| --- |
| base_model: BAAI/bge-base-en-v1.5 |
| language: |
| - en |
| library_name: sentence-transformers |
| license: apache-2.0 |
| 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:56355 |
| - loss:MatryoshkaLoss |
| - loss:MultipleNegativesRankingLoss |
| widget: |
| - source_sentence: "\n Given the Column informations, generate an SQL query for\ |
| \ the following question:\n Column: Finishing position | Points awarded (Platinum)\ |
| \ | Points awarded (Gold) | Points awarded (Silver) | Points awarded (Satellite)\n\ |
| \ Question: How many platinum points were awarded when 6 gold points were awarded?\n\ |
| \ SQL Query: SELECT MAX Points awarded (Platinum) FROM table WHERE Points awarded\ |
| \ (Gold) = 6\n " |
| sentences: |
| - How many platinum points were awarded when 6 gold points were awarded? |
| - Did any team score games that totaled up to 860.5? |
| - Who had the pole position at the German Grand Prix? |
| - source_sentence: "\n Given the Column informations, generate an SQL query for\ |
| \ the following question:\n Column: Player | No. | Nationality | Position | Years\ |
| \ in Toronto | School/Club Team\n Question: What's Dell Curry nationality?\n\ |
| \ SQL Query: SELECT Nationality FROM table WHERE Player = Dell Curry\n " |
| sentences: |
| - What is the title when original air date is may15,2008? |
| - What's Dell Curry nationality? |
| - What's the minimum total attendance of the Premier League association football? |
| - source_sentence: "\n Given the Column informations, generate an SQL query for\ |
| \ the following question:\n Column: Sepal length | Sepal width | Petal length\ |
| \ | Petal width | Species\n Question: Name the species when petal width is 2.0\ |
| \ and petal length is 4.9\n SQL Query: SELECT Species FROM table WHERE Petal\ |
| \ width = 2.0 AND Petal length = 4.9\n " |
| sentences: |
| - What year was the championship in Wimbledon (2)? |
| - Who wrote Series 38? |
| - Name the species when petal width is 2.0 and petal length is 4.9 |
| - source_sentence: "\n Given the Column informations, generate an SQL query for\ |
| \ the following question:\n Column: No. in season | No. in series | Title | Directed\ |
| \ by | Written by | Original air date | U.S. viewers (million)\n Question: How\ |
| \ many millions of U.S. viewers watched the episode that first aired on March\ |
| \ 31, 2013?\n SQL Query: SELECT U.S. viewers (million) FROM table WHERE Original\ |
| \ air date = March 31, 2013\n " |
| sentences: |
| - How many millions of U.S. viewers watched the episode that first aired on March |
| 31, 2013? |
| - How many viewers were there for the premier with 34 |
| - What is Bruce Cerone overall? |
| - source_sentence: "\n Given the Column informations, generate an SQL query for\ |
| \ the following question:\n Column: Nomination | Actors Name | Film Name | Director\ |
| \ | Country\n Question: What was the film Falling up nominated for?\n SQL Query:\ |
| \ SELECT Nomination FROM table WHERE Film Name = Falling Up\n " |
| sentences: |
| - What was the film Falling up nominated for? |
| - Who wrote an episode watched by 19.01 million US viewers? |
| - What player is on the Montreal Alouettes CFl team? |
| model-index: |
| - name: BGE base SQL Matryoshka |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 768 |
