This is a sentence-transformers model finetuned from nreimers/TinyBERT_L-4_H-312_v2. It maps sentences & paragraphs to a 312-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: nreimers/TinyBERT_L-4_H-312_v2
Maximum Sequence Length: 512 tokens
Output Dimensionality: 312 dimensions
Similarity Function: Cosine Similarity

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, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 312, '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("alantang2025/TinyBERT_L-4_H-312_v2-distilled-from-stsb-roberta-base-v2")
# Run inference
sentences = [
    'A restaurant front line, with a warmer in the front and a person in a red Coca Cola shirt cooking.',
    'The dog is wearing a clown suit.',
    'A group of girls ride an ATV.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 312]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000, -0.0939, -0.1122],
#         [-0.0939,  1.0000, -0.1206],
#         [-0.1122, -0.1206,  1.0000]])

Evaluation

Metrics

Semantic Similarity

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

Metric	sts-dev	sts-test
pearson_cosine	0.8037	0.753
spearman_cosine	0.8179	0.756

Knowledge Distillation

Evaluated with MSEEvaluator

Metric	Value
negative_mse	-50.2813

Training Details

Training Dataset

Unnamed Dataset

Size: 200,000 training samples
Columns: sentence and label
Approximate statistics based on the first 1000 samples:
sentence label
type string list
details
min: 4 tokens
mean: 12.24 tokens
max: 52 tokens
size: 312 elements

Samples:

sentence	label
`A person on a horse jumps over a broken down airplane.`	`[0.057932913303375244, 0.6749712228775024, -2.633713722229004, 1.7274808883666992, 1.3418258428573608, ...]`
`Children smiling and waving at camera`	`[-2.8878378868103027, 3.2693028450012207, 7.1657891273498535, 5.132803916931152, -2.36763858795166, ...]`
`A boy is jumping on skateboard in the middle of a red bridge.`	`[2.916928291320801, 3.217933177947998, 1.2827091217041016, 6.163186073303223, -1.0696818828582764, ...]`

Loss: MSELoss

Evaluation Dataset

Unnamed Dataset

Size: 10,000 evaluation samples
Columns: sentence and label
Approximate statistics based on the first 1000 samples:
sentence label
type string list
details
min: 5 tokens
mean: 13.23 tokens
max: 57 tokens
size: 312 elements

Samples:

sentence	label
`Two women are embracing while holding to go packages.`	`[-6.1593122482299805, -2.2116942405700684, 2.101496696472168, -1.9072985649108887, 1.6521663665771484, ...]`
`Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.`	`[-1.8597674369812012, 0.6282176971435547, 2.513129472732544, 3.8436083793640137, -3.6456544399261475, ...]`
`A man selling donuts to a customer during a world exhibition event held in the city of Angeles`	`[3.224872350692749, 3.18795108795166, -0.34250038862228394, -2.301283359527588, 3.2137651443481445, ...]`

Loss: MSELoss

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 64
per_device_eval_batch_size: 64
learning_rate: 0.0001
num_train_epochs: 1
warmup_ratio: 0.1
fp16: True
load_best_model_at_end: 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: 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: 0.0001
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: True
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: True
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}
tp_size: 0
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
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
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev_spearman_cosine	negative_mse	sts-test_spearman_cosine
0.032	100	0.8817	-	-	-	-
0.064	200	0.8019	-	-	-	-
0.096	300	0.6853	-	-	-	-
0.128	400	0.6058	-	-	-	-
0.16	500	0.5591	0.6318	0.7609	-63.1812	-
0.192	600	0.5267	-	-	-	-
0.224	700	0.5019	-	-	-	-
0.256	800	0.4851	-	-	-	-
0.288	900	0.4654	-	-	-	-
0.32	1000	0.4501	0.5671	0.7963	-56.7083	-
0.352	1100	0.4374	-	-	-	-
0.384	1200	0.4268	-	-	-	-
0.416	1300	0.4175	-	-	-	-
0.448	1400	0.4098	-	-	-	-
0.48	1500	0.405	0.5358	0.8082	-53.5812	-
0.512	1600	0.3929	-	-	-	-
0.544	1700	0.3898	-	-	-	-
0.576	1800	0.3845	-	-	-	-
0.608	1900	0.3774	-	-	-	-
0.64	2000	0.3732	0.5175	0.8140	-51.7472	-
0.672	2100	0.3705	-	-	-	-
0.704	2200	0.3682	-	-	-	-
0.736	2300	0.3654	-	-	-	-
0.768	2400	0.3607	-	-	-	-
0.8	2500	0.3569	0.5089	0.8169	-50.8933	-
0.832	2600	0.3538	-	-	-	-
0.864	2700	0.3536	-	-	-	-
0.896	2800	0.3514	-	-	-	-
0.928	2900	0.351	-	-	-	-
0.96	3000	0.3516	0.5028	0.8179	-50.2813	-
0.992	3100	0.3491	-	-	-	-
-1	-1	-	-	-	-	0.7560

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.12.9
Sentence Transformers: 5.1.2
Transformers: 4.51.3
PyTorch: 2.6.0
Accelerate: 1.11.0
Datasets: 3.6.0
Tokenizers: 0.21.4

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",
}

MSELoss

bibtex

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}

	sentence	label
type	string	list
details	min: 4 tokens mean: 12.24 tokens max: 52 tokens	size: 312 elements