--- tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:184 - loss:MultipleNegativesRankingLoss base_model: sentence-transformers/all-MiniLM-L12-v2 widget: - source_sentence: Onde tirar dúvidas sobre o SIASS? sentences: - Envie um e-mail para siass.ceunes@ufes.br - Envie um e-mail para drm.ceunes@ufes.br. - Envie um e-mail para pagamento.dae.proaeci@ufes.br solicitando a alteração dos dados bancários. - source_sentence: Como acionar a manutenção de um bem em garantia? sentences: - Preencha o formulário em https://administrativo.ufes.br e envie com 15 dias de antecedência. - Acesse https://compras.ufes.br/inclusao-de-produto-no-catalogo-de-materiais. - Entre em contato com o fornecedor. - source_sentence: Computador não abre sistema operacional sentences: - Faça login no gmail.com com o usuário único @ufes.br e siga as instruções em https://senha.ufes.br/site/ativaGmail. - Clique no link https://chat.google.com/room/AAAAHqHLj6c?cls=4. - Se o sistema operacional não inicia, pode ser um problema no disco ou sistema. Contate o suporte de TI para suporte e diagnóstico. - source_sentence: Como acessar os dados acadêmicos e administrativos? sentences: - Siga as orientações disponíveis em https://progep.ufes.br/exames-periodicos. - Acesse o Portal Administrativo em https://administrativo.ufes.br. - Acesse https://senha.ufes.br/site/recuperaCredenciais. - source_sentence: Como cadastrar ou alterar dados no Sistema Integrado de Ensino (SIE), Protocolo, Portal Administrativo, Acadêmico e Reservas? sentences: - Siga os procedimentos em https://portaladministrativo.ufes.br/utilizacao-de-registro-de-precos-existente. - 'Acesse nosso chat para falar com um atendente humano: https://chat.google.com/room/AAAAHqHLj6c?cls=7' - Acesse https://dtin.saomateus.ufes.br/cadastros-e-habilitacao-aos-sistemas-institucionais e preencha o formulário. datasets: - matunderstars/ufes-qa-data pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2 This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) on the [train](https://huggingface.co/datasets/matunderstars/ufes-qa-data) and [test](https://huggingface.co/datasets/matunderstars/ufes-qa-data) datasets. 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-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 384 dimensions - **Similarity Function:** Cosine Similarity - **Training Datasets:** - [train](https://huggingface.co/datasets/matunderstars/ufes-qa-data) - [test](https://huggingface.co/datasets/matunderstars/ufes-qa-data) ### 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: 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("matunderstars/ufes-qa-embedding-finetuned") # Run inference sentences = [ 'Como cadastrar ou alterar dados no Sistema Integrado de Ensino (SIE), Protocolo, Portal Administrativo, Acadêmico e Reservas?', 'Acesse https://dtin.saomateus.ufes.br/cadastros-e-habilitacao-aos-sistemas-institucionais e preencha o formulário.', 'Acesse nosso chat para falar com um atendente humano: https://chat.google.com/room/AAAAHqHLj6c?cls=7', ] 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] ``` ## Training Details ### Training Datasets #### train * Dataset: [train](https://huggingface.co/datasets/matunderstars/ufes-qa-data) at [9021242](https://huggingface.co/datasets/matunderstars/ufes-qa-data/tree/9021242881748c37acc972de64de25d00d54f4d1) * Size: 92 training samples * Columns: question and answer * Approximate statistics based on the first 92 samples: | | question | answer | |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | question | answer | |:-------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Como registrar atestado de saúde? | Realize o registro pelo aplicativo SouGov (Menu > Atestado de Saúde > Incluir > Selecionar arquivo no dispositivo) ou pelo Portal Sigepe em Gestão de Pessoas > Minha Saúde > Atestado Médico. | | Como fazer uma doação ou empréstimo de um bem patrimonial? | Modelos estão em https://drm.saomateus.ufes.br → Patrimônio → Formulários e Modelos. | | Onde encontrar informações sobre as salas de aula e a configuração de equipamentos? | Consulte o manual em https://dtin.saomateus.ufes.br/tecnologias-educacionais. | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### test * Dataset: [test](https://huggingface.co/datasets/matunderstars/ufes-qa-data) at [9021242](https://huggingface.co/datasets/matunderstars/ufes-qa-data/tree/9021242881748c37acc972de64de25d00d54f4d1) * Size: 92 training samples * Columns: question and answer * Approximate statistics based on the first 92 samples: | | question | answer | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | question | answer | |:-----------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------| | Como acessar o manual do Estudo Técnico Preliminar (ETP)? | Acesse o manual em https://gov.br/compras/pt-br/centrais-de-conteudo/manuais/manual-etp-digital. | | Como solicitar material de consumo? | Faça login em https://administrativo.ufes.br/sistema/catalogo-produtos/catalogo. | | Problemas de conexão de internet | Problemas de conexão de internet podem ser causados por falhas de rede. Para resolver, entre em contato com o suporte de TI da UFES. | * 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 - `per_device_train_batch_size`: 16 - `per_device_eval_batch_size`: 16 - `num_train_epochs`: 150 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: no - `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`: 150 - `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 - `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 | |:--------:|:----:|:-------------:| | 71.4286 | 500 | 0.1147 | | 142.8571 | 1000 | 0.0001 | ### Framework Versions - Python: 3.10.12 - Sentence Transformers: 3.3.1 - Transformers: 4.46.2 - PyTorch: 2.5.1+cu121 - Accelerate: 1.1.1 - Datasets: 3.1.0 - Tokenizers: 0.20.3 ## 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} } ```