| --- |
| 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:6300 |
| - loss:MatryoshkaLoss |
| - loss:MultipleNegativesRankingLoss |
| widget: |
| - source_sentence: Item 8 includes Financial Statements and Supplementary Data. |
| sentences: |
| - What does the FDA label update for Yescarta include as of the latest approval? |
| - What information can be found in Item 8 of a document? |
| - When does the Company's fiscal year end? |
| - source_sentence: Item 8 in a financial document is designated for Financial Statements |
| and Supplementary Data. |
| sentences: |
| - What are the primary goals of AutoZone's store management system? |
| - What information is contained in Item 8 of a financial document? |
| - What were the pre-tax earnings of the manufacturing sector in 2023, 2022, and |
| 2021? |
| - source_sentence: of approximately $1.0 billion in IBNR liabilities, producing a |
| corresponding decrease in pre-tax earnings. We believe it is reasonably possible |
| for these assumptions to increase at these rates. |
| sentences: |
| - What was the decrease in pre-tax earnings due to the $1.0 billion in IBNR liabilities? |
| - What was the total long-term debt, including the current portion, for AbbVie as |
| of December 31, 2023? |
| - What feature dedicated AI hardware in an x86 processor and uses the XDNA architecture? |
| - source_sentence: In the year ended December 31, 2023, sellers generated GMS of $13.2 |
| billion, approximately 68% of which came from purchases made on mobile devices. |
| sentences: |
| - What was the change in the total balance of revolving credits from December 31, |
| 2022, to December 31, 2023? |
| - What are the purposes of borrowings under the 2021 credit facility? |
| - What percentage of Etsy's Gross Merchandise Sales (GMS) in 2023 came from mobile |
| purchases? |
| - source_sentence: As of December 31, 2023, approximately $1.80 billion is available |
| to be repatriated from Mainland China to the U.S. |
| sentences: |
| - What is the total amount of unrestricted cash available for repatriation from |
| Mainland China to the U.S. as of the end of 2023? |
| - What is the focus of the company's research and development efforts? |
| - Where does the Report of Independent Registered Public Accounting Firm begin in |
| this report? |
| model-index: |
| - name: BGE base Financial Matryoshka |
| results: |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 768 |
| type: dim_768 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.6771428571428572 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.8142857142857143 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.8642857142857143 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.9142857142857143 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.6771428571428572 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.2714285714285714 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.17285714285714282 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.09142857142857141 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.6771428571428572 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.8142857142857143 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.8642857142857143 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.9142857142857143 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.7948920706768223 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7568055555555551 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.7601580985784901 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 512 |
| type: dim_512 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.6714285714285714 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.8157142857142857 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.8657142857142858 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.92 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.6714285714285714 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.27190476190476187 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.17314285714285713 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.09199999999999998 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.6714285714285714 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.8157142857142857 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.8657142857142858 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.92 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.7936366054643341 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7534455782312921 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.756388193211117 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 256 |
| type: dim_256 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.6714285714285714 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.8157142857142857 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.8585714285714285 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.9157142857142857 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.6714285714285714 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.27190476190476187 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.1717142857142857 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.09157142857142857 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.6714285714285714 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.8157142857142857 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.8585714285714285 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.9157142857142857 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.7926136922070053 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7535062358276641 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.7564593466816174 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 128 |
