This is a sentence-transformers model finetuned from klue/roberta-base on the klue dataset. 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: klue/roberta-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- klue
Language: ko

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': 512, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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:

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 = [
    '보일러로 난방하는 방법 좀 알려줘',
    '보일러 켜는 방법 좀 설명해줘',
    '당신이 좋아하는 뉴스 채널이 뭐였더라?',
]
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

Datasets: sts-test and sts-eval
Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-test	sts-eval
pearson_cosine	0.3477	0.9608
spearman_cosine	0.3556	0.9196

Training Details

Training Dataset

klue

Dataset: klue at 349481e
Size: 10,501 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string float
details
min: 6 tokens
mean: 20.29 tokens
max: 58 tokens
min: 7 tokens
mean: 19.81 tokens
max: 55 tokens
min: 0.0
mean: 0.45
max: 1.0

Samples:

sentence1	sentence2	label
`시설은 좋으나 잠자리 민감하신 분들은 다른 곳으로 가세요`	`시설도 좋지만, 잠자리라면 다른 곳으로 가보세요.`	`0.6799999999999999`
`유럽 에어비엔비 숙소 중에서 제일 잘 터졌습니다!`	`유럽에서 가장 좋은 호텔이에요!`	`0.38`
`고모가 원하는게 볼륨 이단계야 삼단계야?`	`에어컨 사용료로 이번 달 얼마 정도 내야하나요?`	`0.0`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Evaluation Dataset

klue

Dataset: klue at 349481e
Size: 1,167 evaluation samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string float
details
min: 6 tokens
mean: 19.99 tokens
max: 62 tokens
min: 7 tokens
mean: 19.26 tokens
max: 64 tokens
min: 0.0
mean: 0.45
max: 1.0

Samples:

sentence1	sentence2	label
`4인은 멀티탭을 1개 준비하시면 편할것입니다.`	`멀티탭 1개를 준비하시면 4명이 편리하게 이용하실 수 있습니다.`	`0.6799999999999999`
`청결도, 화장실청소상태,방분위기 모두 훌륭했습니다.`	`체크인, 청소 및 고객서비스는 모두 훌륭했습니다.`	`0.26`
`심지어 사진보다 조금 넓었던 것 같다.`	`그것은 심지어 사진보다 조금 더 넓었습니다.`	`0.8`

Loss: CosineSimilarityLoss with these parameters:
json
1{ 2 "loss_fct": "torch.nn.modules.loss.MSELoss" 3}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
warmup_steps: 100
remove_unused_columns: False

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: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 100
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: False
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}
tp_size: 0
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
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: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-test_spearman_cosine	sts-eval_spearman_cosine
-1	-1	-	-	0.3556	-
0.7610	500	0.0272	-	-	-
1.5221	1000	0.0095	0.0172	-	0.9120
2.2831	1500	0.0059	-	-	-
3.0441	2000	0.004	0.0146	-	0.9196
3.8052	2500	0.0025	-	-	-

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.013 kWh
Carbon Emitted: 0.006 kg of CO2
Hours Used: 0.036 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 4090
CPU Model: Intel(R) Core(TM) i7-14700K
RAM Size: 62.51 GB

Framework Versions

Python: 3.11.11
Sentence Transformers: 4.0.1
Transformers: 4.50.2
PyTorch: 2.6.0+cu124
Accelerate: 0.34.1
Datasets: 2.19.1
Tokenizers: 0.21.1

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",
}

	sentence1	sentence2	label
type	string	string	float
details	min: 6 tokens mean: 20.29 tokens max: 58 tokens	min: 7 tokens mean: 19.81 tokens max: 55 tokens	min: 0.0 mean: 0.45 max: 1.0

SECUFIBRE/klue-roberta-base-klue-sts

SentenceTransformer based on klue/roberta-base

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Semantic Similarity

Training Details

Training Dataset

klue

Evaluation Dataset

klue

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Environmental Impact

Training Hardware

Framework Versions

Citation

BibTeX

Sentence Transformers

SECUFIBRE/
klue-roberta-base-klue-sts