--- language: - en tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:942069 - loss:MultipleNegativesRankingLoss base_model: FacebookAI/roberta-base widget: - source_sentence: Two women having drinks and smoking cigarettes at the bar. sentences: - Women are celebrating at a bar. - Two kids are outdoors. - The four girls are attending the street festival. - source_sentence: Two male police officers on patrol, wearing the normal gear and bright green reflective shirts. sentences: - The officers have shot an unarmed black man and will not go to prison for it. - The four girls are playing card games at the table. - A woman is playing with a toddler. - source_sentence: 5 women sitting around a table doing some crafts. sentences: - The girl wearing a dress skips down the sidewalk. - The kids are together. - Five men stand on chairs. - source_sentence: Three men look on as two other men carve up a freshly barbecued hog in the backyard. sentences: - A group of people prepare cars for racing. - There are men watching others prepare food - They are both waiting for a bus. - source_sentence: The little boy is jumping into a puddle on the street. sentences: - A man is wearing a black shirt - The dog is playing with a ball. - The boy is outside. datasets: - sentence-transformers/all-nli pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on FacebookAI/roberta-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on the [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) 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:** [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) - **Maximum Sequence Length:** 256 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Training Dataset:** - [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) - **Language:** en ### 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': 256, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, '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("sentence_transformers_model_id") # Run inference sentences = [ 'The little boy is jumping into a puddle on the street.', 'The boy is outside.', 'The dog is playing with a ball.', ] 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] ``` ## Training Details ### Training Dataset #### all-nli * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab) * Size: 942,069 training samples * Columns: premise, hypothesis, and label * Approximate statistics based on the first 1000 samples: | | premise | hypothesis | label | |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | premise | hypothesis | label | |:--------------------------------------------------------------------|:---------------------------------------------------------------|:---------------| | A person on a horse jumps over a broken down airplane. | A person is training his horse for a competition. | 1 | | A person on a horse jumps over a broken down airplane. | A person is at a diner, ordering an omelette. | 2 | | A person on a horse jumps over a broken down airplane. | A person is outdoors, on a horse. | 0 | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Evaluation Dataset #### all-nli * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [d482672](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/d482672c8e74ce18da116f430137434ba2e52fab) * Size: 19,657 evaluation samples * Columns: premise, hypothesis, and label * Approximate statistics based on the first 1000 samples: | | premise | hypothesis | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------------------------------------------------------------------| | type | string | string | int | | details | | | | * Samples: | premise | hypothesis | label | |:-------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------|:---------------| | Two women are embracing while holding to go packages. | The sisters are hugging goodbye while holding to go packages after just eating lunch. | 1 | | Two women are embracing while holding to go packages. | Two woman are holding packages. | 0 | | Two women are embracing while holding to go packages. | The men are fighting