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 tokens
- 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 = [
'테라스에서 봤던 뷰와 그곳에서 먹었던 식사가 그리울 것 같아요.',
'테라스에서 본 풍경과 거기서 먹었던 음식이 그리울 것 같아요.',
'이쪽 주변에서 여행할 계획이라면 추천합니다!',
]
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 |
pearson_manhattan | 0.3674 |
spearman_manhattan | 0.3646 |
pearson_euclidean | 0.3607 |
spearman_euclidean | 0.3548 |
pearson_dot | 0.2125 |
spearman_dot | 0.2006 |
pearson_max | 0.3674 |
spearman_max | 0.3646 |
Semantic Similarity
- Evaluated with
EmbeddingSimilarityEvaluator
Metric | Value |
---|---|
pearson_cosine | 0.962 |
spearman_cosine | 0.9196 |
pearson_manhattan | 0.953 |
spearman_manhattan | 0.9186 |
pearson_euclidean | 0.9533 |
spearman_euclidean | 0.9191 |
pearson_dot | 0.9493 |
spearman_dot | 0.8999 |
pearson_max | 0.962 |
spearman_max | 0.9196 |
Training Details
Training Dataset
Unnamed Dataset
- Size: 10,501 training samples
- Columns:
sentence_0
,sentence_1
, andlabel
- Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label type string string float details - min: 7 tokens
- mean: 20.23 tokens
- max: 64 tokens
- min: 5 tokens
- mean: 19.94 tokens
- max: 63 tokens
- min: 0.0
- mean: 0.44
- max: 1.0
- Samples:
sentence_0 sentence_1 label 지하철 역 내려서 1분정도의 아주 가까운 거리입니다.
지하철역에서 1분 정도 아주 가까운 거리입니다.
0.86
그것빼곤 2인여행자들에게는 좋은숙소에요!
계단이 많다는거 빼곤 완벽한 숙소에요!
0.27999999999999997
이어 현금이 286만 가구(13.2%) 1조3007억원, 선불카드가 75만 가구(3.5%) 4990억원, 지역사랑상품권은 63만 가구(2.9%) 4171억원으로 각각 집계됐다.
이어 현금 286만 가구(13.2%), 현금 1조337억 원, 선불카드 75만 가구(3.5%), 4990억 원, 지역사랑상품권 63만 가구(2.9%), 4171억 원 순이었습니다.
0.86
- Loss:
CosineSimilarityLoss
with these parameters:{ "loss_fct": "torch.nn.modules.loss.MSELoss" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy
: stepsper_device_train_batch_size
: 16per_device_eval_batch_size
: 16num_train_epochs
: 4multi_dataset_batch_sampler
: round_robin
All Hyperparameters
Click to expand
overwrite_output_dir
: Falsedo_predict
: Falseeval_strategy
: stepsprediction_loss_only
: Trueper_device_train_batch_size
: 16per_device_eval_batch_size
: 16per_gpu_train_batch_size
: Noneper_gpu_eval_batch_size
: Nonegradient_accumulation_steps
: 1eval_accumulation_steps
: Nonetorch_empty_cache_steps
: Nonelearning_rate
: 5e-05weight_decay
: 0.0adam_beta1
: 0.9adam_beta2
: 0.999adam_epsilon
: 1e-08max_grad_norm
: 1num_train_epochs
: 4max_steps
: -1lr_scheduler_type
: linearlr_scheduler_kwargs
: {}warmup_ratio
: 0.0warmup_steps
: 0log_level
: passivelog_level_replica
: warninglog_on_each_node
: Truelogging_nan_inf_filter
: Truesave_safetensors
: Truesave_on_each_node
: Falsesave_only_model
: Falserestore_callback_states_from_checkpoint
: Falseno_cuda
: Falseuse_cpu
: Falseuse_mps_device
: Falseseed
: 42data_seed
: Nonejit_mode_eval
: Falseuse_ipex
: Falsebf16
: Falsefp16
: Falsefp16_opt_level
: O1half_precision_backend
: autobf16_full_eval
: Falsefp16_full_eval
: Falsetf32
: Nonelocal_rank
: 0ddp_backend
: Nonetpu_num_cores
: Nonetpu_metrics_debug
: Falsedebug
: []dataloader_drop_last
: Falsedataloader_num_workers
