| --- |
| base_model: intfloat/multilingual-e5-large |
| 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:198 |
| - loss:MatryoshkaLoss |
| - loss:MultipleNegativesRankingLoss |
| widget: |
| - source_sentence: Najčešći tipovi uključuju iznad/ispod 2.5, ukupno golova, i klađenje |
| na broj golova u poluvremenima. |
| sentences: |
| - Koji su najčešći tipovi klađenja na golove? |
| - Koje kladionice u Srbiji nude DNB opciju? |
| - Šta je hendikep klađenje? |
| - source_sentence: Facebook grupe posvećene klađenju omogućavaju korisnicima da dobijaju |
| savete i predloge od velikih zajednica korisnika i kladioničara. |
| sentences: |
| - Šta je limit u klađenju? |
| - Kako se koristi Facebook za klađenje? |
| - Šta je cash-out opcija u uživo klađenju? |
| - source_sentence: Najčešći tipovi uključuju klađenje na konačan ishod, broj gemova, |
| broj setova, i klađenje uživo. |
| sentences: |
| - Koje su prednosti praćenja utakmica uživo? |
| - Koji su najčešći tipovi klađenja na tenis? |
| - Šta je e-novčanik? |
| - source_sentence: Premijum provizija je dodatna naknada koju berze kvota mogu naplatiti |
| igračima za specifične usluge ili dobitke. |
| sentences: |
| - Šta je premijum provizija? |
| - Koje su strategije za uspešno uživo klađenje? |
| - Kako funkcioniše klađenje na ukupan broj poena timova? |
| - source_sentence: '''Super Jenki'' sistem uključuje pet događaja i 26 pojedinačnih |
| opklada, takođe poznat kao kanadski sistem.' |
| sentences: |
| - Šta je 'Super Jenki' sistem klađenja? |
| - Šta je procena verovatnoće? |
| - Kako klađenje uživo funkcioniše u tenisu? |
| model-index: |
| - name: SentenceTransformer based on intfloat/multilingual-e5-large |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 768 |
| type: dim_768 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.8260869565217391 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.9565217391304348 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 1.0 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.8260869565217391 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.31884057971014484 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.20000000000000007 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000003 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.8260869565217391 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.9565217391304348 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 1.0 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9271072095125116 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.9021739130434783 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.9021739130434783 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 512 |
| type: dim_512 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.8695652173913043 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 1.0 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 1.0 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.8695652173913043 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.3333333333333332 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.20000000000000007 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000003 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.8695652173913043 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 1.0 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 1.0 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9461678046583877 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.9275362318840579 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.9275362318840579 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 256 |
| type: dim_256 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.8260869565217391 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 1.0 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 1.0 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.8260869565217391 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.3333333333333332 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.20000000000000007 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000003 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.8260869565217391 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 1.0 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 1.0 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9301212722049728 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.9057971014492753 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.9057971014492753 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 128 |
