x1saint/gte-small-triplet-tr

SentenceTransformer based on Supabase/gte-small

This is a sentence-transformers model finetuned from Supabase/gte-small on the all-nli-tr dataset. 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: Supabase/gte-small
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • all-nli-tr
• Language: tr

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': 512, '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("x1saint/gte-small-triplet-tr")
# Run inference
sentences = [
    'Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti, her şeyi denedi ve daha az ilgileniyordu.',
    'Oğlu her şeye olan ilgisini kaybediyordu.',
    'Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu.',
]
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

Triplet

• Dataset: all-nli-dev
• Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.8552

Training Details

Training Dataset

all-nli-tr

• Dataset: all-nli-tr at daeabfb
• Size: 482,091 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: 47.48 tokens max: 301 tokens	min: 4 tokens mean: 25.16 tokens max: 80 tokens	min: 5 tokens mean: 23.67 tokens max: 90 tokens

• Samples:

  anchor	positive	negative
  Mevsim boyunca ve sanırım senin seviyendeyken onları bir sonraki seviyeye düşürürsün. Eğer ebeveyn takımını çağırmaya karar verirlerse Braves üçlü A'dan birini çağırmaya karar verirlerse çifte bir adam onun yerine geçmeye gider ve bekar bir adam gelir.	Eğer insanlar hatırlarsa, bir sonraki seviyeye düşersin.	Hiçbir şeyi hatırlamazlar.
  Numaramızdan biri talimatlarınızı birazdan yerine getirecektir.	Ekibimin bir üyesi emirlerinizi büyük bir hassasiyetle yerine getirecektir.	Şu anda boş kimsek yok, bu yüzden sen de harekete geçmelisin.
  Bunu nereden biliyorsun? Bütün bunlar yine onların bilgileri.	Bu bilgi onlara ait.	Hiçbir bilgileri yok.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

all-nli-tr

• Dataset: all-nli-tr at daeabfb
• Size: 6,567 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: 45.12 tokens max: 201 tokens	min: 7 tokens mean: 25.11 tokens max: 98 tokens	min: 5 tokens mean: 23.81 tokens max: 64 tokens

• Samples:

  anchor	positive	negative
  Bilemiyorum. Onunla ilgili karışık duygularım var. Bazen ondan hoşlanıyorum ama aynı zamanda birisinin onu dövmesini görmeyi seviyorum.	Çoğunlukla ondan hoşlanıyorum, ama yine de birinin onu dövdüğünü görmekten zevk alıyorum.	O benim favorim ve kimsenin onu yendiğini görmek istemiyorum.
  Sen ve arkadaşların burada hoş karşılanmaz, Severn söyledi.	Severn orada insanların hoş karşılanmadığını söyledi.	Severn orada insanların her zaman hoş karşılanacağını söyledi.
  Gecenin en aşağısı ne olduğundan emin değilim.	Dün gece ne kadar soğuk oldu bilmiyorum.	Dün gece hava 37 dereceydi.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 64
• gradient_accumulation_steps: 4
• learning_rate: 1e-05
• warmup_ratio: 0.1
• bf16: True
• dataloader_num_workers: 4

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 64
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 4
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 1e-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: 3
• 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: True
• 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: 4
• 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
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss	all-nli-dev_cosine_accuracy
0.1327	500	9.1341	1.4261	0.7835
0.2655	1000	5.2529	1.2543	0.7967
0.3982	1500	4.5877	1.1583	0.8119
0.5310	2000	4.229	1.0974	0.8171
0.6637	2500	4.0158	1.0592	0.8238
0.7965	3000	3.7869	1.0161	0.8310
0.9292	3500	3.6862	0.9897	0.8372
1.0619	4000	3.5519	0.9751	0.8406
1.1946	4500	3.3986	0.9596	0.8421
1.3274	5000	3.3479	0.9377	0.8435
1.4601	5500	3.3104	0.9296	0.8465
1.5929	6000	3.2255	0.9178	0.8467
1.7256	6500	3.1998	0.9077	0.8514
1.8584	7000	3.1491	0.9017	0.8496
1.9911	7500	3.1337	0.8955	0.8511
2.1237	8000	3.052	0.8885	0.8526
2.2565	8500	2.9998	0.8836	0.8524
2.3892	9000	2.9835	0.8794	0.8517
2.5220	9500	2.9941	0.8778	0.8532
2.6547	10000	2.9704	0.8744	0.8555
2.7875	10500	2.9731	0.8723	0.8541
2.9202	11000	2.9221	0.8717	0.8552

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.4.1
• Transformers: 4.48.3
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.3.0
• Tokenizers: 0.21.0

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}
}