सत्यापनको लागि निवेदकको सही, र नाबालकको हकमा बाबु, आमा, वा संरक्षकको सही चाहिन्छ।</code> | |
| | <code>राहदानी नियमावली, २०७७ मा कस्तो निकायले राहदानी जारी गर्छ?</code> | <code>राहदानी नियमावली, २०७७ मा विभाग, नियोग, वा जिल्ला प्रशासन कार्यालयले राहदानी जारी गर्छ।</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 |
| ], |
| "matryoshka_weights": [ |
| 1, |
| 1, |
| 1, |
| 1 |
| ], |
| "n_dims_per_step": -1 |
| } |
| ``` |
|
|
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
|
|
| - `eval_strategy`: epoch |
| - `per_device_train_batch_size`: 32 |
| - `per_device_eval_batch_size`: 16 |
| - `gradient_accumulation_steps`: 16 |
| - `learning_rate`: 2e-05 |
| - `num_train_epochs`: 4 |
| - `lr_scheduler_type`: cosine |
| - `warmup_ratio`: 0.1 |
| - `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`: 32 |
| - `per_device_eval_batch_size`: 16 |
| - `per_gpu_train_batch_size`: None |
| - `per_gpu_eval_batch_size`: None |
| - `gradient_accumulation_steps`: 16 |
| - `eval_accumulation_steps`: None |
| - `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 |
| - `hub_revision`: None |
| - `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 |
| - `liger_kernel_config`: None |
| - `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_384_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |
| |:-------:|:-----:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
| | 1.0 | 3 | - | 0.5232 | 0.5074 | 0.4679 | 0.4451 | |
| | 2.0 | 6 | - | 0.5891 | 0.5703 | 0.5555 | 0.5275 | |
| | **3.0** | **9** | **-** | **0.6108** | **0.6052** | **0.5815** | **0.5594** | |
| | 3.4848 | 10 | 2.5112 | - | - | - | - | |
| | 4.0 | 12 | - | 0.6218 | 0.6160 | 0.5799 | 0.5652 | |
|
|
| * The bold row denotes the saved checkpoint. |
|
|
| ### Framework Versions |
| - Python: 3.11.13 |
| - Sentence Transformers: 4.1.0 |
| - Transformers: 4.53.2 |
| - PyTorch: 2.6.0+cu124 |
| - Accelerate: 1.9.0 |
| - Datasets: 4.0.0 |
| - Tokenizers: 0.21.2 |
|
|
| ## 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.* |
| --> |