| type: dim_128 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.6614285714285715 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.8 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.8414285714285714 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.8885714285714286 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.6614285714285715 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.26666666666666666 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.16828571428571426 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.08885714285714286 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.6614285714285715 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.8 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.8414285714285714 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.8885714285714286 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.7767052058983972 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7407840136054418 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.7454236920389576 |
| name: Cosine Map@100 |
| - task: |
| type: information-retrieval |
| name: Information Retrieval |
| dataset: |
| name: dim 64 |
| type: dim_64 |
| metrics: |
| - type: cosine_accuracy@1 |
| value: 0.6357142857142857 |
| name: Cosine Accuracy@1 |
| - type: cosine_accuracy@3 |
| value: 0.7742857142857142 |
| name: Cosine Accuracy@3 |
| - type: cosine_accuracy@5 |
| value: 0.8185714285714286 |
| name: Cosine Accuracy@5 |
| - type: cosine_accuracy@10 |
| value: 0.8642857142857143 |
| name: Cosine Accuracy@10 |
| - type: cosine_precision@1 |
| value: 0.6357142857142857 |
| name: Cosine Precision@1 |
| - type: cosine_precision@3 |
| value: 0.2580952380952381 |
| name: Cosine Precision@3 |
| - type: cosine_precision@5 |
| value: 0.1637142857142857 |
| name: Cosine Precision@5 |
| - type: cosine_precision@10 |
| value: 0.08642857142857142 |
| name: Cosine Precision@10 |
| - type: cosine_recall@1 |
| value: 0.6357142857142857 |
| name: Cosine Recall@1 |
| - type: cosine_recall@3 |
| value: 0.7742857142857142 |
| name: Cosine Recall@3 |
| - type: cosine_recall@5 |
| value: 0.8185714285714286 |
| name: Cosine Recall@5 |
| - type: cosine_recall@10 |
| value: 0.8642857142857143 |
| name: Cosine Recall@10 |
| - type: cosine_ndcg@10 |
| value: 0.7511926722277801 |
| name: Cosine Ndcg@10 |
| - type: cosine_mrr@10 |
| value: 0.7148713151927435 |
| name: Cosine Mrr@10 |
| - type: cosine_map@100 |
| value: 0.7199017346952273 |
| name: Cosine Map@100 |
| --- |
| |
| # BGE base Financial 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("SMARTICT/bge-base-financial-matryoshka") |
| # Run inference |
| sentences = [ |
| 'As of December 31, 2023, approximately $1.80 billion is available to be repatriated from Mainland China to the U.S.', |
| 'What is the total amount of unrestricted cash available for repatriation from Mainland China to the U.S. as of the end of 2023?', |
| "What is the focus of the company's research and development efforts?", |
| ] |
| 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 | 0.6771 | 0.6714 | 0.6714 | 0.6614 | 0.6357 | |
| | cosine_accuracy@3 | 0.8143 | 0.8157 | 0.8157 | 0.8 | 0.7743 | |
| | cosine_accuracy@5 | 0.8643 | 0.8657 | 0.8586 | 0.8414 | 0.8186 | |
| | cosine_accuracy@10 | 0.9143 | 0.92 | 0.9157 | 0.8886 | 0.8643 | |
| | cosine_precision@1 | 0.6771 | 0.6714 | 0.6714 | 0.6614 | 0.6357 | |
| | cosine_precision@3 | 0.2714 | 0.2719 | 0.2719 | 0.2667 | 0.2581 | |
| | cosine_precision@5 | 0.1729 | 0.1731 | 0.1717 | 0.1683 | 0.1637 | |
| | cosine_precision@10 | 0.0914 | 0.092 | 0.0916 | 0.0889 | 0.0864 | |
| | cosine_recall@1 | 0.6771 | 0.6714 | 0.6714 | 0.6614 | 0.6357 | |
| | cosine_recall@3 | 0.8143 | 0.8157 | 0.8157 | 0.8 | 0.7743 | |
| | cosine_recall@5 | 0.8643 | 0.8657 | 0.8586 | 0.8414 | 0.8186 | |
| | cosine_recall@10 | 0.9143 | 0.92 | 0.9157 | 0.8886 | 0.8643 | |
| | **cosine_ndcg@10** | **0.7949** | **0.7936** | **0.7926** | **0.7767** | **0.7512** | |
| | cosine_mrr@10 | 0.7568 | 0.7534 | 0.7535 | 0.7408 | 0.7149 | |
| | cosine_map@100 | 0.7602 | 0.7564 | 0.7565 | 0.7454 | 0.7199 | |
| |
| <!-- |
| ## 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: 6,300 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: 4 tokens</li><li>mean: 46.71 tokens</li><li>max: 281 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 20.48 tokens</li><li>max: 43 tokens</li></ul> | |
| * Samples: |
| | positive | anchor | |
| |:---------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------| |
| | <code>Information on legal proceedings is included in Note 15 to the Consolidated Financial Statements.</code> | <code>What note in the Consolidated Financial Statements provides details on legal proceedings?</code> | |
| | <code>As of December 31, 2023, approximately $1.80 billion is available to be repatriated from Mainland China to the U.S.</code> | <code>What is the total amount of unrestricted cash available for repatriation from Mainland China to the U.S. as of the end of 2023?</code> | |
| | <code>Bank deposits amounted to $289,953 million as of December 31, 2023.</code> | <code>What was the balance of bank deposits at Charles Schwab Corporation as of December 31, 2023?</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`: 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`: 16 |
| - `per_gpu_train_batch_size`: None |
| - `per_gpu_eval_batch_size`: None |
| - `gradient_accumulation_steps`: 16 |
| - `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`: 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 |
| - `prompts`: None |
| - `batch_sampler`: no_duplicates |
| - `multi_dataset_batch_sampler`: proportional |
|
|
| </details> |
|
|
| ### Training Logs |
| | 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 | |
| |:----------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
| | 0.8122 | 10 | 1.5517 | - | - | - | - | - | |
| | 0.9746 | 12 | - | 0.7830 | 0.7842 | 0.7814 | 0.7623 | 0.7215 | |
| | 1.6244 | 20 | 0.6616 | - | - | - | - | - | |
| | 1.9492 | 24 | - | 0.7918 | 0.7924 | 0.7884 | 0.7737 | 0.7429 | |
| | 2.4365 | 30 | 0.46 | - | - | - | - | - | |
| | 2.9239 | 36 | - | 0.7941 | 0.7920 | 0.7930 | 0.7764 | 0.7482 | |
| | 3.2487 | 40 | 0.3917 | - | - | - | - | - | |
| | **3.8985** | **48** | **-** | **0.7949** | **0.7936** | **0.7926** | **0.7767** | **0.7512** | |
| |
| * The bold row denotes the saved checkpoint. |
| |
| ### Framework Versions |
| - Python: 3.10.12 |
| - Sentence Transformers: 3.3.1 |
| - 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.* |
| --> |
