SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'En la vendidos de junio pickup con 3.002 un del 27,4% en a mayo vehículo de gran otro Toyota, hatchback, creció por',
    'En la lista de los diez modelos más vendidos de junio aparece en primer lugar la pickup Toyota Hilux con 3.002 unidades que representan un crecimiento del 27,4% en relación a mayo, solo superado en vehículo de gran volumen por otro Toyota, el Yaris hatchback, que creció un 28 por ciento.',
    'El auto volvió a crecer de tamaño, entrando en el segmento C, con un equipamiento interior llamativo para el precio, que seguía siendo muy accesible.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9557, 0.7611],
#         [0.9557, 1.0000, 0.7616],
#         [0.7611, 0.7616, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 36,035 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 100 samples:
sentence_0 sentence_1
type string string
modality text text
details
min: 4 tokens
mean: 15.55 tokens
max: 37 tokens
min: 9 tokens
mean: 35.86 tokens
max: 72 tokens

Samples:

sentence_0	sentence_1
`hora del inicio del encuentro la era de MWh`	`Una hora antes del inicio del encuentro, la demanda era de 22.534 MWh.`
`El comportamiento riesgo genera`	`El mercado ve un comportamiento inusual del riesgo país genera sospechas`
`El consenso mercado enfoca en los instrumentos como el relación dado la inflación implícita semestre corre por que proyectaba meses.`	`El consenso de mercado se enfoca en los instrumentos CER como el vehículo con mejor relación de cobertura, dado que la inflación implícita del segundo semestre corre por debajo de lo que proyectaba el mercado hace unos meses.`

Loss: DenoisingAutoEncoderLoss with these parameters:
json
1{ 2 "decoder_name_or_path": "models/tsdae-ep1", 3 "need_retokenization": false 4}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 4
num_train_epochs: 1
per_device_eval_batch_size: 4
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

per_device_train_batch_size: 4
num_train_epochs: 1
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: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 4
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_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
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
0.0555	500	5.2347
0.1110	1000	4.4297
0.1665	1500	4.1614
0.2220	2000	4.0017
0.2775	2500	3.8804
0.3330	3000	3.7861
0.3885	3500	3.7142
0.4440	4000	3.6728
0.4995	4500	3.5872
0.5550	5000	3.5418
0.6105	5500	3.5456
0.6660	6000	3.5069
0.7215	6500	3.4841
0.7770	7000	3.4563
0.8325	7500	3.4269
0.8880	8000	3.3934
0.9435	8500	3.3259
0.9990	9000	3.3699

Training Time

Training: 43.7 minutes

Framework Versions

Python: 3.12.10
Sentence Transformers: 5.6.0
Transformers: 5.14.1
PyTorch: 2.13.0+cu130
Accelerate: 1.14.0
Datasets: 5.0.0
Tokenizers: 0.22.2

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",
}

DenoisingAutoEncoderLoss

bibtex

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}

	sentence_0	sentence_1
type	string	string
modality	text	text
details	min: 4 tokens mean: 15.55 tokens max: 37 tokens	min: 9 tokens mean: 35.86 tokens max: 72 tokens

Oblix15/tsdae-financiero

SentenceTransformer

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Training Details

Training Dataset

Unnamed Dataset

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Training Time

Framework Versions

Citation

BibTeX

Sentence Transformers

DenoisingAutoEncoderLoss

Oblix15/
tsdae-financiero