| type: dim_768 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.4676281647562665 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.4676281647562665 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.15656883738506108 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.09394130243103667 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.046970651215518334 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.4676281647562665 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.4697065121551833 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.4697065121551833 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.4697065121551833 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.46889822604232273 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.4686148549355503 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.4686406337350657 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 512 |
| type: dim_512 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.46775412520468573 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.46775412520468573 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.15656883738506108 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.09394130243103667 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.046970651215518334 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.46775412520468573 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.4697065121551833 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.4697065121551833 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.4697065121551833 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.4689612062665323 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.46869882856782963 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.4687237988187482 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 256 |
| type: dim_256 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.46750220430784734 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.46976949237939286 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.46750220430784734 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.15656883738506108 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.09394130243103667 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.04697694923793929 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.46750220430784734 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.4697065121551833 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.4697065121551833 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.46976949237939286 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.4688906637675648 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.4685833648234455 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.468602927990512 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 128 |
| type: dim_128 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.46769114498047615 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.4696435319309737 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.46976949237939286 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.46976949237939286 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.46769114498047615 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.1565478439769912 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.09395389847587858 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.04697694923793929 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.46769114498047615 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.4696435319309737 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.46976949237939286 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.46976949237939286 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.4689469541953942 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.468661040433304 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.4686773555936371 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 64 |
