--- language: - th license: apache-2.0 tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:2452 - loss:MultipleNegativesRankingLoss - thai - semantic-search - food - ingredients - retrieval base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2 widget: - source_sentence: น้ำ, ปีกไก่, ไข่เป็ด, รากผักชี, อบเชย, โป๊ยกั๊ก, น้ำตาลมะพร้าว, น้ำปลา, เกลือ, มะนาว, พริกขี้หนู, พริกจินดา, ผักชี sentences: - พะโล้ไข่เป็ดต้มแซ่บ - ต้มยำซี่โครงหมู สูตรใส่คนอร์ - ชุดอาหารเช้า - source_sentence: ข้าวสวย, หมึกกล้วย, หมูสับ, พริกแกง, น้ำปลา, น้ำตาลทราย, น้ำมันพืช, ใบโหระพา, ใบมะกรูด, พริกชี้ฟ้าแดง, ผักชี, พริกแกงเขียวหวาน, กะทิ, น้ำปลา, น้ำตาลทราย sentences: - ไส้กรอกพันเบคอนซอสน้ำตก (เบทาโกร) - ผักกาดขาวผัดไข่ - หมึกยัดไส้ข้าวผัดเขียวหวาน - source_sentence: กะปิ, กุ้งแห้ง, พริกขี้หนูสวน, กระเทียมไทย, น้ำปลา, น้ำตาลปี๊บ, น้ำมะนาว, น้ำเปล่า, ใบตอง, มะเขือพวง sentences: - น้ำพริกกะปิกุ้งแห้ง - หมูสวรรค์ - แกงส้มผักรวมปลากระพง - source_sentence: กล้วยไข่สุก, น้ำตาลทรายขาว, เกลือ, มะพร้าวอ่อน, ใบเตย sentences: - กล้วยไข่บวดชีมะพร้าวอ่อน - เส้นใหญ่ผัดซีอิ๊วไก่ - หุง(นึ่ง)ข้าวเหนียว ด้วยไมโครเวฟ - source_sentence: ปลาทูน่า, พริกขี้หนู, ไข่ไก่, น้ำปลา, เล็กน้อย, น้ำมันพืช sentences: - เจี๋ยนปลาทับทิม สูตร 2 น้ำมะขามเปียก - ข้าวแต๋น - ไข่เจียวทูน่าพริกสับ pipeline_tag: sentence-similarity library_name: sentence-transformers metrics: - cosine_accuracy@1 - cosine_accuracy@3 - cosine_accuracy@5 - cosine_accuracy@10 - cosine_precision@1 - cosine_precision@3 - cosine_precision@5 - cosine_recall@1 - cosine_recall@3 - cosine_recall@5 - cosine_ndcg@10 - cosine_mrr@10 - cosine_map@100 model-index: - name: Thai Food Ingredients → Dish Prediction results: - task: type: information-retrieval name: Information Retrieval dataset: name: thai food eval type: thai-food-eval metrics: - type: cosine_accuracy@1 value: 0.6052631578947368 name: Cosine Accuracy@1 - type: cosine_accuracy@3 value: 0.8421052631578947 name: Cosine Accuracy@3 - type: cosine_accuracy@5 value: 0.9605263157894737 name: Cosine Accuracy@5 - type: cosine_accuracy@10 value: 0.9736842105263158 name: Cosine Accuracy@10 - type: cosine_precision@1 value: 0.6052631578947368 name: Cosine Precision@1 - type: cosine_precision@3 value: 0.28070175438596484 name: Cosine Precision@3 - type: cosine_precision@5 value: 0.19210526315789467 name: Cosine Precision@5 - type: cosine_recall@1 value: 0.6052631578947368 name: Cosine Recall@1 - type: cosine_recall@3 value: 0.8421052631578947 name: Cosine Recall@3 - type: cosine_recall@5 value: 0.9605263157894737 name: Cosine Recall@5 - type: cosine_ndcg@10 value: 0.7948700328021918 name: Cosine Ndcg@10 - type: cosine_mrr@10 value: 0.735964912280702 name: Cosine Mrr@10 - type: cosine_map@100 value: 0.7371832358674465 name: Cosine Map@100 --- # Thai Food Ingredients → Dish Prediction This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-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/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity - **Language:** th - **License:** apache-2.0 ### 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}) with Transformer model: XLMRobertaModel (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}) ) ``` ## 