This is a sentence-transformers model finetuned from RomainDarous/large_directOneEpoch_maxPooling_mistranslationModel on the corrupted_open_os_by_language 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: RomainDarous/large_directOneEpoch_maxPooling_mistranslationModel
Maximum Sequence Length: 128 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- corrupted_open_os_by_language

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: XLMRobertaModel 
  (1): MultiHeadGeneralizedPooling()
)

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("RomainDarous/large_directTwoEpoch_maxPooling_mistranslationModel")
# Run inference
sentences = [
    'Search for matching log entries',
    'quem te lembra? caralho tô assustada aqui kkkkk',
    'sendotasunik gabeko\\ egoera bistaratuko den ala ez adierazten du',
]
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

Semantic Similarity

Datasets: sts-eval and sts-test
Evaluated with EmbeddingSimilarityEvaluator

Metric	sts-eval	sts-test
pearson_cosine	0.9735	0.9735
spearman_cosine	0.8656	0.8656

Training Details

Training Dataset

corrupted_open_os_by_language

Dataset: corrupted_open_os_by_language at 9d25780
Size: 4,460,010 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string int
details
min: 6 tokens
mean: 18.33 tokens
max: 128 tokens
min: 4 tokens
mean: 26.47 tokens
max: 128 tokens
0: ~50.60%
1: ~49.40%

Samples:

sentence1	sentence2	score
`Check spelling. Print the document. Show completion window. General. Show help`	`Kontrolli õigekirja. присоединяюсь.`	`0`
`EXIF not supported for this file format.`	`Šiam failo formatui EXIF nepalaikomas.`	`1`
`This package includes the documentation for texlive everyhook`	`Paket ini menyertakan dokumentasi untuk texlive everyhook`	`1`

Loss: CoSENTLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "pairwise_cos_sim" 4}

Evaluation Dataset

corrupted_open_os_by_language

Dataset: corrupted_open_os_by_language at 9d25780
Size: 4,460,010 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string int
details
min: 5 tokens
mean: 17.71 tokens
max: 128 tokens
min: 3 tokens
mean: 26.95 tokens
max: 128 tokens
0: ~50.60%
1: ~49.40%

Samples:

sentence1	sentence2	score
`Could not identify the current seat.`	天天花着男人的钱还这这创造新词汇男权你可真牛批,你也就这一出了一问男权，就说是我是吧,到现在我也没听到你给我们讲的男权,你也就是在网上喷喷，现实走道都不敢探头自卑，你现实要把你女权的劲拿出来总低啥头,您老应该去国家教育局把男权加上是吧,你们女权天天说自己生活不好没地位，给你们地位了你们能干啥？用你们的女权打到全世界男性是吧,能相出男权这一词您老也是人才呀，是不是庆幸自己是个女的,活在自己想想的世界里不觉得孤单吗，假象有男权是吧,自己假象和男权还说自己不是田园女权,田园女权能连自己都骂说自己妈是驴爸是大鼎的也是奇葩呀,那我们国家大肆宣扬过你们这么田园女权吗，国家要的是女性人群自主自理，你们可好看看你们女权干的啥事,给你们女权地位高了，看看你们女权干的事n绿地集团高管怎么都不说呀，人家可是有钱有地位,也不是我们说三从四德洗衣做饭你们女权会吗？,那我问问你们女权干过啥惊天大事,还甩锅给孔子，还封建社会，那我问问你们女权在福利面前为啥说自己是女性呀不是社会主义社会吗不应该男女平等吗,天天自己也不知道是不是抱个手机天天欧巴欧巴，你家那位要是不陪你看一会就会问你是不是不爱我了是吧大姐,您老也就赚这白菜钱操心国家事,中国五千年的历史被您老一句否决，还嘲讽人家日本女性，好意思说自己不是女权，三从四德流传这么久到您这变成日本文化了,我就想问问男权您老是怎么想的,那你问孔子老人家呗为什么女人要三从四德,我说的是女权你干嘛自己对号入座,连中华人民传承的东西都不认跟我这谈男权,还男权您老给我举个例子呗，让我们男权听听都是h啥,这些不都是你们女权的标准吗？,还男权，您老醒醒吧这里是现实，不是你的公主世界，总觉得自己多么多么重要，地球没你是不能转了还是人类要灭亡呀,我真的想问一句你给我找一条男权的新闻,咋了我们男人不能提女权呗你老授权了呗,那我们谈论田园女权你老对号入座干嘛,天天过节要礼物，还嫌弃自己男朋友没有钱，我寻思你找个有钱人包养你呗，对了有钱人怎么可能看上你这种女权的呢,还要孩子跟女方姓我也没看见你没跟你妈姓呀,年年过节男人给你们送礼物你们女人给男人送过礼物吗？，一问我不是陪着他吗我对他说我爱你了这不是最好的礼物吗？，男人只要不送礼物就是不爱你们了呗,人家国际女权讲的男人能做的我们女人也能做，田园女权男人能做的我们女人为啥要做,还男权我笑了，以前结婚几头牛换个衣服原装的，现在几十万彩...	`0`
`Undoing Date and Time Adjustment`	`正在取消日期和时间调整`	`1`
`Dependency package for gsl_2_6 gnu hpc`	`Pacotes de desenvolvimento do KDE`	`1`

Loss: CoSENTLoss with these parameters:
json
1{ 2 "scale": 20.0, 3 "similarity_fct": "pairwise_cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
num_train_epochs: 1
warmup_ratio: 0.1

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
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: 1.0
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: 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	corrupted open os by language loss	sts-eval_spearman_cosine	sts-test_spearman_cosine
1.0	55751	0.2483	0.2853	0.8656	-
-1	-1	-	-	-	0.8656

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.4.1
Transformers: 4.48.2
PyTorch: 2.1.2+cu121
Accelerate: 1.3.0
Datasets: 2.16.1
Tokenizers: 0.21.0

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",
}

CoSENTLoss

bibtex

@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},
}

	sentence1	sentence2	score
type	string	string	int
details	min: 6 tokens mean: 18.33 tokens max: 128 tokens	min: 4 tokens mean: 26.47 tokens max: 128 tokens	0: ~50.60% 1: ~49.40%