--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - loss:CosineSimilarityLoss base_model: sentence-transformers/all-MiniLM-L6-v2 widget: - source_sentence: Oracle Cloud - Infrastructure and Platform Services for Enterprises sentences: - PulseAudio - Ubuntu Wiki - Documentation page not found - Read the Docs - Dwarf Fortress beginner tips - Video Games on Sports Illustrated - source_sentence: Suggest opt in User Test - Google Slides sentences: - ReleaseEngineering/TryServer - MozillaWiki - Dwarf Fortress beginner tips - Video Games on Sports Illustrated - Tutanota - Private Mailbox with End-to-End Encryption and Calendar - source_sentence: https://portal.naviabenefits.com/part/prioritytasks.aspx sentences: - What to Expect - Pregnancy and Parenting Tips, Week-by-Week Guides - Parents.com - Articles, Recipes, and Ideas for Family Activities - Pinterest - Boards for Collecting and Sharing Inspiration on Any Topic - source_sentence: Tidal - High-Fidelity Music Streaming with Master Quality Audio sentences: - Walmart - Everyday Low Prices on Groceries, Electronics, and More - Notion - Integrated Workspace for Notes, Tasks, Databases, and Wikis - Ambient Dreams Playlist on Amazon Music pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine model-index: - name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 results: - task: type: semantic-similarity name: Semantic Similarity metrics: - type: pearson_cosine value: 0.982180856269761 name: Pearson Cosine - type: spearman_cosine value: 0.24020738836963906 name: Spearman Cosine --- # SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co./sentence-transformers/all-MiniLM-L6-v2) - **Maximum Sequence Length:** 256 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity ### 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: BertModel (1): Pooling({'word_embedding_dimension': 384, '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 = [ 'Tabletop Simulator Hub - Workshop Mods and Board Game Fans', 'PC Gamer Club - Official Community for PC Gaming Enthusiasts', 'Booking.com - Hotels, Homes, and Vacation Rentals Worldwide', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 384] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Semantic Similarity * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.9822 | | **spearman_cosine** | **0.2402** | ## Training Details ### Training Dataset * Size: 49,800 training samples * Columns: sentence_0, sentence_1, and label * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | label | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:-----------------| | TripAdvisor - Hotel Reviews, Photos, and Travel Forums | Docker Hub - Container Image Repository for DevOps Environments | 0.0 | | Mastodon - Decentralized Social Media for Niche Communities | Allrecipes - User-Submitted Recipes, Reviews, and Cooking Tips | 0.0 | | YouTube Music - Music Videos, Official Albums, and Live Performances | ESPN - Sports News, Live Scores, Stats, and Highlights | 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" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `num_train_epochs`: 6 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `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`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1 - `num_train_epochs`: 6 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `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`: batch_sampler - `multi_dataset_batch_sampler`: round_robin
### Training Logs | Epoch | Step | Training Loss | spearman_cosine | |:------:|:-----:|:-------------:|:---------------:| | 0.0754 | 500 | 0.0216 | - | | 0.1509 | 1000 | 0.0178 | - | | 0.2263 | 1500 | 0.016 | - | | 0.3018 | 2000 | 0.015 | - | | 0.3772 | 2500 | 0.0144 | - | | 0.4526 | 3000 | 0.013 | - | | 0.5281 | 3500 | 0.0123 | - | | 0.6035 | 4000 | 0.0119 | - | | 0.6789 | 4500 | 0.0116 | - | | 0.7544 | 5000 | 0.0102 | - | | 0.8298 | 5500 | 0.0092 | - | | 0.9053 | 6000 | 0.0087 | - | | 0.9807 | 6500 | 0.0076 | - | | 1.0561 | 7000 | 0.0068 | - | | 1.1316 | 7500 | 0.0063 | - | | 1.2070 | 8000 | 0.0061 | - | | 1.2824 | 8500 | 0.0059 | - | | 1.3579 | 9000 | 0.0055 | - | | 1.4333 | 9500 | 0.0056 | - | | 1.5088 | 10000 | 0.0045 | - | | 1.5842 | 10500 | 0.004 | - | | 1.6596 | 11000 | 0.0045 | - | | 1.7351 | 11500 | 0.0039 | - | | 1.8105 | 12000 | 0.0044 | - | | 1.8859 | 12500 | 0.0036 | - | | 1.9614 | 13000 | 0.0032 | - | | 2.0368 | 13500 | 0.0034 | - | | 2.1123 | 14000 | 0.0028 | - | | 2.1877 | 14500 | 0.0029 | - | | 2.2631 | 15000 | 0.0031 | - | | 2.3386 | 15500 | 0.0026 | - | | 2.4140 | 16000 | 0.0026 | - | | 2.4894 | 16500 | 0.003 | - | | 2.5649 | 17000 | 0.0027 | - | | 2.6403 | 17500 | 0.0026 | - | | 2.7158 | 18000 | 0.0024 | - | | 2.7912 | 18500 | 0.0025 | - | | 2.8666 | 19000 | 0.002 | - | | 2.9421 | 19500 | 0.0022 | - | | 3.0175 | 20000 | 0.0021 | - | | 3.0929 | 20500 | 0.0021 | - | | 3.1684 | 21000 | 0.0019 | - | | 3.2438 | 21500 | 0.0021 | - | | 3.3193 | 22000 | 0.002 | - | | 3.3947 | 22500 | 0.0018 | - | | 3.4701 | 23000 | 0.0018 | - | | 3.5456 | 23500 | 0.0019 | - | | 3.6210 | 24000 | 0.0017 | - | | 3.6964 | 24500 | 0.0017 | - | | 3.7719 | 25000 | 0.0016 | - | | 3.8473 | 25500 | 0.0016 | - | | 3.9228 | 26000 | 0.0015 | - | | 3.9982 | 26500 | 0.0019 | - | | 4.0736 | 27000 | 0.0016 | - | | 4.1491 | 27500 | 0.0016 | - | | 4.2245 | 28000 | 0.0015 | - | | 4.2999 | 28500 | 0.0015 | - | | 4.3754 | 29000 | 0.0016 | - | | 4.4508 | 29500 | 0.0014 | - | | 4.5263 | 30000 | 0.0015 | - | | 4.6017 | 30500 | 0.0014 | - | | 4.6771 | 31000 | 0.0017 | - | | 4.7526 | 31500 | 0.0014 | - | | 4.8280 | 32000 | 0.0016 | - | | 4.9034 | 32500 | 0.0015 | - | | 4.9789 | 33000 | 0.0014 | - | | 5.0543 | 33500 | 0.0014 | - | | 5.1298 | 34000 | 0.0013 | - | | 5.2052 | 34500 | 0.0014 | - | | 5.2806 | 35000 | 0.0014 | - | | 5.3561 | 35500 | 0.0016 | - | | 5.4315 | 36000 | 0.0013 | - | | 5.5069 | 36500 | 0.0015 | - | | 5.5824 | 37000 | 0.0013 | - | | 5.6578 | 37500 | 0.0016 | - | | 5.7333 | 38000 | 0.0015 | - | | 5.8087 | 38500 | 0.0014 | - | | 5.8841 | 39000 | 0.0015 | - | | 5.9596 | 39500 | 0.0014 | - | | -1 | -1 | - | 0.2402 | ### Framework Versions - Python: 3.11.11 - Sentence Transformers: 3.4.1 - Transformers: 4.48.2 - PyTorch: 2.5.1+cu124 - 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", } ```