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("thai_food_prediction1") # Run inference sentences = [ 'ปลาทูน่า, พริกขี้หนู, ไข่ไก่, น้ำปลา, เล็กน้อย, น้ำมันพืช', 'ไข่เจียวทูน่าพริกสับ', 'ข้าวแต๋น', ] 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 #### Information Retrieval * Dataset: `thai-food-eval` * Evaluated with [InformationRetrievalEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:-------------------|:-----------| | cosine_accuracy@1 | 0.6053 | | cosine_accuracy@3 | 0.8421 | | cosine_accuracy@5 | 0.9605 | | cosine_accuracy@10 | 0.9737 | | cosine_precision@1 | 0.6053 | | cosine_precision@3 | 0.2807 | | cosine_precision@5 | 0.1921 | | cosine_recall@1 | 0.6053 | | cosine_recall@3 | 0.8421 | | cosine_recall@5 | 0.9605 | | **cosine_ndcg@10** | **0.7949** | | cosine_mrr@10 | 0.736 | | cosine_map@100 | 0.7372 | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 2,452 training samples * Columns: anchor and positive * Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:-----------------------------------------------------------------------------------------------------------------------|:-------------------------| | ปลาหมึก, ซีอิ๊วดำ, ผงขมิ้น, น้ำปูนใส, กระเทียมสับ, รากผักชี, พริกแดง, น้ำตาลปี๊บ, เกลือ, น้ำปลา, น้ำมะนาว | ปลาหมึกย่าง | | ไปตกหมึกมา อยากทำอะไรกินง่ายๆ ได้รสชาติของปลาหมึกแท้ๆ | ปลาหมึกย่าง | | อยากกินปลาหมึกๆ ซีฟุ้ด อร่อยๆ | ปลาหมึกย่าง | * 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: 76 evaluation samples * Columns: anchor and positive * Approximate statistics based on the first 76 samples: | | anchor | positive | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | anchor | positive | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------| | น้ำมันพืช, กระเทียม, น้ำตาลทราย, น้ำปลา, ซีอิ๊วขาว, ซอสปรุงรส, ซีอิ๊วดำเค็ม, น้ำส้มสายชู, พริกไทย, เส้นหมี่แห้ง, ลูกชิ้น, ถั่วงอก | หมี่คลุก | | น้ำมัน, กระเทียม, หมูหมัก, เส้นใหญ่, ซีอิ้วดำ, คะน้า, กระหล่ำปลี, แครอท, ไข่เป็ด, ไข่ไก่, ผงปรุงรส, น้ำตาลทราย, ซอสหอยนางรม, ซอสปรุงรส, พริกไทย | ผัดซีอิ้วเส้นใหญ่ | | สะโพกหมู, น้ำตาลทราย, น้ำตาลปี๊บ, ซีอิ๊วขาว, เกลือ, น้ำเปล่า, ลูกผักชี, ยี่หร่า, กระเทียมไทย, สับละเอียด, น้ำมันพืช | หมูสวรรค์ | * 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`: epoch - `per_device_train_batch_size`: 24 - `per_device_eval_batch_size`: 24 - `learning_rate`: 5e-06 - `num_train_epochs`: 8 - `warmup_ratio`: 0.1 - `load_best_model_at_end`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: epoch - `prediction_loss_only`: True - `per_device_train_batch_size`: 24 - `per_device_eval_batch_size`: 24 - `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-06 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 8 - `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`: True - `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 - `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 | thai-food-eval_cosine_ndcg@10 | |:-------:|:-------:|:-------------:|:---------------:|:-----------------------------:| | 0.0971 | 10 | 3.2623 | - | - | | 0.1942 | 20 | 2.7506 | - | - | | 0.2913 | 30 | 2.45 | - | - | | 0.3883 | 40 | 2.1205 | - | - | | 0.4854 | 50 | 2.0216 | - | - | | 0.5825 | 60 | 1.7865 | - | - | | 0.6796 | 70 | 1.7075 | - | - | | 0.7767 | 