--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:178 - loss:MultipleNegativesRankingLoss base_model: BAAI/bge-base-en-v1.5 widget: - source_sentence: Where can investors find more information about NVIDIA's financial information and company updates? sentences: - ' The potential risks include restrictions on sales of products containing certain components made by Micron, restrictions on receiving supply of components, parts, or services from Taiwan, increased scrutiny from shareholders, regulators, and others regarding corporate sustainability practices, and failure to meet evolving shareholder, regulator, or other industry stakeholder expectations, which could result in additional costs, reputational harm, and loss of customers and suppliers.' - ' Investors and others can find more information about NVIDIA''s financial information and company updates on the company''s investor relations website, through press releases, SEC filings, public conference calls and webcasts, as well as on the company''s social media channels, including Twitter, the NVIDIA Corporate Blog, Facebook, LinkedIn, Instagram, and YouTube.' - ' The text mentions the following forms and agreements: Officers'' Certificate, Form of Note (with various years), Form of Indemnity Agreement, Amended and Restated 2007 Equity Incentive Plan, Non-Employee Director Deferred Restricted Stock Unit Grant Notice and Deferred Restricted Stock Unit Agreement, Non-Employee Director Restricted Stock Unit Grant Notice and Restricted Stock Unit Agreement, Global Performance-Based Restricted Stock Unit Grant Notice and Performance-Based Restricted Stock Unit Agreement, Global Restricted Stock Unit Grant Notice and Global Restricted Stock Unit Agreement, and various Schedules and Exhibits (such as 2.1, 3.1, 4.1, 4.2, 10.1, 10.2, 10.26, and 10.27).' - source_sentence: What are the potential consequences if regulators in China conclude that NVIDIA has failed to fulfill its commitments or has violated applicable law in China? sentences: - ' The company''s share repurchase program aims to offset dilution from shares issued to employees.' - ' Ms. Shoquist served as Senior Vice President and General Manager of the Electro-Optics business at Coherent, Inc., and previously worked at Quantum Corp. as President of the Personal Computer Hard Disk Drive Division, and at Hewlett-Packard.' - ' If regulators in China conclude that NVIDIA has failed to fulfill its commitments or has violated applicable law in China, the company could be subject to various penalties or restrictions on its ability to conduct its business, which could have a material and adverse impact on its business, operating results, and financial condition.' - source_sentence: What percentage of the company's revenue was attributed to sales to customers outside of the United States in fiscal year 2024? sentences: - ' NVIDIA reports its business results in two segments: the Compute & Networking segment and the Graphics segment.' - ' The company expects to use its existing cash, cash equivalents, and marketable securities, as well as the cash generated by its operations, to fund its capital investments of approximately $3.5 billion to $4.0 billion related to property and equipment during fiscal year 2025.' - ' 56% of the company''s total revenue in fiscal year 2024 was attributed to sales to customers outside of the United States.' - source_sentence: What is the net income per share of NVIDIA Corporation for the year ended January 29, 2023? sentences: - ' 6% of the company''s workforce in the United States is composed of Black or African American employees.' - ' The net income per share of NVIDIA Corporation for the year ended January 29, 2023 is $12.05 for basic and $11.93 for diluted.' - ' The company may face potential risks and challenges such as increased expenses, substantial expenditures and time spent to fully resume operations, disruption to product development or operations due to employees being called-up for active military duty, and potential impact on future product development, operations, and revenue. Additionally, the company may also experience interruptions or delays in services from third-party providers, which could impair its ability to provide its products and services and harm its business.' - source_sentence: What percentage of the company's accounts receivable balance as of January 28, 2024, was accounted for by two customers? sentences: - ' The change in equipment and assembly and test equipment resulted in a benefit of $135 million in operating income and $114 million in net income, or $0.05 per both basic and diluted share, for the fiscal year ended January 28, 2024.' - ' The estimates of deferred tax assets and liabilities may change based on added certainty or finality to an anticipated outcome, changes in accounting standards or tax laws in the U.S. or foreign jurisdictions where the company operates, or changes in other facts or circumstances.' - ' 24% and 11%, which is a total of 35%.' 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 - dot_accuracy@1 - dot_accuracy@3 - dot_accuracy@5 - dot_accuracy@10 - dot_precision@1 - dot_precision@3 - dot_precision@5 - dot_precision@10 - dot_recall@1 - dot_recall@3 - dot_recall@5 - dot_recall@10 - dot_ndcg@10 - dot_mrr@10 - dot_map@100 model-index: - name: SentenceTransformer based on BAAI/bge-base-en-v1.5 results: - task: type: information-retrieval name: Information Retrieval dataset: name: bge base en type: bge-base-en metrics: - type: cosine_accuracy@1 value: 0.9269662921348315 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.9831460674157303 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9943820224719101 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 1.0 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.9269662921348315 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.3277153558052434 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.198876404494382 name: Cosine Precision@5 - type: cosine_precision@10 value: 0.09999999999999998 name: Cosine Precision@10 - type: cosine_recall@1 value: 