metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:10501
  - loss:CosineSimilarityLoss
base_model: klue/roberta-base
widget:
  - source_sentence: 일정이 더 많은 날은 오늘입니까 내일입니까?
    sentences:
      - 내일 일곱시에 맞춰둔 알람 벨소리가 뭐야?
      - 슬플 때 참지 말고 빗속을 달려보도록.
      - 티비 켤때 음성명령은 어떻게 해?
  - source_sentence: 호스트의 초코릿 선물에 저희아기들이 행복했답니다.
    sentences:
      - 신속하고 정확한 의사소통도 장점입니다.
      - 역사에 기록된 태풍 중 가장 큰 규모의 태풍은 무엇일까?
      - 그리고 일단 호스트분들이 친절했습니다.
  - source_sentence: 역시나 주방을 이용할 수 있다는건 정말 큰 장점인 것 같아요.
    sentences:
      - 텝스 스터디 모임을 매주에 몇 번씩 하나?
      - 저는 부엌을 사용할 수 있다는 것이 큰 장점이라고 생각해요.
      - 저는 이 이후로는 에어비앤비안쓸라고요.
  - source_sentence: 하지만 사소하게 아쉬웠던 점은 이불이 담요에요.
    sentences:
      - 하지만 조금 아쉬운 점은 이불이 담요라는 것입니다.
      - 진정한 에어비앤비를 느낄 수 있었습니다.
      - 위치, 청결도, 가격, 호스트 모두 좋습니다.
  - source_sentence: 이 숙소에서 가장 좋았던 점은 위치였습니다.
    sentences:
      - 이 숙소의 가장 좋은 점은 그것의 위치였습니다.
      - 생산업체들이 생산 물량을 늘릴 수 있도록 원재료 추가 확보 등 최대한 지원하기 바랍니다.
      - 다른 리뷰들과 마찬가지로, 부엌에는 여러분이 필요한 모든 것이 있고 화장실은 깨끗해요!
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
co2_eq_emissions:
  emissions: 5.887689224694198
  energy_consumed: 0.013454438564481419
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: AMD Ryzen 7 7800X3D 8-Core Processor
  ram_total_size: 30.908397674560547
  hours_used: 0.05
  hardware_used: 1 x NVIDIA GeForce RTX 4080
model-index:
  - name: SentenceTransformer based on klue/roberta-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: pearson_cosine
            value: 0.34770709642503844
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.35560473197486514
            name: Spearman Cosine
          - type: pearson_cosine
            value: 0.9623505245361443
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.9225407729630292
            name: Spearman Cosine

SentenceTransformer based on klue/roberta-base

This is a sentence-transformers model finetuned from klue/roberta-base. 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

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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    '이 숙소에서 가장 좋았던 점은 위치였습니다.',
    '이 숙소의 가장 좋은 점은 그것의 위치였습니다.',
    '생산업체들이 생산 물량을 늘릴 수 있도록 원재료 추가 확보 등 최대한 지원하기 바랍니다.',
]
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

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.3477
spearman_cosine	0.3556

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.9624
spearman_cosine	0.9225

Training Details

Training Dataset

Unnamed Dataset

Size: 10,501 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 float
details
min: 5 tokens
mean: 20.15 tokens
max: 56 tokens

min: 6 tokens
mean: 19.71 tokens
max: 58 tokens

min: 0.0
mean: 0.44
max: 1.0

	sentence_0	sentence_1	label
type	string	string	float
details	min: 5 tokens mean: 20.15 tokens max: 56 tokens	min: 6 tokens mean: 19.71 tokens max: 58 tokens	min: 0.0 mean: 0.44 max: 1.0

Samples:

sentence_0	sentence_1	label
`가이드북이 이메일로 오는 만큼 관리가 철저한 걸 느낄 수 있었습니다!`	`심지어 넷플릭스도 무료로 볼 수 있었습니다!`	`0.0`
`숙소가 정말 깨끗하고 온수도 잘나옵니다.`	`집이 정말 깔끔하고 온수도 잘 나옵니다.`	`0.8400000000000001`
`완전 1분 거리에 시부야에서 정말 맛있는 맛집이 많습니다.`	`시부야에는 1분 거리에 맛있는 음식점이 너무 많아요.`	`0.74`

Loss: CosineSimilarityLoss with these parameters:

{
    "loss_fct": "torch.nn.modules.loss.MSELoss"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
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: 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
num_train_epochs: 4
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
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: 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: 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: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	spearman_cosine
-1	-1	-	0.3556
0.7610	500	0.0282	-
1.0	657	-	0.9132
1.5221	1000	0.0079	0.9169
2.0	1314	-	0.9194
2.2831	1500	0.005	-
3.0	1971	-	0.9212
3.0441	2000	0.0034	0.9215
3.8052	2500	0.0026	-
4.0	2628	-	0.9225

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.013 kWh
Carbon Emitted: 0.006 kg of CO2
Hours Used: 0.05 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 4080
CPU Model: AMD Ryzen 7 7800X3D 8-Core Processor
RAM Size: 30.91 GB

Framework Versions

Python: 3.10.12
Sentence Transformers: 4.1.0
Transformers: 4.52.3
PyTorch: 2.6.0+cu124
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

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",
}