80 | 1.4338 | - | - | | 0.8738 | 90 | 1.5122 | - | - | | 0.9709 | 100 | 1.4975 | - | - | | 1.0 | 103 | - | 1.0337 | 0.6411 | | 1.0680 | 110 | 1.2398 | - | - | | 1.1650 | 120 | 1.1619 | - | - | | 1.2621 | 130 | 1.1641 | - | - | | 1.3592 | 140 | 1.084 | - | - | | 1.4563 | 150 | 0.992 | - | - | | 1.5534 | 160 | 0.9877 | - | - | | 1.6505 | 170 | 1.0527 | - | - | | 1.7476 | 180 | 1.0431 | - | - | | 1.8447 | 190 | 1.0235 | - | - | | 1.9417 | 200 | 1.0231 | - | - | | 2.0 | 206 | - | 0.6985 | 0.7429 | | 2.0388 | 210 | 0.8387 | - | - | | 2.1359 | 220 | 0.6738 | - | - | | 2.2330 | 230 | 0.7837 | - | - | | 2.3301 | 240 | 0.8629 | - | - | | 2.4272 | 250 | 0.6708 | - | - | | 2.5243 | 260 | 0.8917 | - | - | | 2.6214 | 270 | 0.7686 | - | - | | 2.7184 | 280 | 0.7352 | - | - | | 2.8155 | 290 | 0.6844 | - | - | | 2.9126 | 300 | 0.7821 | - | - | | 3.0 | 309 | - | 0.6023 | 0.7508 | | 3.0097 | 310 | 0.6968 | - | - | | 3.1068 | 320 | 0.6536 | - | - | | 3.2039 | 330 | 0.6157 | - | - | | 3.3010 | 340 | 0.6562 | - | - | | 3.3981 | 350 | 0.563 | - | - | | 3.4951 | 360 | 0.6401 | - | - | | 3.5922 | 370 | 0.6167 | - | - | | 3.6893 | 380 | 0.5221 | - | - | | 3.7864 | 390 | 0.5609 | - | - | | 3.8835 | 400 | 0.6595 | - | - | | 3.9806 | 410 | 0.5761 | - | - | | 4.0 | 412 | - | 0.5541 | 0.7728 | | 4.0777 | 420 | 0.4465 | - | - | | 4.1748 | 430 | 0.4011 | - | - | | 4.2718 | 440 | 0.4988 | - | - | | 4.3689 | 450 | 0.5891 | - | - | | 4.4660 | 460 | 0.6107 | - | - | | 4.5631 | 470 | 0.5573 | - | - | | 4.6602 | 480 | 0.5007 | - | - | | 4.7573 | 490 | 0.4907 | - | - | | 4.8544 | 500 | 0.4756 | - | - | | 4.9515 | 510 | 0.5233 | - | - | | 5.0 | 515 | - | 0.4831 | 0.7920 | | 5.0485 | 520 | 0.4877 | - | - | | 5.1456 | 530 | 0.5158 | - | - | | 5.2427 | 540 | 0.4769 | - | - | | 5.3398 | 550 | 0.4461 | - | - | | 5.4369 | 560 | 0.4684 | - | - | | 5.5340 | 570 | 0.347 | - | - | | 5.6311 | 580 | 0.4203 | - | - | | 5.7282 | 590 | 0.4448 | - | - | | 5.8252 | 600 | 0.3725 | - | - | | 5.9223 | 610 | 0.4598 | - | - | | **6.0** | **618** | **-** | **0.4754** | **0.7938** | | 6.0194 | 620 | 0.5246 | - | - | | 6.1165 | 630 | 0.3768 | - | - | | 6.2136 | 640 | 0.3567 | - | - | | 6.3107 | 650 | 0.4294 | - | - | | 6.4078 | 660 | 0.356 | - | - | | 6.5049 | 670 | 0.4915 | - | - | | 6.6019 | 680 | 0.3908 | - | - | | 6.6990 | 690 | 0.3245 | - | - | | 6.7961 | 700 | 0.4382 | - | - | | 6.8932 | 710 | 0.4935 | - | - | | 6.9903 | 720 | 0.4248 | - | - | | 7.0 | 721 | - | 0.4928 | 0.7886 | | 7.0874 | 730 | 0.2804 | - | - | | 7.1845 | 740 | 0.3395 | - | - | | 7.2816 | 750 | 0.3559 | - | - | | 7.3786 | 760 | 0.4312 | - | - | | 7.4757 | 770 | 0.3929 | - | - | | 7.5728 | 780 | 0.3772 | - | - | | 7.6699 | 790 | 0.3205 | - | - | | 7.7670 | 800 | 0.3914 | - | - | | 7.8641 | 810 | 0.4501 | - | - | | 7.9612 | 820 | 0.4708 | - | - | | 8.0 | 824 | - | 0.4766 | 0.7949 | * The bold row denotes the saved checkpoint. ### Framework Versions - Python: 3.11.13 - Sentence Transformers: 4.1.0 - Transformers: 4.52.4 - PyTorch: 2.6.0+cu124 - Accelerate: 1.8.1 - Datasets: 2.14.4 - Tokenizers: 0.21.2 ## 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", } ``` #### 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} } ```