outside a deli. | 2 | * 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`: steps - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `learning_rate`: 1e-05 - `warmup_ratio`: 0.1 - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 1e-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`: 3 - `max_steps`: -1 - `lr_scheduler_type`: linear - `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`: False - `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 - `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`: None - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `include_for_metrics`: [] - `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 - `average_tokens_across_devices`: False - `prompts`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | |:------:|:----:|:-------------:|:---------------:| | 0.0007 | 5 | - | 4.4994 | | 0.0014 | 10 | - | 4.4981 | | 0.0020 | 15 | - | 4.4960 | | 0.0027 | 20 | - | 4.4930 | | 0.0034 | 25 | - | 4.4890 | | 0.0041 | 30 | - | 4.4842 | | 0.0048 | 35 | - | 4.4784 | | 0.0054 | 40 | - | 4.4716 | | 0.0061 | 45 | - | 4.4636 | | 0.0068 | 50 | - | 4.4543 | | 0.0075 | 55 | - | 4.4438 | | 0.0082 | 60 | - | 4.4321 | | 0.0088 | 65 | - | 4.4191 | | 0.0095 | 70 | - | 4.4042 | | 0.0102 | 75 | - | 4.3875 | | 0.0109 | 80 | - | 4.3686 | | 0.0115 | 85 | - | 4.3474 | | 0.0122 | 90 | - | 4.3236 | | 0.0129 | 95 | - | 4.2968 | | 0.0136 | 100 | 4.4995 | 4.2666 | | 0.0143 | 105 | - | 4.2326 | | 0.0149 | 110 | - | 4.1947 | | 0.0156 | 115 | - | 4.1516 | | 0.0163 | 120 | - | 4.1029 | | 0.0170 | 125 | - | 4.0476 | | 0.0177 | 130 | - | 3.9850 | | 0.0183 | 135 | - | 3.9162 | | 0.0190 | 140 | - | 3.8397 | | 0.0197 | 145 | - | 3.7522 | | 0.0204 | 150 | - | 3.6521 | | 0.0211 | 155 | - | 3.5388 | | 0.0217 | 160 | - | 3.4114 | | 0.0224 | 165 | - | 3.2701 | | 0.0231 | 170 | - | 3.1147 | | 0.0238 | 175 | - | 2.9471 | | 0.0245 | 180 | - | 2.7710 | | 0.0251 | 185 | - | 2.5909 | | 0.0258 | 190 | - | 2.4127 | | 0.0265 | 195 | - | 2.2439 | | 0.0272 | 200 | 3.6918 | 2.0869 | | 0.0279 | 205 | - | 1.9477 | | 0.0285 | 210 | - | 1.8274 | | 0.0292 | 215 | - | 1.7156 | | 0.0299 | 220 | - | 1.6211 | | 0.0306 | 225 | - | 1.5416 | | 0.0312 | 230 | - | 1.4732 | | 0.0319 | 235 | - | 1.4176 | | 0.0326 | 240 | - | 1.3702 | | 0.0333 | 245 | - | 1.3269 | | 0.0340 | 250 | - | 1.2892 | | 0.0346 | 255 | - | 1.2563 | | 0.0353 | 260 | - | 1.2281 | | 0.0360 | 265 | - | 1.2024 | | 0.0367 | 270 | - | 1.1796 | | 0.0374 | 275 | - | 1.1601 | | 0.0380 | 280 | - | 1.1428 | | 0.0387 | 285 | - | 1.1271 | | 0.0394 | 290 | - | 1.1129 | | 0.0401 | 295 | - | 1.1002 | | 0.0408 | 300 | 1.7071 | 1.0876 | | 0.0414 | 305 | - | 1.0761 | | 0.0421 | 310 | - | 1.0658 | | 0.0428 | 315 | - | 1.0554 | | 0.0435 | 320 | - | 1.0458 | | 0.0442 | 325 | - | 1.0365 | | 0.0448 | 330 | - | 1.0276 | | 0.0455 | 335 | - | 1.0180 | | 0.0462 | 340 | - | 1.0086 | | 0.0469 | 345 | - | 0.9996 | | 0.0476 | 350 | - | 0.9920 | | 0.0482 | 355 | - | 0.9846 | | 0.0489 | 360 | - | 0.9782 | | 0.0496 | 365 | - | 0.9715 | | 0.0503 | 370 | - | 0.9641 | | 0.0510 | 375 | - | 0.9572 | | 0.0516 | 380 | - | 0.9503 | | 0.0523 | 385 | - | 0.9444 | | 0.0530 | 390 | - | 0.9384 | | 0.0537 | 395 | - | 0.9329 | | 0.0543 | 400 | 1.2083 | 0.9276 | | 0.0550 | 405 | - | 0.9220 | | 0.0557 | 410 | - | 0.9166 | | 0.0564 | 415 | - | 0.9114 | | 0.0571 | 420 | - | 0.9062 | | 0.0577 | 425 | - | 0.9006 | | 0.0584 | 430 | - | 0.8960 | | 0.0591 | 435 | - | 0.8931 | | 0.0598 | 440 | - | 0.8904 | | 0.0605 | 445 | - | 0.8865 | | 0.0611 | 450 | - | 0.8822 | | 0.0618 | 455 | - | 0.8777 | | 0.0625 | 460 | - | 0.8741 | | 0.0632 | 465 | - | 0.8712 | | 0.0639 | 470 | - | 0.8673 | | 0.0645 | 475 | - | 0.8623 | | 0.0652 | 480 | - | 0.8576 | | 0.0659 | 485 | - | 0.8535 | | 0.0666 | 490 | - | 0.8495 | | 0.0673 | 495 | - | 0.8459 | | 0.0679 | 500 | 1.0828 | 0.8434 | ### Framework Versions - Python: 3.12.8 - Sentence Transformers: 3.4.1 - Transformers: 4.48.3 - PyTorch: 2.2.0+cu121 - Accelerate: 1.3.0 - Datasets: 3.2.0 - Tokenizers: 0.21.0 ## 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} } ```