ozertuu/yemeksepeti-MiniLM-L12-v2

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, 'architecture': '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 = [
    'Kategori: İçecekler | İsim: Şalgam | Açıklama: Şalgam suyu | Mutfak: Kokoreç',
    'Kategori: Kokoreç | İsim: Kokoreç Dürüm XL | Açıklama: Dürüm kokoreç | Mutfak: Kokoreç',
    'Kategori: Kahvaltı | İsim: Menemen Extra | Açıklama: Domates, biber, yumurta | Mutfak: Kahvaltı',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9996, 0.1973],
#         [0.9996, 1.0000, 0.2010],
#         [0.1973, 0.2010, 1.0000]])

Evaluation

Metrics

Semantic Similarity

• Dataset: menu-embedding-eval
• Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8753
spearman_cosine	0.7485

Training Details

Training Dataset

Unnamed Dataset

• Size: 148,352 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: 24 tokens mean: 36.31 tokens max: 52 tokens	min: 24 tokens mean: 35.96 tokens max: 52 tokens	min: 1.0 mean: 1.0 max: 1.0

• Samples:

  sentence_0	sentence_1	label
  Kategori: Makarnalar | İsim: Ravioli | Açıklama: Peynirli ravioli, krema sos | Mutfak: İtalyan	Kategori: Makarnalar | İsim: Fettuccine Alfredo Extra | Açıklama: Kremalı tavuklu fettuccine | Mutfak: İtalyan	1.0
  Kategori: İçecekler | İsim: Su Özel | Açıklama: 0.5L | Mutfak: Tavuk	Kategori: İçecekler | İsim: Ayran Özel | Açıklama: Taze ayran | Mutfak: Tavuk	1.0
  Kategori: Yan Lezzetler | İsim: Turşu Extra | Açıklama: Karışık turşu | Mutfak: Kokoreç	Kategori: Kokoreç | İsim: Kokoreç Porsiyon Özel | Açıklama: Porsiyon kokoreç, pilav ile | Mutfak: Kokoreç	1.0

• Loss: main.LoggedMultipleNegativesRankingLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• per_device_eval_batch_size: 64
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• per_device_train_batch_size: 64
• num_train_epochs: 3
• 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: trackio
• eval_strategy: no
• per_device_eval_batch_size: 64
• 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_backend: None
• ddp_timeout: 1800
• fsdp: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• 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	menu-embedding-eval_spearman_cosine
0.2157	500	1.8984	-
0.4314	1000	1.5666	-
0.6471	1500	1.5590	-
0.8628	2000	1.5634	-
1.0	2318	-	0.7456
1.0785	2500	1.5603	-
1.2942	3000	1.5584	-
1.5099	3500	1.5602	-
1.7256	4000	1.5677	-
1.9413	4500	1.5574	-
2.0	4636	-	0.7468
2.1570	5000	1.5577	-
2.3727	5500	1.5592	-
2.5884	6000	1.5604	-
2.8041	6500	1.5681	-
3.0	6954	-	0.7485

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.2.0
• Transformers: 5.2.0
• PyTorch: 2.9.0+cu126
• Accelerate: 1.12.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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",
}