| type: dim_64 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.46775412520468573 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.4696435319309737 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.4696435319309737 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.4697065121551833 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.46775412520468573 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.1565478439769912 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.09392870638619474 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.046970651215518334 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.46775412520468573 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.4696435319309737 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.4696435319309737 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.4697065121551833 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.4689578301883334 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.468696204391821 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.46870770760703784 |
| name: Cosine Map@100 |
| --- |
| |
| # BGE base SQL Matryoshka |
|
|
| This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
|
|
| ## Model Details |
|
|
| ### Model Description |
| - **Model Type:** Sentence Transformer |
| - **Base model:** [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) <!-- at revision a5beb1e3e68b9ab74eb54cfd186867f64f240e1a --> |
| - **Maximum Sequence Length:** 512 tokens |
| - **Output Dimensionality:** 768 dimensions |
| - **Similarity Function:** Cosine Similarity |
| - **Training Dataset:** |
| - json |
| - **Language:** en |
| - **License:** apache-2.0 |
|
|
| ### Model Sources |
|
|
| - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
| - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
|
|
| ### Full Model Architecture |
|
|
| ``` |
| SentenceTransformer( |
| (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel |
| (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
| (2): Normalize() |
| ) |
| ``` |
|
|
| ## Usage |
|
|
| ### Direct Usage (Sentence Transformers) |
|
|
| First install the Sentence Transformers library: |
|
|
| ```bash |
| pip install -U sentence-transformers |
| ``` |
|
|
| Then you can load this model and run inference. |
| ```python |
| from sentence_transformers import SentenceTransformer |
| |
| # Download from the 🤗 Hub |
| model = SentenceTransformer("dat-ai/bge-base-for_text2sql") |
| # Run inference |
| sentences = [ |
| '\n Given the Column informations, generate an SQL query for the following question:\n Column: Nomination | Actors Name | Film Name | Director | Country\n Question: What was the film Falling up nominated for?\n SQL Query: SELECT Nomination FROM table WHERE Film Name = Falling Up\n ', |
| 'What was the film Falling up nominated for?', |
| 'Who wrote an episode watched by 19.01 million US viewers?', |
| ] |
| embeddings = model.encode(sentences) |
| print(embeddings.shape) |
| # [3, 768] |
| |
| # Get the similarity scores for the embeddings |
| similarities = model.similarity(embeddings, embeddings) |
| print(similarities.shape) |
| # [3, 3] |
| ``` |
|
|
| <!-- |
| ### Direct Usage (Transformers) |
|
|
| <details><summary>Click to see the direct usage in Transformers</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Downstream Usage (Sentence Transformers) |
|
|
| You can finetune this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| </details> |
| --> |
|
|
| <!-- |
| ### Out-of-Scope Use |
|
