--- base_model: sentence-transformers/all-mpnet-base-v2 library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:25110 - loss:MultipleNegativesRankingLoss widget: - source_sentence: APPLE iPhone 16 PRO MAX 512GB sentences: - Communications Devices and Accessories - Communications Devices and Accessories - Communications Devices and Accessories - source_sentence: CISCO.CISCO 878-K9 G.SHDSL SECURİTY ROUTER sentences: - Communications Devices and Accessories - Data Voice or Multimedia Network Equipment or Platforms and Accessories - Computer Equipment and Accessories - source_sentence: iPhone 14 36 months Tier 3+ sentences: - Heating and ventilation and air circulation - Portable Structure Building Components - Components for information technology or broadcasting or telecommunications - source_sentence: Elektrik Sayacı Optik Okuyucu sentences: - Components for information technology or broadcasting or telecommunications - Power sources - Components for information technology or broadcasting or telecommunications - source_sentence: Power Cable,600V/1000V,ROV-K,4mm^2,Black Jacket(The Color Of Core Is Blue And Brown),36A,Shielded Style Outdoor Cable sentences: - Electrical equipment and components and supplies - Communications Devices and Accessories - Power sources model-index: - name: SentenceTransformer based on sentence-transformers/all-mpnet-base-v2 results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: Unknown type: unknown metrics: - type: pearson_cosine value: .nan name: Pearson Cosine - type: spearman_cosine value: .nan name: Spearman Cosine - type: pearson_manhattan value: .nan name: Pearson Manhattan - type: spearman_manhattan value: .nan name: Spearman Manhattan - type: pearson_euclidean value: .nan name: Pearson Euclidean - type: spearman_euclidean value: .nan name: Spearman Euclidean - type: pearson_dot value: .nan name: Pearson Dot - type: spearman_dot value: .nan name: Spearman Dot - type: pearson_max value: .nan name: Pearson Max - type: spearman_max value: .nan name: Spearman Max --- # 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 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-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) - **Maximum Sequence Length:** 384 tokens - **Output Dimensionality:** 768 tokens - **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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel (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("alpcansoydas/product-model-16.10.24-ifhavemorethan10sampleperfamily") # Run inference sentences = [ 'Power Cable,600V/1000V,ROV-K,4mm^2,Black Jacket(The Color Of Core Is Blue And Brown),36A,Shielded Style Outdoor Cable', 'Electrical equipment and components and supplies', 'Power sources', ] 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 #### Semantic Similarity * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:-------------------|:--------| | pearson_cosine | nan | | spearman_cosine | nan | | pearson_manhattan | nan | | spearman_manhattan | nan | | pearson_euclidean | nan | | spearman_euclidean | nan | | pearson_dot | nan | | spearman_dot | nan | | pearson_max | nan | | **spearman_max** | **nan** | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 25,110 training samples * Columns: sentence1 and sentence2 * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence1 | sentence2 | |:---------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | USRC20(RH2288,2*E5-2680v2,16*16G,12*600GB(2.5 )+2*600GB(2.5 ),4*10GE,4*GE,DC)-OS RAID1,DATA RAID5+Hotspare,No DVDRW | Computer Equipment and Accessories | | 100m 160x10 Kafes Kule | Heavy construction machinery and equipment | | Air4820 Superonline Video Bridge | Data Voice or Multimedia Network Equipment or Platforms and Accessories | * 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 #### Unnamed Dataset * Size: 5,381 evaluation samples * Columns: sentence1 and sentence2 * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence1 | sentence2 | |:------------------------------------------------------------------|:-----------------------------------------------------------------------------------------| | SNTC-24X7X4 Cisco ISR 4331 (2GE,2NIM,4G FLASH,4G DRA | Data Voice or Multimedia Network Equipment or Platforms and Accessories | | Iridium GO Ecex | Communications Devices and Accessories | | LC/LC SM 9/125 DX 1.8mm Lszh L 10m | Components for information technology or broadcasting or telecommunications | * 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`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 2 - `warmup_ratio`: 0.1 - `fp16`: True #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `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`: 1.0 - `num_train_epochs`: 2 - `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`: True - `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`: 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 - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | Training Loss | Validation Loss | spearman_max | |:------:|:----:|:-------------:|:---------------:|:------------:| | 0.0637 | 100 | 2.2804 | 1.9512 | nan | | 0.1274 | 200 | 1.8803 | 1.9189 | nan | | 0.1911 | 300 | 1.8687 | 1.7873 | nan | | 0.2548 | 400 | 1.7455 | 1.7351 | nan | | 0.3185 | 500 | 1.714 | 1.6717 | nan | | 0.3822 | 600 | 1.6956 | 1.6789 | nan | | 0.4459 | 700 | 1.7134 | 1.6407 | nan | | 0.5096 | 800 | 1.7059 | 1.6175 | nan | | 0.5732 | 900 | 1.674 | 1.6256 | nan | | 0.6369 | 1000 | 1.6725 | 1.5826 | nan | | 0.7006 | 1100 | 1.6238 | 1.5815 | nan | | 0.7643 | 1200 | 1.5819 | 1.5684 | nan | | 0.8280 | 1300 | 1.526 | 1.5511 | nan | | 0.8917 | 1400 | 1.4976 | 1.5496 | nan | | 0.9554 | 1500 | 1.5709 | 1.5358 | nan | | 1.0191 | 1600 | 1.4731 | 1.5498 | nan | | 1.0828 | 1700 | 1.3914 | 1.5280 | nan | | 1.1465 | 1800 | 1.4137 | 1.4980 | nan | | 1.2102 | 1900 | 1.3964 | 1.5012 | nan | | 1.2739 | 2000 | 1.4244 | 1.4972 | nan | | 1.3376 | 2100 | 1.4567 | 1.4943 | nan | | 1.4013 | 2200 | 1.4224 | 1.4880 | nan | | 1.4650 | 2300 | 1.4452 | 1.4685 | nan | | 1.5287 | 2400 | 1.3843 | 1.4976 | nan | | 1.5924 | 2500 | 1.4538 | 1.4715 | nan | | 1.6561 | 2600 | 1.3864 | 1.4738 | nan | | 1.7197 | 2700 | 1.3514 | 1.4724 | nan | | 1.7834 | 2800 | 1.4295 | 1.4538 | nan | | 1.8471 | 2900 | 1.3631 | 1.4629 | nan | | 1.9108 | 3000 | 1.3654 | 1.4588 | nan | | 1.9745 | 3100 | 1.3335 | 1.4552 | nan | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.2.0 - Transformers: 4.44.2 - PyTorch: 2.4.1+cu121 - Accelerate: 0.34.2 - Datasets: 3.0.1 - 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", } ``` #### 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} } ```