: 0dataloader_prefetch_factor
: Nonepast_index
: -1disable_tqdm
: Falseremove_unused_columns
: Truelabel_names
: Noneload_best_model_at_end
: Falseignore_data_skip
: Falsefsdp
: []fsdp_min_num_params
: 0fsdp_config
: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap
: Noneaccelerator_config
: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}deepspeed
: Nonelabel_smoothing_factor
: 0.0optim
: adamw_torchoptim_args
: Noneadafactor
: Falsegroup_by_length
: Falselength_column_name
: lengthddp_find_unused_parameters
: Noneddp_bucket_cap_mb
: Noneddp_broadcast_buffers
: Falsedataloader_pin_memory
: Truedataloader_persistent_workers
: Falseskip_memory_metrics
: Trueuse_legacy_prediction_loop
: Falsepush_to_hub
: Falseresume_from_checkpoint
: Nonehub_model_id
: Nonehub_strategy
: every_savehub_private_repo
: Falsehub_always_push
: Falsegradient_checkpointing
: Falsegradient_checkpointing_kwargs
: Noneinclude_inputs_for_metrics
: Falseeval_do_concat_batches
: Truefp16_backend
: autopush_to_hub_model_id
: Nonepush_to_hub_organization
: Nonemp_parameters
:auto_find_batch_size
: Falsefull_determinism
: Falsetorchdynamo
: Noneray_scope
: lastddp_timeout
: 1800torch_compile
: Falsetorch_compile_backend
: Nonetorch_compile_mode
: Nonedispatch_batches
: Nonesplit_batches
: Noneinclude_tokens_per_second
: Falseinclude_num_input_tokens_seen
: Falseneftune_noise_alpha
: Noneoptim_target_modules
: Nonebatch_eval_metrics
: Falseeval_on_start
: Falseeval_use_gather_object
: Falsebatch_sampler
: batch_samplermulti_dataset_batch_sampler
: round_robin
Training Logs
Epoch | Step | Training Loss | spearman_max |
---|---|---|---|
0 | 0 | - | 0.3646 |
0.7610 | 500 | 0.0283 | - |
1.0 | 657 | - | 0.9075 |
1.5221 | 1000 | 0.0082 | 0.9148 |
2.0 | 1314 | - | 0.9148 |
2.2831 | 1500 | 0.0047 | - |
3.0 | 1971 | - | 0.9180 |
3.0441 | 2000 | 0.0034 | 0.9168 |
3.8052 | 2500 | 0.0027 | - |
4.0 | 2628 | - | 0.9196 |
Environmental Impact
Carbon emissions were measured using CodeCarbon.
- Energy Consumed: 0.017 kWh
- Carbon Emitted: 0.007 kg of CO2
- Hours Used: 0.057 hours
Training Hardware
- On Cloud: No
- GPU Model: 1 x NVIDIA GeForce RTX 4090
- CPU Model: 13th Gen Intel(R) Core(TM) i7-13700
- RAM Size: 62.57 GB
Framework Versions
- Python: 3.9.0
- Sentence Transformers: 3.0.1
- Transformers: 4.44.1
- PyTorch: 2.3.1+cu121
- Accelerate: 0.33.0
- Datasets: 2.19.1
- Tokenizers: 0.19.1
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",
}
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for hyunkookim/klue-roberta-base-klue-sts
Evaluation results
- Pearson Cosine on Unknownself-reported0.348
- Spearman Cosine on Unknownself-reported0.356
- Pearson Manhattan on Unknownself-reported0.367
- Spearman Manhattan on Unknownself-reported0.365
- Pearson Euclidean on Unknownself-reported0.361
- Spearman Euclidean on Unknownself-reported0.355
- Pearson Dot on Unknownself-reported0.213
- Spearman Dot on Unknownself-reported0.201
- Pearson Max on Unknownself-reported0.367
- Spearman Max on Unknownself-reported0.365