SentenceTransformer based on CocoRoF/ModernBERT-SimCSE-multitask_v03-retry

This is a sentence-transformers model finetuned from CocoRoF/ModernBERT-SimCSE-multitask_v03-retry on the misc_sts_pairs_v2_kor_kosimcse dataset. It maps sentences & paragraphs to a 1024-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: CocoRoF/ModernBERT-SimCSE-multitask_v03-retry
Maximum Sequence Length: 2048 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- misc_sts_pairs_v2_kor_kosimcse

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': 2048, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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})
  (2): Dense({'in_features': 768, 'out_features': 1024, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
)

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("CocoRoF/ModernBERT-SimCSE-multitask_v03-distill")
# Run inference
sentences = [
    '버스가 바쁜 길을 따라 운전한다.',
    '녹색 버스가 도로를 따라 내려간다.',
    '그 여자는 데이트하러 가는 중이다.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 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	0.8221
spearman_cosine	0.8282
pearson_euclidean	0.7929
spearman_euclidean	0.798
pearson_manhattan	0.7937
spearman_manhattan	0.7997
pearson_dot	0.7011
spearman_dot	0.6845
pearson_max	0.8221
spearman_max	0.8282

Training Details

Training Dataset

misc_sts_pairs_v2_kor_kosimcse

Dataset: misc_sts_pairs_v2_kor_kosimcse at e747415
Size: 449,904 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 18.3 tokens
max: 69 tokens

min: 6 tokens
mean: 18.69 tokens
max: 66 tokens

min: 0.11
mean: 0.77
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 18.3 tokens max: 69 tokens	min: 6 tokens mean: 18.69 tokens max: 66 tokens	min: 0.11 mean: 0.77 max: 1.0

Samples:

sentence1	sentence2	score
`주홍글씨는 언제 출판되었습니까?`	`《주홍글씨》는 몇 년에 출판되었습니까?`	`0.8638778924942017`
`폴란드에서 빨간색과 흰색은 무엇을 의미합니까?`	`폴란드 국기의 색상은 무엇입니까?`	`0.6773715019226074`
`노르만인들은 방어를 위해 모트와 베일리 성을 어떻게 사용했는가?`	`11세기에는 어떻게 모트와 베일리 성을 만들었습니까?`	`0.7460665702819824`

Loss: CosineSimilarityLoss with these parameters:

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

Evaluation Dataset

Unnamed Dataset

Size: 1,500 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 7 tokens
mean: 20.38 tokens
max: 52 tokens

min: 6 tokens
mean: 20.52 tokens
max: 54 tokens

min: 0.0
mean: 0.42
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 7 tokens mean: 20.38 tokens max: 52 tokens	min: 6 tokens mean: 20.52 tokens max: 54 tokens	min: 0.0 mean: 0.42 max: 1.0

Samples:

sentence1	sentence2	score
`안전모를 가진 한 남자가 춤을 추고 있다.`	`안전모를 쓴 한 남자가 춤을 추고 있다.`	`1.0`
`어린아이가 말을 타고 있다.`	`아이가 말을 타고 있다.`	`0.95`
`한 남자가 뱀에게 쥐를 먹이고 있다.`	`남자가 뱀에게 쥐를 먹이고 있다.`	`1.0`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

overwrite_output_dir: True
eval_strategy: steps
gradient_accumulation_steps: 16
learning_rate: 8e-05
num_train_epochs: 10.0
warmup_ratio: 0.2
push_to_hub: True
hub_model_id: CocoRoF/ModernBERT-SimCSE-multitask_v03-distill
hub_strategy: checkpoint
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: True
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: 16
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 8e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 10.0
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.2
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: True
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: True
resume_from_checkpoint: None
hub_model_id: CocoRoF/ModernBERT-SimCSE-multitask_v03-distill
hub_strategy: checkpoint
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
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
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs