--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:12001 - loss:CosineSimilarityLoss base_model: sentence-transformers/all-mpnet-base-v2 widget: - source_sentence: The country's president and his deputies urged security forces to intensify their efforts to secure the country. sentences: - Since January he has been on loan with his first club, Fluminense . - Plan is to eventually simulate an entire Neanderthal sentence . - Parked car bomb in same area of Baghdad kills at least 9 people on Tuesday . - source_sentence: 'Rob Andrew, the RFU''s elite director of rugby, said in a statement: "The England rugby team has been informed by Auckland Police that an allegation has been made against four members of the England playing squad.' sentences: - Raghad, wanted in Iraq on terrorism charges, currently living in Jordan . - Brittanee Drexel disappears on trip to Myrtle Beach, South Carolina . - 'RFU: Players concerned have complete support of all players and management .' - source_sentence: President Dmitry Medvedev announced the measures just two weeks ago, in his first state-of-the-nation speech on November 5. sentences: - Former Portuguese colony has a history of military coups . - However he has played only two Serie A matches in a disappointing campaign . - Kremlin says amendment needed to ensure stability of future governments . - source_sentence: '(CNN) -- In Focus: Sovereign Wealth Funds .' sentences: - MME talks U.A.E. - Followed president's decision to overturn Cabinet's sacking of army chief . - Southwest happy to have settled "all outstanding issues with the FAA" - source_sentence: Sikorsky's alert, on January 28, said the "main gearbox filter bowl assembly mounting titanium studs should be replaced with steel mounting studs." sentences: - Out-of-control school bus crashes into dozens of cars in Phoenix, Arizona . - Suspects blamed for bombings, civilian torture, warning insurgents about operations . - Sikorsky-92 A crashed last week off Newfoundland; 17 people died . pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) - **Maximum Sequence Length:** 384 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Supported Modality:** Text ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'MPNetModel'}) (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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("kttt294/english-sbert-finetuned") # Run inference sentences = [ 'Sikorsky\'s alert, on January 28, said the "main gearbox filter bowl assembly mounting titanium studs should be replaced with steel mounting studs."', 'Sikorsky-92 A crashed last week off Newfoundland; 17 people died .', 'Suspects blamed for bombings, civilian torture, warning insurgents about operations .', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[ 1.0000, 0.0059, 0.0283], # [ 0.0059, 1.0000, -0.0197], # [ 0.0283, -0.0197, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 12,001 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 100 samples: | | sentence_0 | sentence_1 | label | |:---------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | modality | text | text | | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:-----------------| | The 2009 Super Bowl will be broadcast in 230 countries and territories, the NFL said. | The Super Bowl will be broadcast February 1 . | 1.0 | | Madhav Kumar Nepal of the Communist Party of Nepal (Unified Marxist-Leninist) was the only person to serve as a candidate for the post after he received backing from more than 20 of the 25 parties in parliament. | Madhav Kumar Nepal of the Communist Party of Nepal was only candidate . | 1.0 | | Sailors from the cruiser USS Vella Gulf arrested the men Wednesday in the western Gulf of Aden -- a waterway between Africa and the Middle East -- after a distress call from the 420-foot (128-meter) tanker Polaris. | Seven men captured after failed attack on ship, U.S. Navy says . | 0.0 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss", "cos_score_transformation": "torch.nn.modules.linear.Identity" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `per_device_train_batch_size`: 32 - `num_train_epochs`: 3 - `max_steps`: -1 - `learning_rate`: 5e-05 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: None - `warmup_steps`: 0 - `optim`: adamw_torch_fused - `optim_args`: None - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `optim_target_modules`: None - `gradient_accumulation_steps`: 1 - `average_tokens_across_devices`: True - `max_grad_norm`: 1 - `label_smoothing_factor`: 0.0 - `bf16`: False - `fp16`: False - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `use_liger_kernel`: False - `liger_kernel_config`: None - `use_cache`: False - `neftune_noise_alpha`: None - `torch_empty_cache_steps`: None - `auto_find_batch_size`: False - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `include_num_input_tokens_seen`: no - `log_level`: passive - `log_level_replica`: warning - `disable_tqdm`: False - `project`: huggingface - `trackio_space_id`: None - `trackio_bucket_id`: None - `trackio_static_space_id`: None - `per_device_eval_batch_size`: 32 - `prediction_loss_only`: True - `eval_on_start`: False - `eval_do_concat_batches`: True - `eval_use_gather_object`: False - `eval_accumulation_steps`: None - `include_for_metrics`: [] - `batch_eval_metrics`: False - `save_only_model`: False - `save_on_each_node`: False - `enable_jit_checkpoint`: False - `push_to_hub`: False - `hub_private_repo`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_always_push`: False - `hub_revision`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `restore_callback_states_from_checkpoint`: False - `full_determinism`: False - `seed`: 42 - `data_seed`: None - `use_cpu`: False - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `parallelism_config`: None - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `dataloader_prefetch_factor`: None - `remove_unused_columns`: True - `label_names`: None - `train_sampling_strategy`: random - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `ddp_static_graph`: None - `ddp_backend`: None - `ddp_timeout`: 1800 - `fsdp`: None - `fsdp_config`: None - `deepspeed`: None - `debug`: [] - `skip_memory_metrics`: True - `do_predict`: False - `resume_from_checkpoint`: None - `warmup_ratio`: None - `local_rank`: -1 - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 1.3298 | 500 | 0.0243 | | 2.6596 | 1000 | 0.0118 | ### Training Time - **Training**: 10.0 minutes ### Framework Versions - Python: 3.12.13 - Sentence Transformers: 5.6.0 - Transformers: 5.13.1 - PyTorch: 2.11.0+cu128 - Accelerate: 1.14.0 - Datasets: 4.0.0 - Tokenizers: 0.22.2 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ```