This is a sentence-transformers model finetuned from keepitreal/vietnamese-sbert. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: keepitreal/vietnamese-sbert
Maximum Sequence Length: 256 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'RobertaModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'mean', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    '[CONTEXT] Domain: Design | Environment: Corporate [CONTENT] Sử dụng thành thạo các công cụ đồ họa chuyên nghiệp',
    '[CONTEXT] Type: professional_employment | Domain: Graphic Design | Seniority: senior [CONTENT] Adobe Photoshop, Illustrator and InDesign',
    '[CONTEXT] Type: professional_employment | Domain: Human Resources | Seniority: senior [CONTENT] Payroll and Benefits Administration',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9077, 0.7920],
#         [0.9077, 1.0000, 0.8230],
#         [0.7920, 0.8230, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7211
spearman_cosine	0.7256

Training Details

Training Dataset

Unnamed Dataset

Size: 5,202 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 100 samples:
sentence_0 sentence_1 label
type string string float
modality text text
details
min: 30 tokens
mean: 39.09 tokens
max: 60 tokens
min: 41 tokens
mean: 48.18 tokens
max: 60 tokens
min: 0.0
mean: 0.54
max: 1.0

Samples:

sentence_0	sentence_1	label
`[CONTEXT] Domain: Logistics \| Environment: Warehouse [CONTENT] Documentation and inventory management`	`[CONTEXT] Type: professional_employment \| Domain: Logistics \| Seniority: mid [CONTENT] Forklift operation`	`0.41000000000000003`
`[CONTEXT] Domain: Healthcare \| Environment: Medical facility [CONTENT] Scheduling`	`[CONTEXT] Type: professional_employment \| Domain: Customer Service \| Seniority: mid [CONTENT] Training and development`	`0.03`
`[CONTEXT] Domain: Healthcare \| Environment: Hospital/Clinic [CONTENT] Communication and patient consultation`	`[CONTEXT] Type: professional_employment \| Domain: Healthcare \| Seniority: mid [CONTENT] Lytec`	`0.25`

Loss: CoSENTLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "pairwise_cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
num_train_epochs: 4
per_device_eval_batch_size: 32
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

per_device_train_batch_size: 32
num_train_epochs: 4
max_steps: -1
learning_rate: 5e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 32
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	spearman_cosine
0.6135	100	-	0.6159
1.0	163	-	0.6522
1.2270	200	-	0.6727
1.8405	300	-	0.6952
2.0	326	-	0.7058
2.4540	400	-	0.7096
3.0	489	-	0.7179
3.0675	500	5.9469	0.7179
3.6810	600	-	0.7250
4.0	652	-	0.7256

Training Time

Training: 9.3 minutes

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.6.0
Transformers: 5.13.1
PyTorch: 2.11.0+cu128
Accelerate: 1.14.0
Datasets: 4.0.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

CoSENTLoss