This is a sentence-transformers model finetuned from BAAI/bge-m3. 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: BAAI/bge-m3
Maximum Sequence Length: 8192 tokens
Output Dimensionality: 1024 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': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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): Normalize()
)

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("MarcoAland/Indonesian-bge-m3")
# Run inference
sentences = [
    'Seorang anak laki-laki sedang membaca.',
    'Anak laki-laki kecil duduk di kursi modern yang besar, membaca buku anak-anak.',
    'Seorang anak baru saja memukul bola saat bermain T-ball.',
]
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

Triplet

Dataset: model-evaluation
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9596
dot_accuracy	0.0404
manhattan_accuracy	0.9592
euclidean_accuracy	0.9596
max_accuracy	0.9596

Training Details

Training Dataset

Unnamed Dataset

Size: 45,000 training samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 6 tokens
mean: 10.02 tokens
max: 61 tokens
min: 5 tokens
mean: 16.08 tokens
max: 79 tokens
min: 5 tokens
mean: 16.47 tokens
max: 52 tokens

Samples:

anchor	positive	negative
`Dua pengendara sepeda motor berlomba di lintasan miring.`	`Lintasan pada gambar tidak sepenuhnya datar.`	`Pengendara sepeda motor memakai sarung tangannya sebelum balapan`
`Pria itu ada di luar.`	`Seorang pria berpakaian hitam sedang memegang kantong sampah hitam dan memungut barang-barang dari tempat pembuangan tanah.`	`Seorang pria mengenakan jas hitam dikelilingi oleh banyak orang di dalam sebuah gedung dengan patung dada orang di dinding.`
`Orang-orang ada di luar ruangan.`	`Ada orang-orang yang menonton band bermain di luar ruangan dan seorang anak berada di latar depan.`	`Dua orang bertopi baseball sedang duduk di dalam ruang kantor besar dan menatap layar komputer.`

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

Evaluation Dataset

Unnamed Dataset

Size: 5,000 evaluation samples
Columns: anchor, positive, and negative
Approximate statistics based on the first 1000 samples:
anchor positive negative
type string string string
details
min: 4 tokens
mean: 9.88 tokens
max: 65 tokens
min: 6 tokens
mean: 16.1 tokens
max: 50 tokens
min: 5 tokens
mean: 16.69 tokens
max: 46 tokens

Samples:

anchor	positive	negative
`Anjing itu sedang berlari.`	`Seekor anjing coklat mengejar bola di rumput`	`Anjing itu berbaring telentang di dekat bola hijau.`
`Seorang pria sedang tidur.`	`Seorang pria sedang tidur siang di kereta.`	`Pria muda bekerja di laboratorium sains.`
`Seorang pria sedang tidur.`	`Seorang pria sedang tidur di dalam bus.`	`seorang pria mendayung ganilla menyusuri jalan setapak yang berair`

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 4
per_device_eval_batch_size: 4
num_train_epochs: 1
warmup_ratio: 0.1
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 4
per_device_eval_batch_size: 4
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: 1.0
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
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
eval_on_start: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	model-evaluation_max_accuracy
0.0089	100	0.81	0.5528	-
0.0178	200	0.5397	0.4948	-
0.0267	300	0.5349	0.5147	-
0.0356	400	0.5342	0.5475	-
0.0444	500	0.4433	0.5679	0.9596

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.3.1+cu121
Accelerate: 0.32.1
Datasets: 2.20.0
Tokenizers: 0.19.1

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",
}

MultipleNegativesRankingLoss

bibtex

@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}
}

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 10.02 tokens max: 61 tokens	min: 5 tokens mean: 16.08 tokens max: 79 tokens	min: 5 tokens mean: 16.47 tokens max: 52 tokens