|
| *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| --> |
|
|
| ## Evaluation |
|
|
| ### Metrics |
|
|
| #### Information Retrieval |
|
|
| * Datasets: `dim_768`, `dim_512`, `dim_256`, `dim_128` and `dim_64` |
| * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) |
|
|
| | Metric | dim_768 | dim_512 | dim_256 | dim_128 | dim_64 | |
| |:--------------------|:-----------|:----------|:-----------|:-----------|:----------| |
| | cosine_accuracy@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 | |
| | cosine_accuracy@3 | 0.4697 | 0.4697 | 0.4697 | 0.4696 | 0.4696 | |
| | cosine_accuracy@5 | 0.4697 | 0.4697 | 0.4697 | 0.4698 | 0.4696 | |
| | cosine_accuracy@10 | 0.4697 | 0.4697 | 0.4698 | 0.4698 | 0.4697 | |
| | cosine_precision@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 | |
| | cosine_precision@3 | 0.1566 | 0.1566 | 0.1566 | 0.1565 | 0.1565 | |
| | cosine_precision@5 | 0.0939 | 0.0939 | 0.0939 | 0.094 | 0.0939 | |
| | cosine_precision@10 | 0.047 | 0.047 | 0.047 | 0.047 | 0.047 | |
| | cosine_recall@1 | 0.4676 | 0.4678 | 0.4675 | 0.4677 | 0.4678 | |
| | cosine_recall@3 | 0.4697 | 0.4697 | 0.4697 | 0.4696 | 0.4696 | |
| | cosine_recall@5 | 0.4697 | 0.4697 | 0.4697 | 0.4698 | 0.4696 | |
| | cosine_recall@10 | 0.4697 | 0.4697 | 0.4698 | 0.4698 | 0.4697 | |
| | **cosine_ndcg@10** | **0.4689** | **0.469** | **0.4689** | **0.4689** | **0.469** | |
| | cosine_mrr@10 | 0.4686 | 0.4687 | 0.4686 | 0.4687 | 0.4687 | |
| | cosine_map@100 | 0.4686 | 0.4687 | 0.4686 | 0.4687 | 0.4687 | |
| |
| <!-- |
| ## 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: 56,355 training samples |
| * Columns: <code>context</code> and <code>question</code> |
| * Approximate statistics based on the first 1000 samples: |
| | | context | question | |
| |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| |
| | type | string | string | |
| | details | <ul><li>min: 45 tokens</li><li>mean: 72.61 tokens</li><li>max: 196 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 15.41 tokens</li><li>max: 36 tokens</li></ul> | |
| * Samples: |
| | context | question | |
| |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| |
| | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: Tell me what the notes are for South Australia <br> SQL Query: SELECT Notes FROM table WHERE Current slogan = SOUTH AUSTRALIA<br> </code> | <code>Tell me what the notes are for South Australia </code> | |
| | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: What is the current series where the new series began in June 2011?<br> SQL Query: SELECT Current series FROM table WHERE Notes = New series began in June 2011<br> </code> | <code>What is the current series where the new series began in June 2011?</code> | |
| | <code><br> Given the Column informations, generate an SQL query for the following question:<br> Column: State/territory | Text/background colour | Format | Current slogan | Current series | Notes<br> Question: What is the format for South Australia?<br> SQL Query: SELECT Format FROM table WHERE State/territory = South Australia<br> </code> | <code>What is the format for South Australia?</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 |
| ], |
| "matryoshka_weights": [ |
| 1, |
| 1 |
| ], |
| "n_dims_per_step": -1 |
| } |
| ``` |
| |
| ### Training Hyperparameters |
| #### Non-Default Hyperparameters |
|
|
| - `eval_strategy`: epoch |
| - `per_device_train_batch_size`: 16 |
| - `gradient_accumulation_steps`: 8 |
| - `learning_rate`: 2e-05 |
| - `num_train_epochs`: 4 |
| - `lr_scheduler_type`: cosine |
| - `warmup_ratio`: 0.1 |
| - `fp16`: 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`: 16 |
