metadata

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 [email protected]
      - Envie um e-mail para [email protected].
      - >-
        Envie um e-mail para [email protected] 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 model finetuned from sentence-transformers/all-MiniLM-L12-v2 on the train and test 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
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 dimensions
Similarity Function: Cosine Similarity
Training Datasets:
- train
- test

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

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:

pip install -U sentence-transformers

Then you can load this model and run inference.

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 at 9021242
Size: 92 training samples
Columns: question and answer
Approximate statistics based on the first 92 samples:
question answer
type string string
details
min: 7 tokens
mean: 17.88 tokens
max: 45 tokens

min: 14 tokens
mean: 46.03 tokens
max: 128 tokens

	question	answer
type	string	string
details	min: 7 tokens mean: 17.88 tokens max: 45 tokens	min: 14 tokens mean: 46.03 tokens max: 128 tokens

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 with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

test

Dataset: test at 9021242
Size: 92 training samples
Columns: question and answer
Approximate statistics based on the first 92 samples:
question answer
type string string
details
min: 9 tokens
mean: 17.32 tokens
max: 30 tokens

min: 15 tokens
mean: 40.58 tokens
max: 68 tokens

	question	answer
type	string	string
details	min: 9 tokens mean: 17.32 tokens max: 30 tokens	min: 15 tokens mean: 40.58 tokens max: 68 tokens

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 with these parameters:

{
    "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

@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

@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}
}