TurkEmbed4STS / README.md

ozayezerceli

Upload 10 files

813afca verified 10 months ago

preview code

raw

history blame contribute delete

34.9 kB

metadata

language:
  - tr
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:482091
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
  - loss:CoSENTLoss
base_model: Alibaba-NLP/gte-multilingual-base
widget:
  - source_sentence: >-
      Ya da dışarı çıkıp yürü ya da biraz koşun. Bunu düzenli olarak yapmıyorum
      ama Washington bunu yapmak için harika bir yer.
    sentences:
      - “Washington's yürüyüş ya da koşu için harika bir yer.”
      - H-2A uzaylılar Amerika Birleşik Devletleri'nde zaman kısa süreleri var.
      - “Washington'da düzenli olarak yürüyüşe ya da koşuya çıkıyorum.”
  - source_sentence: >-
      Orta yaylalar ve güney kıyıları arasındaki kontrast daha belirgin
      olamazdı.
    sentences:
      - >-
        İşitme Yardımı Uyumluluğu Müzakere Kuralları Komitesi, Federal İletişim
        Komisyonu'nun bir ürünüdür.
      - Dağlık ve sahil arasındaki kontrast kolayca işaretlendi.
      - Kontrast işaretlenemedi.
  - source_sentence: >-
      Bir 1997 Henry J. Kaiser Aile Vakfı anket yönetilen bakım planlarında
      Amerikalılar temelde kendi bakımı ile memnun olduğunu bulundu.
    sentences:
      - Kaplanları takip ederken çok sessiz olmalısın.
      - >-
        Henry Kaiser vakfı insanların sağlık hizmetlerinden hoşlandığını
        gösteriyor.
      - >-
        Henry Kaiser Vakfı insanların sağlık hizmetlerinden nefret ettiğini
        gösteriyor.
  - source_sentence: Eminim yapmışlardır.
    sentences:
      - Eminim öyle yapmışlardır.
      - Batı Teksas'ta 100 10 dereceydi.
      - Eminim yapmamışlardır.
  - source_sentence: >-
      Ve gerçekten, baba haklıydı, oğlu zaten her şeyi tecrübe etmişti, her şeyi
      denedi ve daha az ilgileniyordu.
    sentences:
      - Oğlu her şeye olan ilgisini kaybediyordu.
      - Pek bir şey yapmadım.
      - Baba oğlunun tecrübe için hala çok şey olduğunu biliyordu.
datasets:
  - emrecan/all-nli-tr
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on Alibaba-NLP/gte-multilingual-base
    results:
      - task:
          type: triplet
          name: Triplet
        dataset:
          name: all nli tr test
          type: all-nli-tr-test
        metrics:
          - type: cosine_accuracy
            value: 0.8966145437983908
            name: Cosine Accuracy
          - type: cosine_accuracy
            value: 0.9351753453772582
            name: Cosine Accuracy
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test
          type: sts-test
        metrics:
          - type: pearson_cosine
            value: 0.8043925123766598
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.804133282756889
            name: Spearman Cosine
          - type: pearson_cosine
            value: 0.8133873820848544
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8199552151367876
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts22 test
          type: sts22-test
        metrics:
          - type: pearson_cosine
            value: 0.647912337747937
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6694072470896322
            name: Spearman Cosine
          - type: pearson_cosine
            value: 0.6514085062457564
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.6827342891126081
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev gte multilingual base
          type: sts-dev-gte-multilingual-base
        metrics:
          - type: pearson_cosine
            value: 0.838717139426684
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8428367492381358
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test gte multilingual base
          type: sts-test-gte-multilingual-base
        metrics:
          - type: pearson_cosine
            value: 0.8133873820848544
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8199552151367876
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb dev 768
          type: stsb-dev-768
        metrics:
          - type: pearson_cosine
            value: 0.870311456444647
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8747522169942328
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb dev 512
          type: stsb-dev-512
        metrics:
          - type: pearson_cosine
            value: 0.8696934286998554
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8753487201891684
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb dev 256
          type: stsb-dev-256
        metrics:
          - type: pearson_cosine
            value: 0.8644706498119142
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.873468734899321
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb dev 128
          type: stsb-dev-128
        metrics:
          - type: pearson_cosine
            value: 0.8591309130178328
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8700377378574327
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb dev 64
          type: stsb-dev-64
        metrics:
          - type: pearson_cosine
            value: 0.8479124810212979
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8655596653561272
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb test 768
          type: stsb-test-768
        metrics:
          - type: pearson_cosine
            value: 0.8455412308380735
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8535290217691063
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb test 512
          type: stsb-test-512
        metrics:
          - type: pearson_cosine
            value: 0.8464773608783734
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8553900248212041
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb test 256
          type: stsb-test-256
        metrics:
          - type: pearson_cosine
            value: 0.8443046458551826
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8550098621393595
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb test 128
          type: stsb-test-128
        metrics:
          - type: pearson_cosine
            value: 0.8363964421208214
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8511193715667303
            name: Spearman Cosine
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: stsb test 64
          type: stsb-test-64
        metrics:
          - type: pearson_cosine
            value: 0.8235450515966374
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8460761238725121
            name: Spearman Cosine