| - `per_device_eval_batch_size`: 8 |
| - `per_gpu_train_batch_size`: None |
| - `per_gpu_eval_batch_size`: None |
| - `gradient_accumulation_steps`: 8 |
| - `eval_accumulation_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`: False |
| - `fp16`: True |
| - `fp16_opt_level`: O1 |
| - `half_precision_backend`: auto |
| - `bf16_full_eval`: False |
| - `fp16_full_eval`: False |
| - `tf32`: None |
| - `local_rank`: 0 |
| - `ddp_backend`: None |
| - `tpu_num_cores`: None |
| - `tpu_metrics_debug`: False |
| - `debug`: [] |
| - `dataloader_drop_last`: False |
| - `dataloader_num_workers`: 0 |
| - `dataloader_prefetch_factor`: None |
| - `past_index`: -1 |
| - `disable_tqdm`: False |
| - `remove_unused_columns`: True |
| - `label_names`: None |
| - `load_best_model_at_end`: True |
| - `ignore_data_skip`: False |
| - `fsdp`: [] |
| - `fsdp_min_num_params`: 0 |
| - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
| - `fsdp_transformer_layer_cls_to_wrap`: None |
| - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
| - `deepspeed`: None |
| - `label_smoothing_factor`: 0.0 |
| - `optim`: adamw_torch_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 |
| - `prompts`: None |
| - `batch_sampler`: no_duplicates |
| - `multi_dataset_batch_sampler`: proportional |
|
|
| </details> |
|
|
| ### Training Logs |
| <details><summary>Click to expand</summary> |
|
|
| | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |
| |:----------:|:--------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
| | 0.0227 | 10 | 1.773 | - | - | - | - | - | |
| | 0.0454 | 20 | 1.3231 | - | - | - | - | - | |
| | 0.0681 | 30 | 0.713 | - | - | - | - | - | |
| | 0.0908 | 40 | 0.286 | - | - | - | - | - | |
| | 0.1135 | 50 | 0.1013 | - | - | - | - | - | |
| | 0.1362 | 60 | 0.0635 | - | - | - | - | - | |
| | 0.1590 | 70 | 0.0453 | - | - | - | - | - | |
| | 0.1817 | 80 | 0.041 | - | - | - | - | - | |
| | 0.2044 | 90 | 0.039 | - | - | - | - | - | |
| | 0.2271 | 100 | 0.027 | - | - | - | - | - | |
| | 0.2498 | 110 | 0.0193 | - | - | - | - | - | |
| | 0.2725 | 120 | 0.0167 | - | - | - | - | - | |
| | 0.2952 | 130 | 0.016 | - | - | - | - | - | |
| | 0.3179 | 140 | 0.0197 | - | - | - | - | - | |
| | 0.3406 | 150 | 0.0217 | - | - | - | - | - | |
| | 0.3633 | 160 | 0.0162 | - | - | - | - | - | |
| | 0.3860 | 170 | 0.012 | - | - | - | - | - | |
| | 0.4087 | 180 | 0.013 | - | - | - | - | - | |
| | 0.4315 | 190 | 0.0255 | - | - | - | - | - | |
| | 0.4542 | 200 | 0.0229 | - | - | - | - | - | |
| | 0.4769 | 210 | 0.0181 | - | - | - | - | - | |
| | 0.4996 | 220 | 0.0195 | - | - | - | - | - | |
| | 0.5223 | 230 | 0.0199 | - | - | - | - | - | |
| | 0.5450 | 240 | 0.0144 | - | - | - | - | - | |
| | 0.5677 | 250 | 0.0102 | - | - | - | - | - | |
| | 0.5904 | 260 | 0.0101 | - | - | - | - | - | |
| | 0.6131 | 270 | 0.0095 | - | - | - | - | - | |
| | 0.6358 | 280 | 0.0173 | - | - | - | - | - | |
| | 0.6585 | 290 | 0.01 | - | - | - | - | - | |
| | 0.6812 | 300 | 0.0129 | - | - | - | - | - | |
| | 0.7039 | 310 | 0.0177 | - | - | - | - | - | |
| | 0.7267 | 320 | 0.0106 | - | - | - | - | - | |
| | 0.7494 | 330 | 0.0146 | - | - | - | - | - | |
| | 0.7721 | 340 | 0.0185 | - | - | - | - | - | |
| | 0.7948 | 350 | 0.0203 | - | - | - | - | - | |
| | 0.8175 | 360 | 0.0146 | - | - | - | - | - | |
| | 0.8402 | 370 | 0.0072 | - | - | - | - | - | |
| | 0.8629 | 380 | 0.0102 | - | - | - | - | - | |
| | 0.8856 | 390 | 0.0075 | - | - | - | - | - | |
| | 0.9083 | 400 | 0.0064 | - | - | - | - | - | |
| | 0.9310 | 410 | 0.0163 | - | - | - | - | - | |
| | 0.9537 | 420 | 0.0069 | - | - | - | - | - | |
