metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1200
  - loss:CosineSimilarityLoss
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
widget:
  - source_sentence: Sekelompok orang di perahu berlomba menuju pantai.
    sentences:
      - >-
        Haruskah kedatangan pada titik ini menjadi fokus untuk pemeriksaan
        sistem apa pun?
      - Sekelompok orang berdiri bersama dan berpose di depan sebuah rumah.
      - >-
        Seperti yang tercakup dalam jawaban lain, satu-satunya pilihan Anda
        adalah menemui dokter hewan untuk melakukan operasi.
  - source_sentence: Industri Musik Memberi Penghormatan kepada Whitney Houston
    sentences:
      - Setiap bahasa diresapi oleh nilai-nilai budaya yang dibenamkannya.
      - Sebuah pesawat merah dan putih terbang di hari yang cerah.
      - Industri musik berduka atas Whitney Houston
  - source_sentence: Pria itu menggunakan pedang untuk mengiris botol plastik.
    sentences:
      - Seorang pria sedang melakukan push up.
      - Seorang pria mengiris botol plastik dengan pedang.
      - >-
        Untuk melatih diri Anda menggunakan pintasan keyboard, cabut mouse Anda
        selama beberapa hari.
  - source_sentence: seorang anak laki-laki memanjat dinding batu
    sentences:
      - Anak memerah susu sapi di luar.
      - >-
        Selalu sulit ketika orang tua menolak untuk melihat apa yang tampak
        jelas bagi seorang guru.
      - Lima bulldog sedang berlomba di jalur pasir.
  - source_sentence: Pekerjaan pembongkaran dimulai di Stadion Don Valley
    sentences:
      - Kedua wanita itu sedang bermain game.
      - >-
        Tingkat pemogokan bowling didefinisikan untuk pemain bowling sebagai
        jumlah rata-rata bola yang dilempar per gawang yang diambil.
      - Pekerjaan pembongkaran dimulai di stadion
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: >-
      SentenceTransformer based on
      sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts eval
          type: sts-eval
        metrics:
          - type: pearson_cosine
            value: -0.040452290633263735
            name: Pearson Cosine
          - type: spearman_cosine
            value: -0.06939895859321697
            name: Spearman Cosine

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 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': 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 = [
    'Pekerjaan pembongkaran dimulai di Stadion Don Valley',
    'Pekerjaan pembongkaran dimulai di stadion',
    'Kedua wanita itu sedang bermain game.',
]
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]

Evaluation

Metrics

Semantic Similarity

Dataset: sts-eval
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	-0.0405
spearman_cosine	-0.0694

Training Details

Training Dataset

Unnamed Dataset

Size: 1,200 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string float
details
min: 5 tokens
mean: 16.78 tokens
max: 45 tokens

min: 6 tokens
mean: 16.67 tokens
max: 49 tokens

min: 0.0
mean: 115.43
max: 398.6

	sentence_0	sentence_1	label
type	string	string	float
details	min: 5 tokens mean: 16.78 tokens max: 45 tokens	min: 6 tokens mean: 16.67 tokens max: 49 tokens	min: 0.0 mean: 115.43 max: 398.6

Samples:

sentence_0	sentence_1	label
`Pendekatan terbaik adalah bermain dengan kucing Anda setiap malam sebelum tidur.`	`Trik yang saya lakukan adalah memegang dan memeluk kucing saya erat-erat jika mereka mengganggu saya di malam hari.`	`234.8`
`Anjing berwarna gelap berdiri di lapangan berumput.`	`Seekor anjing abu-abu berdiri di lapangan berumput.`	`133.6`
`Bebek putih berdiri di tanah.`	`Seorang wanita bertopi hitam berdiri di dekat kereta bawah tanah.`	`96.6`

Loss: CosineSimilarityLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
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
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: 4
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
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
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	sts-eval_spearman_cosine
1.0	75	-0.1137
1.3333	100	-0.1012
2.0	150	-0.0837
2.6667	200	-0.0694

Framework Versions

Python: 3.11.13
Sentence Transformers: 4.1.0
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Accelerate: 1.7.0
Datasets: 2.14.4
Tokenizers: 0.21.1

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",
}