SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 384 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: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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 = [
    'Apa saja panduan umum pelaksanaan Program Magang di ITS?',
    'Mahasiswa dalam melaksanakan magang harus memenuhi ketentuan berikut: 1. Pelaksanaan Program Magang memiliki durasi minimal 1 bulan dan maksimal 6 bulan. 2. Selama Program Magang berlangsung, mahasiswa tidak harus mengajukan cuti. 3. Mahasiswa secara penuh waktu bekerja di lapangan sesuai kesepakatan. 4. Mahasiswa bisa mendapatkan izin untuk kegiatan akademik tertentu dengan kesepakatan pihak Mitra Magang. 5. Mahasiswa dapat mengajukan konversi mata kuliah dengan CPMK yang selaras. 6. Diperlukan pembimbing internal dari Dosen Departemen dan pembimbing lapangan dari Mitra Magang. 7. Sebelum Program Magang, wajib menandatangani perjanjian kerjasama dan nota kesepahaman.',
    '1. Mahasiswa mengurus surat rekomendasi departemen untuk pengajuan magang ke Mitra\n2. Mahasiswa mengajukan permohonan magang ke Mitra\n3. Mitra melakukan seleksi magang\n4. Mahasiswa menerima hasil seleksi magang dari Mitra\n5. Apabila tidak diterima, maka mahasiswa harus mengulang sejak langkah awal\n6. Apabila diterima, Mahasiswa melaporkan ke Departemen\n7. Mahasiswa/Departemen melakukan koordinasi dengan PK2 untuk pengurusan PKS dengan menyertakan Proposal Magang, Surat Rekomendasi Departemen dan Surat Penerimaan Magang\n8. Proses pengurusan PKS (Dapat dilakukan bersamaan dengan pelaksanaan Magang)',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

Size: 704 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: 6 tokens
mean: 16.22 tokens
max: 42 tokens

min: 5 tokens
mean: 57.55 tokens
max: 128 tokens

	sentence_0	sentence_1
type	string	string
details	min: 6 tokens mean: 16.22 tokens max: 42 tokens	min: 5 tokens mean: 57.55 tokens max: 128 tokens

Samples:

sentence_0	sentence_1
`Bagaimana cara menulis dokumen pemerintah dalam daftar pustaka?`	`Nama pengarang dan tahun publikasi sama dengan penulisan artikel dari jurnal. Judul dokumen dicetak miring/italic. Volume atau nomor (jika ada). Nama penerbit. Kota tempat diterbitkan.`
`Apa tugas dosen wali dalam pelaksanaan MBKM?`	`Dosen wali ditugaskan oleh Prodi untuk membuat perencanaan bersama dengan mahasiswa yang akan melaksanakan kegiatan MBKM, melakukan evaluasi terhadap kesesuaian bentuk dan lama pelaksanaan MBKM, serta melakukan penilaian atas rencana, pelaksanaan, dan evaluasi MBKM.`
`Apa yang dimaksud dengan 'Hak Belajar Tiga Semester di Luar Program Studi'?`	`Hak Belajar Tiga Semester di Luar Program Studi adalah kebijakan yang memberikan mahasiswa kesempatan untuk satu semester (setara dengan 20 SKS) menempuh pembelajaran di luar program studi pada perguruan tinggi yang sama, dan paling lama dua semester (setara dengan 40 SKS) di program studi yang sama atau berbeda di perguruan tinggi yang berbeda atau di luar perguruan tinggi.`

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 5
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
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
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}
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
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_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Framework Versions

Python: 3.8.10
Sentence Transformers: 3.0.1
Transformers: 4.39.2
PyTorch: 2.3.1+cu121
Accelerate: 0.29.3
Datasets: 2.19.2
Tokenizers: 0.15.2

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",
}

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}
}

ramamimu
/

finetuning-MiniLM-L12-v2