| type: dim_128 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.782608695652174 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.9565217391304348 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 1.0 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.782608695652174 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.31884057971014484 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.20000000000000007 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000003 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.782608695652174 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.9565217391304348 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 1.0 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9091552965878422 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.8782608695652173 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.8782608695652173 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 64 |
| type: dim_64 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.8260869565217391 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.9565217391304348 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.9565217391304348 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 1.0 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.8260869565217391 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.31884057971014484 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.19130434782608702 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.10000000000000003 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.8260869565217391 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.9565217391304348 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.9565217391304348 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 1.0 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.9164054079968976 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.8894927536231884 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.8894927536231884 |
| name: Cosine Map@100 |
| --- |
| |
| # SentenceTransformer based on intfloat/multilingual-e5-large |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) on the json dataset. It maps sentences & paragraphs to a 1024-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) <!-- at revision ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb --> |
| - **Maximum Sequence Length:** 512 tokens |
| - **Output Dimensionality:** 1024 tokens |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - json |
| <!-- - **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': False}) with Transformer model: XLMRobertaModel |
| (1): Pooling({'word_embedding_dimension': 1024, '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("luka023/proba") |
| # Run inference |
| sentences = [ |
| "'Super Jenki' sistem uključuje pet događaja i 26 pojedinačnih opklada, takođe poznat kao kanadski sistem.", |
| "Šta je 'Super Jenki' sistem klađenja?", |
| 'Kako klađenje uživo funkcioniše u tenisu?', |
| ] |
| embeddings = model.encode(sentences) |
| print(embeddings.shape) |
| # [3, 1024] |
| |
| # 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_768` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
| | Metric | Value | |
| |:--------------------|:-----------| |
| | cosine_accuracy@1 | 0.8261 | |
| | cosine_accuracy@3 | 0.9565 | |
| | cosine_accuracy@5 | 1.0 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_precision@1 | 0.8261 | |
| | cosine_precision@3 | 0.3188 | |
| | cosine_precision@5 | 0.2 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.8261 | |
| | cosine_recall@3 | 0.9565 | |
| | cosine_recall@5 | 1.0 | |
| | cosine_recall@10 | 1.0 | |
| | cosine_ndcg@10 | 0.9271 | |
| | cosine_mrr@10 | 0.9022 | |
| | **cosine_map@100** | **0.9022** | |
| |
| #### Information Retrieval |
| * Dataset: `dim_512` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
| |
| | Metric | Value | |
| |:--------------------|:-----------| |
| | cosine_accuracy@1 | 0.8696 | |
| | cosine_accuracy@3 | 1.0 | |
| | cosine_accuracy@5 | 1.0 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_precision@1 | 0.8696 | |
| | cosine_precision@3 | 0.3333 | |
| | cosine_precision@5 | 0.2 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.8696 | |
| | cosine_recall@3 | 1.0 | |
| | cosine_recall@5 | 1.0 | |
| | cosine_recall@10 | 1.0 | |
| | cosine_ndcg@10 | 0.9462 | |
| | cosine_mrr@10 | 0.9275 | |
| | **cosine_map@100** | **0.9275** | |
| |
| #### 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 | 0.8261 | |
| | cosine_accuracy@3 | 1.0 | |
| | cosine_accuracy@5 | 1.0 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_precision@1 | 0.8261 | |
