--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:69363 - loss:EpochLossWrapper base_model: intfloat/multilingual-e5-large widget: - source_sentence: 'query: MSI 微星 MSI PRO MP165 E6 可攜式螢幕 (16型/FHD/Type C/喇叭/IPS)+SPACE LED觸控護眼三色螢幕掛燈 33cm款' sentences: - 'passage: 六合一清潔組【Apple】AirPods 4' - 'passage: 【MSI 微星】PRO MP251 E2 25型 平面商用螢幕(FHD/IPS/120Hz/DP+HDMI+D-Sub/眼部護理技術)' - 'passage: 【Apple】Apple Watch Series 11 GPS+行動網路 42mm(鋁金屬錶殼搭配運動型錶帶)' - source_sentence: 'query: DAIKIN 大金 7坪閃流放電空氣清淨機 MC30YSCT' sentences: - 'passage: 三合一充電座組【Apple】Apple Watch Ultra 3 GPS+行動網路 49mm(鈦金屬錶殼搭配越野錶環)' - 'passage: 【LG 樂金】58H快配17公斤◆AI DD™智慧直驅變頻洗衣機 ◆曜石黑(WT-VDN17M)' - 'passage: 【LG 樂金】PuriCare Hit 一級能效 超淨化 大白 抗敏 空氣 清淨機 適用18坪 / 台 AS601HWG0' - source_sentence: 'query: Logitech 羅技 G304 LIGHTSPEED 無線電競遊戲滑鼠 黑色' sentences: - 'passage: 【grantclassic】6入濾心套餐組 喝不停 AquaLux 寵物智能陶瓷飲水機 + 6入專用濾心(2L/官方品牌館)' - 'passage: 【Logitech 羅技】M190無線滑鼠(黑色)' - 'passage: 【beyerdynamic】DT 71 IE 鼓組&貝斯 入耳式監聽耳機 #劇院視聽 #HIFI #高解析音質 #有線耳機(公司貨保證)' - source_sentence: 'query: KINTO / TRAVEL TUMBLER 隨行保溫瓶500ml-灰' sentences: - 'passage: 【小不記】1080P旗艦款-多媒體投影儀 4K畫質智慧投影機 LED鏡像同屏(家用投影機 露營投影機 投影機)' - 'passage: 手提陶瓷咖啡保溫杯500ml(內附吸管/五色任選/保冰杯/保溫杯/減塑/保溫瓶)' - 'passage: 【技嘉】顯卡+電源組合★ RTX 5080 GAMING OC 16G 顯示卡+海韻 ATX3 Core GX-850 金牌電源供應器' - source_sentence: 'query: PHILIPS 飛利浦 Sonicare 智慧感應型電動牙刷 新月白 (HX6877/27)' sentences: - 'passage: 【MSI 微星】MSI 微星 MAG 274UPDF E16M 電競螢幕 27吋 160Hz 4k IPS 0.5ms HDR 可旋轉' - 'passage: 【SHARP 夏普】12公升 自動除菌離子除濕機(DW-LT12ST-W)' - 'passage: 【Philips 飛利浦】官方直Sonicare抗敏Pro 鑽石智能音波電動牙刷/護敏刷HX3892/02(雙入組)' pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on intfloat/multilingual-e5-large This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large). It maps sentences & paragraphs to a 1024-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:** [intfloat/multilingual-e5-large](https://huggingface.co/intfloat/multilingual-e5-large) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 1024 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': 128, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'}) (1): Pooling({'word_embedding_dimension': 1024, '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 = [ 'query: PHILIPS 飛利浦 Sonicare 智慧感應型電動牙刷 新月白 (HX6877/27)', 'passage: 【Philips 飛利浦】官方直Sonicare抗敏Pro 鑽石智能音波電動牙刷/護敏刷HX3892/02(雙入組)', 'passage: 【SHARP 夏普】12公升 自動除菌離子除濕機(DW-LT12ST-W)', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 1024] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities) # tensor([[1.0000, 0.1586, 0.0201], # [0.1586, 1.0000, 0.1386], # [0.0201, 0.1386, 1.0000]]) ``` ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 69,363 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 | int | | details | | | | * Samples: | sentence_0 | sentence_1 | label | |:--------------------------------------------------------------------------------------|:---------------------------------------------------------------------------|:---------------| | query: Logitech 羅技 M221 靜音無線滑鼠-黑 | passage: 【Logitech 羅技】Pebble M350s 無線藍牙滑鼠 - 珍珠白(不附接收器) | 0 | | query: Kleenex 舒潔 萬用輕巧包抽取衛生紙(110+20抽x20包/串) | passage: 【Kleenex 舒潔】棉柔舒適抽取衛生紙110抽*60包 | 0 | | query: Apple 蘋果 Apple Watch Series 11 GPS + LTE 46mm 玫瑰金色鋁金屬錶殼搭配淡胭粉色運動錶帶 | passage: 【Apple】Apple Watch S11 GPS + 行動網路 46mm(鋁金屬錶殼搭配運動型錶帶) | 0 | * Loss: __main__.EpochLossWrapper ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `num_train_epochs`: 15 - `fp16`: True - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `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`: 15 - `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 - `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} - `parallelism_config`: 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 - `project`: huggingface - `trackio_space_id`: trackio - `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 - `hub_revision`: None - `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 - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: no - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `use_liger_kernel`: False - `liger_kernel_config`: None - `eval_use_gather_object`: False - `average_tokens_across_devices`: True - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 0.2306 | 500 | 0.0168 | | 0.4613 | 1000 | 0.0042 | | 0.6919 | 1500 | 0.0033 | | 0.9225 | 2000 | 0.0033 | | 1.0 | 2168 | - | ### Framework Versions - Python: 3.11.14 - Sentence Transformers: 5.1.1 - Transformers: 4.57.1 - PyTorch: 2.9.0+cu128 - Accelerate: 1.10.1 - Datasets: 4.2.0 - Tokenizers: 0.22.1 ## 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", } ```