This is a sentence-transformers model finetuned from google/bert_uncased_L-2_H-128_A-2. It maps sentences & paragraphs to a 128-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: google/bert_uncased_L-2_H-128_A-2
Maximum Sequence Length: 128 tokens
Output Dimensionality: 128 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

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': 128, 'pooling_mode': 'mean', '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("swardiantara/bert-tiny-snli-k3-fixed-euclidean")
# Run inference
sentences = [
    'A couple play in the tide with their young son. [SEP] The family is on vacation.',
    'A woman with a panda hat and headphones is in front of a man outside in the snow. [SEP] The man is on the beach.',
    'Male standing in the roadway, he is wearing a light colored shirt and holding a backpack. [SEP] A male is watching his dogs play.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 128]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9983, 0.9951],
#         [0.9983, 1.0000, 0.9962],
#         [0.9951, 0.9962, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 3,845,587 training samples
Columns: text_a, text_b, and label
Approximate statistics based on the first 100 samples:
text_a text_b label
type string string list
modality text text
details
min: 13 tokens
mean: 24.67 tokens
max: 47 tokens
min: 22 tokens
mean: 28.88 tokens
max: 43 tokens
size: 2 elements

Samples:

text_a	text_b	label
`A person on a horse jumps over a broken down airplane. [SEP] A person is training his horse for a competition.`	`A man in goggles and a hat is sitting in the street holding something and wearing white gloves. [SEP] The man is a performance artist.`	`[1.0, 0.0]`
`A person on a horse jumps over a broken down airplane. [SEP] A person is training his horse for a competition.`	`Two boys and a woman standing in front of a Pronto Pups Hamburger stand. [SEP] People are outside.`	`[0.0, 0.5]`
`A person on a horse jumps over a broken down airplane. [SEP] A person is training his horse for a competition.`	`A little girl in a red shirt is suspended in midair on a contraption, as a man wearing white shorts looks up at her. [SEP] A little girl and a man are looking at each other.`	`[0.0, 0.5]`

Loss: [object Object].OrdinalProxyContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 1024
learning_rate: 1e-05
load_best_model_at_end: True

All Hyperparameters

Click to expand

per_device_train_batch_size: 1024
num_train_epochs: 3
max_steps: -1
learning_rate: 1e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0
optim: adamw_torch
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: 1.0
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: 8
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: True
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: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.1331	500	0.7097
0.2662	1000	0.1189
0.3994	1500	0.1118
0.5325	2000	0.1091
0.6656	2500	0.1074
0.7987	3000	0.1064
0.9318	3500	0.1055
1.0	3756	-
1.0650	4000	0.1051
1.1981	4500	0.1049
1.3312	5000	0.1049
1.4643	5500	0.1043
1.5974	6000	0.1040
1.7306	6500	0.1039
1.8637	7000	0.1029
1.9968	7500	0.1030
2.0	7512	-
2.1299	8000	0.1033
2.2630	8500	0.1024
2.3962	9000	0.1024
2.5293	9500	0.1016
2.6624	10000	0.1017
2.7955	10500	0.1015
2.9286	11000	0.1014
3.0	11268	-

The bold row denotes the saved checkpoint.

Training Time

Training: 22.9 minutes
Evaluation: 2.5 seconds
Total: 22.9 minutes

Framework Versions

Python: 3.12.4
Sentence Transformers: 5.5.1
Transformers: 5.11.0
PyTorch: 2.5.1+cu121
Accelerate: 1.13.0
Datasets: 2.21.0
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",
}

	text_a	text_b	label
type	string	string	list
modality	text	text
details	min: 13 tokens mean: 24.67 tokens max: 47 tokens	min: 22 tokens mean: 28.88 tokens max: 43 tokens	size: 2 elements