| | cosine_precision@3 | 0.3333 | |
| | cosine_precision@5 | 0.2 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.8261 | |
| | cosine_recall@3 | 1.0 | |
| | cosine_recall@5 | 1.0 | |
| | cosine_recall@10 | 1.0 | |
| | cosine_ndcg@10 | 0.9301 | |
| | cosine_mrr@10 | 0.9058 | |
| | **cosine_map@100** | **0.9058** | |
| |
| #### 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 | 0.7826 | |
| | cosine_accuracy@3 | 0.9565 | |
| | cosine_accuracy@5 | 1.0 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_precision@1 | 0.7826 | |
| | cosine_precision@3 | 0.3188 | |
| | cosine_precision@5 | 0.2 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.7826 | |
| | cosine_recall@3 | 0.9565 | |
| | cosine_recall@5 | 1.0 | |
| | cosine_recall@10 | 1.0 | |
| | cosine_ndcg@10 | 0.9092 | |
| | cosine_mrr@10 | 0.8783 | |
| | **cosine_map@100** | **0.8783** | |
| |
| #### 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 | 0.8261 | |
| | cosine_accuracy@3 | 0.9565 | |
| | cosine_accuracy@5 | 0.9565 | |
| | cosine_accuracy@10 | 1.0 | |
| | cosine_precision@1 | 0.8261 | |
| | cosine_precision@3 | 0.3188 | |
| | cosine_precision@5 | 0.1913 | |
| | cosine_precision@10 | 0.1 | |
| | cosine_recall@1 | 0.8261 | |
| | cosine_recall@3 | 0.9565 | |
| | cosine_recall@5 | 0.9565 | |
| | cosine_recall@10 | 1.0 | |
| | cosine_ndcg@10 | 0.9164 | |
| | cosine_mrr@10 | 0.8895 | |
| | **cosine_map@100** | **0.8895** | |
| |
| <!-- |
| ## 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: 198 training samples |
| * Columns: <code>positive</code> and <code>anchor</code> |
| * Approximate statistics based on the first 198 samples: |
| | | positive | anchor | |
| |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | string | string | |
| | details | <ul><li>min: 19 tokens</li><li>mean: 33.76 tokens</li><li>max: 53 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.87 tokens</li><li>max: 21 tokens</li></ul> | |
| * Samples: |
| | positive | anchor | |
| |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------| |
| | <code>Klađenje na ukupan broj poena timova podrazumeva predviđanje da li će jedan tim postići više ili manje poena od postavljene granice, nezavisno od konačnog ishoda.</code> | <code>Kako funkcioniše klađenje na ukupan broj poena timova?</code> | |
| | <code>Konačan ishod podrazumeva klađenje na to ko će pobediti u utakmici, pri čemu postoje tri mogućnosti: pobeda domaćina, pobeda gosta ili nerešeno.</code> | <code>Šta znači klađenje na konačan ishod?</code> | |
| | <code>Patent opklada uključuje tri događaja sa ukupno sedam pojedinačnih opklada: tri singl, tri dubl i jedna trostruka opklada.</code> | <code>Šta je patent opklada?</code> | |
| * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: |
| ```json |
| { |
| "loss": "MultipleNegativesRankingLoss", |
| "matryoshka_dims": [ |
| 768, |
| 512, |
| 256, |
| 128, |
| 64 |
| ], |
| "matryoshka_weights": [ |
| 1, |
| 1, |
| 1, |
| 1, |
| 1 |
| ], |
| "n_dims_per_step": -1 |
| } |
| ``` |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
| |
| - `eval_strategy`: epoch |
| - `per_device_train_batch_size`: 32 |
| - `per_device_eval_batch_size`: 16 |
| - `gradient_accumulation_steps`: 16 |
| - `learning_rate`: 2e-05 |
| - `num_train_epochs`: 4 |
| - `lr_scheduler_type`: cosine |
| - `warmup_ratio`: 0.1 |
| - `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`: 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 |
| - `eval_on_start`: False |
| - `eval_use_gather_object`: False |
| - `batch_sampler`: no_duplicates |
| - `multi_dataset_batch_sampler`: proportional |
| |
| </details> |
| |
| ### Training Logs |
| | Epoch | Step | dim_128_cosine_map@100 | dim_256_cosine_map@100 | dim_512_cosine_map@100 | dim_64_cosine_map@100 | dim_768_cosine_map@100 | |
| |:-------:|:-----:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|:----------------------:| |
| | 1.0 | 1 | 0.6717 | 0.7663 | 0.8229 | 0.5755 | 0.8242 | |
| | **2.0** | **2** | **0.7779** | **0.8457** | **0.8638** | **0.7833** | **0.8635** | |
| | 3.0 | 4 | 0.8410 | 0.8732 | 0.8674 | 0.8167 | 0.8659 | |
| | 1.0 | 1 | 0.8410 | 0.8732 | 0.8674 | 0.8167 | 0.8659 | |
| | **2.0** | **2** | **0.8845** | **0.8732** | **0.9022** | **0.858** | **0.9022** | |
| | 3.0 | 4 | 0.8783 | 0.9058 | 0.9275 | 0.8895 | 0.9022 | |
|
|
| * The bold row denotes the saved checkpoint. |
|
|
| ### Framework Versions |
| - Python: 3.10.12 |
| - Sentence Transformers: 3.1.0 |
| - Transformers: 4.44.2 |
| - PyTorch: 2.4.0+cu121 |
| - Accelerate: 0.33.0 |
| - Datasets: 3.0.0 |
| - 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.* |
| --> |