0.9269662921348315 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.9831460674157303 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9943820224719101 name: Cosine Recall@5 - type: cosine_recall@10 value: 1.0 name: Cosine Recall@10 - type: cosine_ndcg@10 value: 0.9682702490705566 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.9575842696629214 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.9575842696629213 name: Cosine Map@100 - type: dot_accuracy@1 value: 0.9269662921348315 name: Dot Accuracy@1 - type: dot_accuracy@3 value: 0.9831460674157303 name: Dot Accuracy@3 - type: dot_accuracy@5 value: 0.9943820224719101 name: Dot Accuracy@5 - type: dot_accuracy@10 value: 1.0 name: Dot Accuracy@10 - type: dot_precision@1 value: 0.9269662921348315 name: Dot Precision@1 - type: dot_precision@3 value: 0.3277153558052434 name: Dot Precision@3 - type: dot_precision@5 value: 0.198876404494382 name: Dot Precision@5 - type: dot_precision@10 value: 0.09999999999999998 name: Dot Precision@10 - type: dot_recall@1 value: 0.9269662921348315 name: Dot Recall@1 - type: dot_recall@3 value: 0.9831460674157303 name: Dot Recall@3 - type: dot_recall@5 value: 0.9943820224719101 name: Dot Recall@5 - type: dot_recall@10 value: 1.0 name: Dot Recall@10 - type: dot_ndcg@10 value: 0.9682702490705566 name: Dot Ndcg@10 - type: dot_mrr@10 value: 0.9575842696629214 name: Dot Mrr@10 - type: dot_map@100 value: 0.9575842696629213 name: Dot Map@100 --- # SentenceTransformer based on BAAI/bge-base-en-v1.5 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 train 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) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Dataset:** - train ### 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("rezarahim/bge-finetuned-detail") # Run inference sentences = [ "What percentage of the company's accounts receivable balance as of January 28, 2024, was accounted for by two customers?", ' 24% and 11%, which is a total of 35%.', ' The change in equipment and assembly and test equipment resulted in a benefit of $135 million in operating income and $114 million in net income, or $0.05 per both basic and diluted share, for the fiscal year ended January 28, 2024.', ] 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] ``` ## Evaluation ### Metrics #### Information Retrieval * Dataset: `bge-base-en` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.927 | | cosine_accuracy@3 | 0.9831 | | cosine_accuracy@5 | 0.9944 | | cosine_accuracy@10 | 1.0 | | cosine_precision@1 | 0.927 | | cosine_precision@3 | 0.3277 | | cosine_precision@5 | 0.1989 | | cosine_precision@10 | 0.1 | | cosine_recall@1 | 0.927 | | cosine_recall@3 | 0.9831 | | cosine_recall@5 | 0.9944 | | cosine_recall@10 | 1.0 | | cosine_ndcg@10 | 0.9683 | | cosine_mrr@10 | 0.9576 | | **cosine_map@100** | **0.9576** | | dot_accuracy@1 | 0.927 | | dot_accuracy@3 | 0.9831 | | dot_accuracy@5 | 0.9944 | | dot_accuracy@10 | 1.0 | | dot_precision@1 | 0.927 | | dot_precision@3 | 0.3277 | | dot_precision@5 | 0.1989 | | dot_precision@10 | 0.1 | | dot_recall@1 | 0.927 | | dot_recall@3 | 0.9831 | | dot_recall@5 | 0.9944 | | dot_recall@10 | 1.0 | | dot_ndcg@10 | 0.9683 | | dot_mrr@10 | 0.9576 | | dot_map@100 | 0.9576 | ## Training Details ### Training Dataset #### train * Dataset: train * Size: 178 training samples * Columns: anchor and positive * Approximate statistics based on the first 178 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | What is the publication date of the NVIDIA Corporation Annual Report 2024? | The publication date of the NVIDIA Corporation Annual Report 2024 is February 21st, 2024. | | What is the filing date of the 10-K report for NVIDIA Corporation in 2004? | The filing dates of the 10-K reports for NVIDIA Corporation in 2004 are May 20th, March 29th, and April 25th. | | What is the purpose of the section of the filing that requires the registrant to indicate whether it has submitted electronically every Interactive Data File required to be submitted pursuant to Rule 405 of Regulation S-T? | The purpose of this section is to require the registrant to disclose whether it has submitted all required Interactive Data Files electronically, as mandated by Rule 405 of Regulation S-T, during the preceding 12 months or for the shorter period that the registrant was required to submit such files. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: epoch - `per_device_train_batch_size`: 4 - `per_device_eval_batch_size`: 16 - `gradient_accumulation_steps`: 16 - `learning_rate`: 2e-05 - `num_train_epochs`: 25 - `lr_scheduler_type`: cosine - `warmup_ratio`: 0.1 - `load_best_model_at_end`: True - `optim`: adamw_torch_fused - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 4 - `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`: 25 - `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`: False - `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 - `eval_on_start`: False - `use_liger_kernel`: False - `eval_use_gather_object`: False - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | bge-base-en_cosine_map@100 | |:-----------:|:------:|:-------------:|:--------------------------:| | 0 | 0 | - | 0.8574 | | 0.7111 | 2 | - | 0.8591 | | 1.7778 | 5 | - | 0.8757 | | 2.8444 | 8 | - | 0.9012 | | 3.5556 | 10 | 0.2885 | - | | 3.9111 | 11 | - | 0.9134 | | 4.9778 | 14 | - | 0.9277 | | 5.6889 | 16 | - | 0.9391 | | 6.7556 | 19 | - | 0.9463 | | 7.1111 | 20 | 0.0644 | - | | 7.8222 | 22 | - | 0.9506 | | 8.8889 | 25 | - | 0.9515 | | 9.9556 | 28 | - | 0.9555 | | 10.6667 | 30 | 0.0333 | 0.9560 | | 11.7333 | 33 | - | 0.9551 | | 12.8 | 36 | - | 0.9569 | | **13.8667** | **39** | **-** | **0.9579** | | 14.2222 | 40 | 0.0157 | - | | 14.9333 | 42 | - | 0.9576 | | 16.0 | 45 | - | 0.9576 | | 16.7111 | 47 | - | 0.9576 | | 17.7778 | 50 | 0.0124 | 0.9576 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.1.1 - Transformers: 4.45.2 - PyTorch: 2.5.1+cu121 - Accelerate: 1.2.1 - Datasets: 3.1.0 - Tokenizers: 0.20.3 ## 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", } ``` #### 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} } ```