SentenceTransformer based on kategosari/cliffsofdover_tsdae

This is a sentence-transformers model finetuned from kategosari/cliffsofdover_tsdae. 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: kategosari/cliffsofdover_tsdae
Maximum Sequence Length: 256 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': 256, 'do_lower_case': False}) with Transformer model: ElectraModel 
  (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("kategosari/cliffsofdover_tsdae2")
# Run inference
sentences = [
    '길이에 녹색광을 [MASK] 것 시간 따라',
    ' 시간 길이에 따라 녹색광을 제어하는 것',
    ' 데이터 처리 및 클라우드 컴퓨팅에 관한 것이며, 코드로서 기술된 클라우드 인프라스트럭처 환경에 적용될 수 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]

Training Details

Training Dataset

Unnamed Dataset

Size: 53,333 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 7 tokens
mean: 28.68 tokens
max: 50 tokens

min: 7 tokens
mean: 29.45 tokens
max: 53 tokens

	sentence_0	sentence_1
type	string	string
details	min: 7 tokens mean: 28.68 tokens max: 50 tokens	min: 7 tokens mean: 29.45 tokens max: 53 tokens

Samples:

sentence_0	sentence_1
`장치를 헤더 제공한다 코스웨어 [MASK] 제작 방법과 인공지능에`	`인공지능에 기초한 코스웨어 헤더 제작 방법과 장치를 제공한다`
`단어와 입력 값으로 가장 [MASK] 정보를 모델은 기반 사용하여 수 적합한 모델 지능 현재 입력된 사용자에게 컨텍스트 규칙 및/또는 컨텍스트에 제공할 인공 있다`	`규칙 기반 모델 및/또는 인공 지능 모델은 입력된 단어와 컨텍스트 정보를 입력 값으로 사용하여 현재 컨텍스트에 가장 적합한 문장을 사용자에게 제공할 수 있다`
`한다. 이전에 있어서의 AI 및 비효율성 적용함에 지침을 기초하여 위한 주관성을 모델을 식별하고 방사선치료를 수행된 활용하여 방사선치료에 구현하기 해결하고자 [MASK]`	`이전에 수행된 방사선치료에 기초하여 훈련된 AI 모델을 활용하여 방사선치료를 구현하기 위한 지침을 식별하고 적용함에 있어서의 비효율성 및 주관성을 해결하고자 한다.`

Loss: DenoisingAutoEncoderLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 5
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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: 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: None
hub_always_push: False
hub_revision: None
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
liger_kernel_config: None
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
0.2999	500	3.383
0.5999	1000	2.6709
0.8998	1500	2.4958
1.1998	2000	2.317
1.4997	2500	2.2062
1.7996	3000	2.1348
2.0996	3500	2.0467
2.3995	4000	1.9364
2.6995	4500	1.8734
2.9994	5000	1.8382
3.2993	5500	1.7141
3.5993	6000	1.6808
3.8992	6500	1.6515
4.1992	7000	1.5583
4.4991	7500	1.5173
4.7990	8000	1.4834

Framework Versions

Python: 3.11.13
Sentence Transformers: 4.1.0
Transformers: 4.53.2
PyTorch: 2.6.0+cu124
Accelerate: 1.9.0
Datasets: 2.20.0
Tokenizers: 0.21.2

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",
}

DenoisingAutoEncoderLoss

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}

Downloads last month: 2

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for kategosari/cliffsofdover_tsdae2

Base model

KIPI-ai/KorPatElectra

Finetuned

kategosari/cliffsofdover_tsdae

Finetuned

(1)

this model

Finetunes

1 model