| | 0.9764 | 430 | 0.0072 | - | - | - | - | - | |
| | 0.9991 | 440 | 0.0147 | 0.4688 | 0.4689 | 0.4688 | 0.4689 | 0.4689 | |
| | 1.0219 | 450 | 0.0151 | - | - | - | - | - | |
| | 1.0446 | 460 | 0.0135 | - | - | - | - | - | |
| | 1.0673 | 470 | 0.0189 | - | - | - | - | - | |
| | 1.0900 | 480 | 0.0121 | - | - | - | - | - | |
| | 1.1127 | 490 | 0.0064 | - | - | - | - | - | |
| | 1.1354 | 500 | 0.0111 | - | - | - | - | - | |
| | 1.1581 | 510 | 0.0103 | - | - | - | - | - | |
| | 1.1808 | 520 | 0.0144 | - | - | - | - | - | |
| | 1.2035 | 530 | 0.0151 | - | - | - | - | - | |
| | 1.2262 | 540 | 0.0062 | - | - | - | - | - | |
| | 1.2489 | 550 | 0.0104 | - | - | - | - | - | |
| | 1.2716 | 560 | 0.0046 | - | - | - | - | - | |
| | 1.2944 | 570 | 0.0056 | - | - | - | - | - | |
| | 1.3171 | 580 | 0.0073 | - | - | - | - | - | |
| | 1.3398 | 590 | 0.007 | - | - | - | - | - | |
| | 1.3625 | 600 | 0.0074 | - | - | - | - | - | |
| | 1.3852 | 610 | 0.0057 | - | - | - | - | - | |
| | 1.4079 | 620 | 0.0052 | - | - | - | - | - | |
| | 1.4306 | 630 | 0.0114 | - | - | - | - | - | |
| | 1.4533 | 640 | 0.0075 | - | - | - | - | - | |
| | 1.4760 | 650 | 0.0116 | - | - | - | - | - | |
| | 1.4987 | 660 | 0.0092 | - | - | - | - | - | |
| | 1.5214 | 670 | 0.0137 | - | - | - | - | - | |
| | 1.5441 | 680 | 0.0066 | - | - | - | - | - | |
| | 1.5668 | 690 | 0.0042 | - | - | - | - | - | |
| | 1.5896 | 700 | 0.0036 | - | - | - | - | - | |
| | 1.6123 | 710 | 0.0039 | - | - | - | - | - | |
| | 1.6350 | 720 | 0.0065 | - | - | - | - | - | |
| | 1.6577 | 730 | 0.0051 | - | - | - | - | - | |
| | 1.6804 | 740 | 0.0054 | - | - | - | - | - | |
| | 1.7031 | 750 | 0.0086 | - | - | - | - | - | |
| | 1.7258 | 760 | 0.0062 | - | - | - | - | - | |
| | 1.7485 | 770 | 0.0071 | - | - | - | - | - | |
| | 1.7712 | 780 | 0.0108 | - | - | - | - | - | |
| | 1.7939 | 790 | 0.009 | - | - | - | - | - | |
| | 1.8166 | 800 | 0.0075 | - | - | - | - | - | |
| | 1.8393 | 810 | 0.0039 | - | - | - | - | - | |
| | 1.8620 | 820 | 0.0047 | - | - | - | - | - | |
| | 1.8848 | 830 | 0.0037 | - | - | - | - | - | |
| | 1.9075 | 840 | 0.0037 | - | - | - | - | - | |
| | 1.9302 | 850 | 0.0064 | - | - | - | - | - | |
| | 1.9529 | 860 | 0.0047 | - | - | - | - | - | |
| | 1.9756 | 870 | 0.0034 | - | - | - | - | - | |
| | 1.9983 | 880 | 0.0061 | 0.4689 | 0.4689 | 0.4689 | 0.4690 | 0.4690 | |
| | 2.0210 | 890 | 0.0096 | - | - | - | - | - | |
| | 2.0437 | 900 | 0.0071 | - | - | - | - | - | |
| | 2.0664 | 910 | 0.0101 | - | - | - | - | - | |
| | 2.0891 | 920 | 0.0054 | - | - | - | - | - | |
| | 2.1118 | 930 | 0.0039 | - | - | - | - | - | |
| | 2.1345 | 940 | 0.0074 | - | - | - | - | - | |
| | 2.1573 | 950 | 0.0044 | - | - | - | - | - | |
| | 2.1800 | 960 | 0.0088 | - | - | - | - | - | |
| | 2.2027 | 970 | 0.0096 | - | - | - | - | - | |
| | 2.2254 | 980 | 0.0057 | - | - | - | - | - | |
| | 2.2481 | 990 | 0.0063 | - | - | - | - | - | |
| | 2.2708 | 1000 | 0.0026 | - | - | - | - | - | |
| | 2.2935 | 1010 | 0.0032 | - | - | - | - | - | |
| | 2.3162 | 1020 | 0.0027 | - | - | - | - | - | |
| | 2.3389 | 1030 | 0.0041 | - | - | - | - | - | |
| | 2.3616 | 1040 | 0.0052 | - | - | - | - | - | |
| | 2.3843 | 1050 | 0.0035 | - | - | - | - | - | |
| | 2.4070 | 1060 | 0.0025 | - | - | - | - | - | |
| | 2.4297 | 1070 | 0.0059 | - | - | - | - | - | |
| | 2.4525 | 1080 | 0.0048 | - | - | - | - | - | |
| | 2.4752 | 1090 | 0.0064 | - | - | - | - | - | |
| | 2.4979 | 1100 | 0.0066 | - | - | - | - | - | |
| | 2.5206 | 1110 | 0.0078 | - | - | - | - | - | |
| | 2.5433 | 1120 | 0.0057 | - | - | - | - | - | |
| | 2.5660 | 1130 | 0.0026 | - | - | - | - | - | |