SentenceTransformer based on Alibaba-NLP/gte-multilingual-base

This is a sentence-transformers model finetuned from Alibaba-NLP/gte-multilingual-base on the all-nli-tr dataset. It maps sentences & paragraphs to a 768-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: Alibaba-NLP/gte-multilingual-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 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: NewModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

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 = [
    '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, 768]

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

Evaluation

Metrics

Triplet

Dataset: all-nli-tr-test
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.8966

Semantic Similarity

Datasets: sts-test, sts22-test, sts-dev-gte-multilingual-base, sts-test-gte-multilingual-base, sts-test, sts22-test, stsb-dev-768, stsb-dev-512, stsb-dev-256, stsb-dev-128, stsb-dev-64, stsb-test-768, stsb-test-512, stsb-test-256, stsb-test-128 and stsb-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-test	sts22-test	sts-dev-gte-multilingual-base	sts-test-gte-multilingual-base	stsb-dev-768	stsb-dev-512	stsb-dev-256	stsb-dev-128	stsb-dev-64	stsb-test-768	stsb-test-512	stsb-test-256	stsb-test-128	stsb-test-64
pearson_cosine	0.8134	0.6514	0.8387	0.8134	0.8703	0.8697	0.8645	0.8591	0.8479	0.8455	0.8465	0.8443	0.8364	0.8235
spearman_cosine	0.82	0.6827	0.8428	0.82	0.8748	0.8753	0.8735	0.87	0.8656	0.8535	0.8554	0.855	0.8511	0.8461

Triplet

Dataset: all-nli-tr-test
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.9352

Training Details

Training Dataset

all-nli-tr

Dataset: all-nli-tr at daeabfb
Size: 482,091 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 10.51 tokens
max: 27 tokens

min: 6 tokens
mean: 10.47 tokens
max: 27 tokens

min: 0.0
mean: 2.23
max: 5.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 10.51 tokens max: 27 tokens	min: 6 tokens mean: 10.47 tokens max: 27 tokens	min: 0.0 mean: 2.23 max: 5.0

Samples:

sentence1	sentence2	score
`Bir uçak kalkıyor.`	`Bir hava uçağı kalkıyor.`	`5.0`
`Bir adam büyük bir flüt çalıyor.`	`Bir adam flüt çalıyor.`	`3.8`
`Bir adam pizzaya rendelenmiş peynir yayıyor.`	`Bir adam pişmemiş pizzaya rendelenmiş peynir yayıyor.`	`3.8`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Evaluation Dataset

all-nli-tr

Dataset: all-nli-tr at daeabfb
Size: 6,567 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 15.89 tokens
max: 39 tokens

min: 6 tokens
mean: 16.02 tokens
max: 49 tokens

min: 0.0
mean: 2.1
max: 5.0

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 15.89 tokens max: 39 tokens	min: 6 tokens mean: 16.02 tokens max: 49 tokens	min: 0.0 mean: 2.1 max: 5.0

