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: 128 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, '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("dev7halo/Ko-sroberta-base-multitask")
# Run inference
sentences = [
    '한국기후·환경네트워크는 콘텐츠 기획 및 개발과 인센티브 제공 등 앱 운영을 주관하고 한국환경공단, 한국환경산업기술원은 앱 제작물 개발과 운영예산 등을 지원한다.',
    '한국기후환경네트워크는 콘텐츠 기획, 개발, 인센티브 등 앱 운영을 관리하고, 한국환경공단과 한국환경산업기술원은 앱 개발 및 운영 예산을 지원합니다.',
    '그 수치는 2015년 메르스의 30퍼센트 감소에서 두 배 이상 증가했습니다.',
]
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

Metric Value
pearson_cosine 0.9625
spearman_cosine 0.9261
pearson_manhattan 0.9525
spearman_manhattan 0.9224
pearson_euclidean 0.9525
spearman_euclidean 0.9223
pearson_dot 0.9525
spearman_dot 0.9109
pearson_max 0.9625
spearman_max 0.9261

Training Details

Training Datasets

Unnamed Dataset

  • Size: 588,126 training samples
  • Columns: sentence_0, sentence_1, and sentence_2
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 sentence_2
    type string string string
    details
    • min: 4 tokens
    • mean: 19.08 tokens
    • max: 128 tokens
    • min: 4 tokens
    • mean: 18.94 tokens
    • max: 122 tokens
    • min: 5 tokens
    • mean: 14.88 tokens
    • max: 53 tokens
  • Samples:
    sentence_0 sentence_1 sentence_2
    바에서 호박을 곁들인 음료를 준비하는 여성 바텐더 바텐더가 술을 만들고 있다. 여자가 보드카를 마시고 있다.
    두 남자가 낮에 구조물 근처를 걷고 있다. 아름다운 화창한 날 건물을 산책하는 두 남자. 남자 몇 명이 코이와 함께 연못에서 수영을 하고 있다.
    두 사람이 꽃으로 둘러싸인 야외에 있다. 한 남자와 그의 딸이 밝은 색의 노란 꽃밭에서 사진을 찍기 위해 포즈를 취하고 있다. 두 남자가 농구를 하고 있다.
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "scale": 20.0,
        "similarity_fct": "cos_sim"
    }
    

Unnamed Dataset

  • Size: 12,187 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: 20.56 tokens
    • max: 70 tokens
    • min: 7 tokens
    • mean: 20.1 tokens
    • max: 68 tokens
    • min: 0.0
    • mean: 0.45
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    강원영서 지역은 언제 옵니까? 소나기. 라니냐가 일어날 때 해수면은 몇 도 정도 하강해? 0.0
    4월 ‘과학의 달’을 맞아 한 달 동안 언제 어디서나 과학기술을 즐길 수 있는 온라인 과학축제가 열린다. 4월의 "과학의 달"을 맞아, 언제 어디서나 한 달 동안 과학기술을 즐길 수 있는 온라인 과학 축제가 열릴 것입니다. 0.9199999999999999
    호스트가 아닌 리스본 컨시어지에서 관리를 하는거라 전문적으로 관리되는 숙소입니다. 이 숙소는 전문적으로 관리되며, 호스트가 아닌 리스본 컨시어지가 관리합니다. 0.76
  • 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: 128
  • per_device_eval_batch_size: 128
  • num_train_epochs: 5
  • 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: 128
  • per_device_eval_batch_size: 128
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_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: 5
  • 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: False
  • hub_always_push: False
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • include_inputs_for_metrics: False
  • 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
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step sts-dev_spearman_max
1.0052 193 0.9215
2.0052 386 0.9261

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.0.1
  • Transformers: 4.41.2
  • PyTorch: 2.3.0+cu121
  • Accelerate: 0.31.0
  • Datasets: 2.19.2
  • 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",
}

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}
}
Downloads last month
22
Safetensors
Model size
111M params
Tensor type
F32
·
Inference Examples
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 dev7halo/Ko-sroberta-base-multitask

Base model

klue/roberta-base
Finetuned
(130)
this model

Evaluation results