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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("DashReza7/sentence-transformers_paraphrase-multilingual-MiniLM-L12-v2_FINETUNED_on_torob_data_v4")
# Run inference
sentences = [
    'هایومکس',
    'ژل هایومکس ولومایزر 2 سی سی',
    'دزدگیر پاناتک مدل P-CA501 دزدگیر پاناتک P-CA501-2 دزدگیر پاناتک مدل P-CA501-2',
]
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

Binary Classification

Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8396
cosine_accuracy_threshold	0.7624
cosine_f1	0.8952
cosine_f1_threshold	0.7235
cosine_precision	0.8454
cosine_recall	0.9511
cosine_ap	0.9296
dot_accuracy	0.8128
dot_accuracy_threshold	18.1649
dot_f1	0.8798
dot_f1_threshold	17.5963
dot_precision	0.8227
dot_recall	0.9454
dot_ap	0.9138
manhattan_accuracy	0.8363
manhattan_accuracy_threshold	56.6106
manhattan_f1	0.8929
manhattan_f1_threshold	60.147
manhattan_precision	0.8404
manhattan_recall	0.9525
manhattan_ap	0.9275
euclidean_accuracy	0.8367
euclidean_accuracy_threshold	3.6917
euclidean_f1	0.8933
euclidean_f1_threshold	3.6917
euclidean_precision	0.8525
euclidean_recall	0.9383
euclidean_ap	0.9275
max_accuracy	0.8396
max_accuracy_threshold	56.6106
max_f1	0.8952
max_f1_threshold	60.147
max_precision	0.8525
max_recall	0.9525
max_ap	0.9296

Binary Classification

Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.8314
cosine_accuracy_threshold	0.7449
cosine_f1	0.8898
cosine_f1_threshold	0.7428
cosine_precision	0.8502
cosine_recall	0.9332
cosine_ap	0.9253
dot_accuracy	0.8083
dot_accuracy_threshold	18.1676
dot_f1	0.8762
dot_f1_threshold	17.1061
dot_precision	0.8156
dot_recall	0.9464
dot_ap	0.9079
manhattan_accuracy	0.8277
manhattan_accuracy_threshold	53.9454
manhattan_f1	0.8875
manhattan_f1_threshold	59.6646
manhattan_precision	0.8337
manhattan_recall	0.9487
manhattan_ap	0.9231
euclidean_accuracy	0.8274
euclidean_accuracy_threshold	3.4869
euclidean_f1	0.8875
euclidean_f1_threshold	3.7965
euclidean_precision	0.8363
euclidean_recall	0.9452
euclidean_ap	0.9232
max_accuracy	0.8314
max_accuracy_threshold	53.9454
max_f1	0.8898
max_f1_threshold	59.6646
max_precision	0.8502
max_recall	0.9487
max_ap	0.9253

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 2e-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: True
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: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	max_ap
None	0	-	-	0.8131
0.1558	500	0.0262	-	-
0.3116	1000	0.0184	-	-
0.4674	1500	0.0173	-	-
0.6232	2000	0.0164	0.0155	0.9253
0.7791	2500	0.016	-	-
0.9349	3000	0.0155	-	-
1.0	3209	-	-	0.9296

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.1
Transformers: 4.42.4
PyTorch: 2.4.0+cu121
Accelerate: 0.32.1
Datasets: 2.21.0
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",
}

ContrastiveLoss

bibtex

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, 
    title={Dimensionality Reduction by Learning an Invariant Mapping}, 
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}