KYUNGHYUN9/ko-sroberta-itos-training-example_v0.03

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

• 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: 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 = [
    '딱딱한 모자를 쓴 남자가 건물 프레임 앞에 주차된 빨간 트럭의 침대를 쳐다본다.',
    '한 남자가 트럭을 보고 있다.',
    '남자가 자고 있다.',
]
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

• Dataset: sts-dev
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8611
spearman_cosine	0.8634
pearson_manhattan	0.8545
spearman_manhattan	0.8591
pearson_euclidean	0.8549
spearman_euclidean	0.8593
pearson_dot	0.8332
spearman_dot	0.8324
pearson_max	0.8611
spearman_max	0.8634

Training Details

Training Datasets

Unnamed Dataset

• Size: 568,640 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: 19.18 tokens max: 128 tokens	min: 3 tokens mean: 18.31 tokens max: 93 tokens	min: 4 tokens mean: 14.58 tokens max: 54 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  발생 부하가 함께 5% 적습니다.	발생 부하의 5% 감소와 함께 11.	발생 부하가 5% 증가합니다.
  어떤 행사를 위해 음식과 옷을 배급하는 여성들.	여성들은 음식과 옷을 나눠줌으로써 난민들을 돕고 있다.	여자들이 사막에서 오토바이를 운전하고 있다.
  어린 아이들은 그 지식을 얻을 필요가 있다.	응, 우리 젊은이들 중 많은 사람들이 그걸 배워야 할 것 같아.	젊은 사람들은 배울 필요가 없다.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Unnamed Dataset

• Size: 5,778 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: 3 tokens mean: 16.98 tokens max: 63 tokens	min: 4 tokens mean: 16.88 tokens max: 76 tokens	min: 0.0 mean: 0.54 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  다우존스 산업평균지수는 9011.53으로 98.32, 즉 약 1.1% 하락했다.	다우존스 산업평균지수는 9,011.53으로 98.32포인트 하락했다.	0.6799999999999999
  미군 특수부대는 콜롬비아에서 두 번째로 큰 유전에서 원유를 운반하는 파이프라인을 보호하기 위해 이 지역의 군사기지에서 콜롬비아 군인들을 훈련시키고 있다.	미군 특수부대는 이 지역의 군사기지에서 콜롬비아 군인들을 훈련시켜 파이프라인을 보호하고 있다.	0.64
  한 사람은 또한 영어/터키어 사전에서 난민이라는 단어를 지적했다.	한 남자는 영어-터키 사전을 휘두르고 "피난민"이라는 단어를 가리켰다.	0.76

• Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• num_train_epochs: 5
• batch_sampler: no_duplicates
• 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: 8
• per_device_eval_batch_size: 8
• 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: no_duplicates
• multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss	sts-dev_spearman_max
0.3458	500	0.4169	-
0.6916	1000	0.2952	0.8533
1.0007	1447	-	0.8581
1.0367	1500	0.2744	-
1.3824	2000	0.1415	0.8520
1.7282	2500	0.0886	-
2.0007	2894	-	0.8634

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.2.2+cu121
• Accelerate: 0.31.0
• Datasets: 2.20.0
• 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}
}