| | 2.5887 | 1140 | 0.0021 | - | - | - | - | - | |
| | 2.6114 | 1150 | 0.0021 | - | - | - | - | - | |
| | 2.6341 | 1160 | 0.0047 | - | - | - | - | - | |
| | 2.6568 | 1170 | 0.0034 | - | - | - | - | - | |
| | 2.6795 | 1180 | 0.0044 | - | - | - | - | - | |
| | 2.7022 | 1190 | 0.0058 | - | - | - | - | - | |
| | 2.7250 | 1200 | 0.0043 | - | - | - | - | - | |
| | 2.7477 | 1210 | 0.0056 | - | - | - | - | - | |
| | 2.7704 | 1220 | 0.0076 | - | - | - | - | - | |
| | 2.7931 | 1230 | 0.0063 | - | - | - | - | - | |
| | 2.8158 | 1240 | 0.0033 | - | - | - | - | - | |
| | 2.8385 | 1250 | 0.0025 | - | - | - | - | - | |
| | 2.8612 | 1260 | 0.0019 | - | - | - | - | - | |
| | 2.8839 | 1270 | 0.0052 | - | - | - | - | - | |
| | 2.9066 | 1280 | 0.0021 | - | - | - | - | - | |
| | 2.9293 | 1290 | 0.0041 | - | - | - | - | - | |
| | 2.9520 | 1300 | 0.0035 | - | - | - | - | - | |
| | 2.9747 | 1310 | 0.0044 | - | - | - | - | - | |
| | 2.9974 | 1320 | 0.0035 | - | - | - | - | - | |
| | **2.9997** | **1321** | **-** | **0.469** | **0.469** | **0.469** | **0.469** | **0.469** | |
| | 3.0202 | 1330 | 0.0062 | - | - | - | - | - | |
| | 3.0429 | 1340 | 0.0047 | - | - | - | - | - | |
| | 3.0656 | 1350 | 0.008 | - | - | - | - | - | |
| | 3.0883 | 1360 | 0.0033 | - | - | - | - | - | |
| | 3.1110 | 1370 | 0.0025 | - | - | - | - | - | |
| | 3.1337 | 1380 | 0.0069 | - | - | - | - | - | |
| | 3.1564 | 1390 | 0.0035 | - | - | - | - | - | |
| | 3.1791 | 1400 | 0.0085 | - | - | - | - | - | |
| | 3.2018 | 1410 | 0.007 | - | - | - | - | - | |
| | 3.2245 | 1420 | 0.007 | - | - | - | - | - | |
| | 3.2472 | 1430 | 0.0052 | - | - | - | - | - | |
| | 3.2699 | 1440 | 0.0019 | - | - | - | - | - | |
| | 3.2926 | 1450 | 0.0022 | - | - | - | - | - | |
| | 3.3154 | 1460 | 0.0019 | - | - | - | - | - | |
| | 3.3381 | 1470 | 0.0028 | - | - | - | - | - | |
| | 3.3608 | 1480 | 0.0042 | - | - | - | - | - | |
| | 3.3835 | 1490 | 0.0023 | - | - | - | - | - | |
| | 3.4062 | 1500 | 0.0024 | - | - | - | - | - | |
| | 3.4289 | 1510 | 0.0036 | - | - | - | - | - | |
| | 3.4516 | 1520 | 0.0038 | - | - | - | - | - | |
| | 3.4743 | 1530 | 0.0063 | - | - | - | - | - | |
| | 3.4970 | 1540 | 0.0044 | - | - | - | - | - | |
| | 3.5197 | 1550 | 0.0064 | - | - | - | - | - | |
| | 3.5424 | 1560 | 0.0053 | - | - | - | - | - | |
| | 3.5651 | 1570 | 0.0019 | - | - | - | - | - | |
| | 3.5879 | 1580 | 0.0019 | - | - | - | - | - | |
| | 3.6106 | 1590 | 0.0017 | - | - | - | - | - | |
| | 3.6333 | 1600 | 0.004 | - | - | - | - | - | |
| | 3.6560 | 1610 | 0.0026 | - | - | - | - | - | |
| | 3.6787 | 1620 | 0.0031 | - | - | - | - | - | |
| | 3.7014 | 1630 | 0.0043 | - | - | - | - | - | |
| | 3.7241 | 1640 | 0.0032 | - | - | - | - | - | |
| | 3.7468 | 1650 | 0.0041 | - | - | - | - | - | |
| | 3.7695 | 1660 | 0.0069 | - | - | - | - | - | |
| | 3.7922 | 1670 | 0.0063 | - | - | - | - | - | |
| | 3.8149 | 1680 | 0.0038 | - | - | - | - | - | |
| | 3.8376 | 1690 | 0.0024 | - | - | - | - | - | |
| | 3.8603 | 1700 | 0.0018 | - | - | - | - | - | |
| | 3.8831 | 1710 | 0.0034 | - | - | - | - | - | |
| | 3.9058 | 1720 | 0.0016 | - | - | - | - | - | |
| | 3.9285 | 1730 | 0.0026 | - | - | - | - | - | |
| | 3.9512 | 1740 | 0.0037 | - | - | - | - | - | |
| | 3.9739 | 1750 | 0.0024 | - | - | - | - | - | |
| | 3.9966 | 1760 | 0.0027 | 0.4689 | 0.4690 | 0.4689 | 0.4689 | 0.4690 | |
| |
| * The bold row denotes the saved checkpoint. |
| </details> |
| |
| ### Framework Versions |
| - Python: 3.10.14 |
| - Sentence Transformers: 3.3.0 |
| - Transformers: 4.41.2 |
| - PyTorch: 2.1.2+cu121 |
| - Accelerate: 0.34.2 |
| - 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.* |
| --> |