Samples:

sentence1	sentence2	score
`Şapkalı bir adam dans ediyor.`	`Sert şapka takan bir adam dans ediyor.`	`5.0`
`Küçük bir çocuk ata biniyor.`	`Bir çocuk ata biniyor.`	`4.75`
`Bir adam yılana fare yediriyor.`	`Adam yılana fare yediriyor.`	`5.0`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "CoSENTLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
learning_rate: 1e-05
weight_decay: 0.01
num_train_epochs: 10
warmup_ratio: 0.1
warmup_steps: 144
bf16: 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: 32
per_device_eval_batch_size: 32
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: 1e-05
weight_decay: 0.01
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 10
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 144
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: 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
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-tr-test_cosine_accuracy	sts-test_spearman_cosine	sts22-test_spearman_cosine	sts-dev-gte-multilingual-base_spearman_cosine	sts-test-gte-multilingual-base_spearman_cosine	stsb-dev-768_spearman_cosine	stsb-dev-512_spearman_cosine	stsb-dev-256_spearman_cosine	stsb-dev-128_spearman_cosine	stsb-dev-64_spearman_cosine	stsb-test-768_spearman_cosine	stsb-test-512_spearman_cosine	stsb-test-256_spearman_cosine	stsb-test-128_spearman_cosine	stsb-test-64_spearman_cosine
0	0	-	-	0.8966	0.8041	0.6694	-	-	-	-	-	-	-	-	-	-	-	-
0.1327	1000	2.5299	3.3893	-	-	-	0.8318	-	-	-	-	-	-	-	-	-	-	-
0.2655	2000	2.1132	3.3050	-	-	-	0.8345	-	-	-	-	-	-	-	-	-	-	-
0.3982	3000	5.1488	2.7752	-	-	-	0.8481	-	-	-	-	-	-	-	-	-	-	-
0.5310	4000	5.4103	2.7242	-	-	-	0.8445	-	-	-	-	-	-	-	-	-	-	-
0.6637	5000	5.1896	2.6701	-	-	-	0.8451	-	-	-	-	-	-	-	-	-	-	-
0.7965	6000	5.0105	2.6489	-	-	-	0.8431	-	-	-	-	-	-	-	-	-	-	-
0.9292	7000	5.1059	2.6114	-	-	-	0.8428	-	-	-	-	-	-	-	-	-	-	-
1.0	7533	-	-	0.9352	0.8200	0.6827	-	0.8200	-	-	-	-	-	-	-	-	-	-
1.1111	200	34.2828	29.8737	-	-	-	-	-	0.8671	0.8671	0.8639	0.8606	0.8546	-	-	-	-	-
2.2222	400	28.038	28.8915	-	-	-	-	-	0.8740	0.8742	0.8720	0.8691	0.8648	-	-	-	-	-
3.3333	600	27.3829	29.3391	-	-	-	-	-	0.8747	0.8751	0.8728	0.8699	0.8653	-	-	-	-	-
4.4444	800	26.807	30.0090	-	-	-	-	-	0.8756	0.8761	0.8741	0.8710	0.8665	-	-	-	-	-
5.5556	1000	26.4543	30.5886	-	-	-	-	-	0.8753	0.8757	0.8739	0.8705	0.8662	-	-	-	-	-
6.6667	1200	26.0413	31.3750	-	-	-	-	-	0.8744	0.8751	0.8730	0.8698	0.8655	-	-	-	-	-
7.7778	1400	25.8221	31.6515	-	-	-	-	-	0.8752	0.8758	0.8739	0.8706	0.8661	-	-	-	-	-
8.8889	1600	25.6656	31.9805	-	-	-	-	-	0.8746	0.8752	0.8733	0.8700	0.8655	-	-	-	-	-
10.0	1800	25.5355	32.0454	-	-	-	-	-	0.8748	0.8753	0.8735	0.8700	0.8656	0.8535	0.8554	0.8550	0.8511	0.8461

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.3.1
Transformers: 4.49.0.dev0
PyTorch: 2.5.1+cu121
Accelerate: 1.2.1
Datasets: 3.2.0
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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}