tomaarsen/TinyBERT_L-4_H-312_v2-distilled-from-stsb-roberta-base-v2-new

SentenceTransformer based on nreimers/TinyBERT_L-4_H-312_v2

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 retrieval.

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
• 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': 312, '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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("tomaarsen/TinyBERT_L-4_H-312_v2-distilled-from-stsb-roberta-base-v2-new")
# Run inference
sentences = [
    'A black dog is drinking next to a brown and white dog that is looking at an orange ball in the lake, whilst a horse and rider passes behind.',
    'There are two people running around a track in lane three and the one wearing a blue shirt with a green thing over the eyes is just barely ahead of the guy wearing an orange shirt and sunglasses.',
    'the guy is dead',
]
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,  0.0220, -0.0339],
#         [ 0.0220,  1.0000, -0.0620],
#         [-0.0339, -0.0620,  1.0000]])

Evaluation

Metrics

Semantic Similarity

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

Metric	sts-dev	sts-test
pearson_cosine	0.8012	0.7444
spearman_cosine	0.8161	0.745

Knowledge Distillation

• Evaluated with MSEEvaluator

Metric	Value
negative_mse	-50.1352

Training Details

Training Dataset

Unnamed Dataset

• Size: 200,000 training samples
• Columns: sentence and label
• Approximate statistics based on the first 100 samples:

  	sentence	label
  type	string	list
  modality	text
  details	min: 8 tokens mean: 17.05 tokens max: 52 tokens	size: 312 elements

• Samples:

  sentence	label
  A person on a horse jumps over a broken down airplane.	[0.10402965545654297, 0.6209299564361572, -2.594356060028076, 1.7435719966888428, 1.3561537265777588, ...]
  Children smiling and waving at camera	[-2.6501543521881104, 3.3227877616882324, 7.259965896606445, 5.15726375579834, -2.4549741744995117, ...]
  A boy is jumping on skateboard in the middle of a red bridge.	[3.1701011657714844, 2.892836332321167, 1.3900458812713623, 6.316932201385498, -0.5788676142692566, ...]

• Loss: MSELoss with these parameters:

  {
      "projection_dim": null
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 10,000 evaluation samples
• Columns: sentence and label
• Approximate statistics based on the first 100 samples:

  	sentence	label
  type	string	list
  modality	text
  details	min: 7 tokens mean: 17.97 tokens max: 45 tokens	size: 312 elements

• Samples:

  sentence	label
  Two women are embracing while holding to go packages.	[-6.30838680267334, -1.7273662090301514, 2.035383701324463, -2.169445514678955, 1.2417519092559814, ...]
  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.	[-1.803275465965271, 0.832683801651001, 2.49751877784729, 3.88055419921875, -3.3611345291137695, ...]
  A man selling donuts to a customer during a world exhibition event held in the city of Angeles	[3.40816593170166, 2.9330062866210938, -0.4831739068031311, -2.500065565109253, 3.062544584274292, ...]

• Loss: MSELoss with these parameters:

  {
      "projection_dim": null
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• num_train_epochs: 1
• learning_rate: 0.0001
• warmup_steps: 0.1
• fp16: True
• per_device_eval_batch_size: 64
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• per_device_train_batch_size: 64
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 0.0001
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• 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: 1.0
• label_smoothing_factor: 0.0
• bf16: False
• fp16: True
• 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: 64
• 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: []
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• 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	Validation Loss	sts-dev_spearman_cosine	negative_mse	sts-test_spearman_cosine
0.032	100	0.8848	-	-	-	-
0.064	200	0.8060	-	-	-	-
0.096	300	0.6912	-	-	-	-
0.128	400	0.6111	-	-	-	-
0.16	500	0.5628	0.6332	0.7578	-63.3232	-
0.192	600	0.5298	-	-	-	-
0.224	700	0.5041	-	-	-	-
0.256	800	0.4870	-	-	-	-
0.288	900	0.4668	-	-	-	-
0.32	1000	0.4519	0.5674	0.7936	-56.7440	-
0.352	1100	0.4383	-	-	-	-
0.384	1200	0.4281	-	-	-	-
0.416	1300	0.4182	-	-	-	-
0.448	1400	0.4106	-	-	-	-
0.48	1500	0.4058	0.5341	0.8055	-53.4073	-
0.512	1600	0.3932	-	-	-	-
0.544	1700	0.3908	-	-	-	-
0.576	1800	0.3848	-	-	-	-
0.608	1900	0.3781	-	-	-	-
0.64	2000	0.3736	0.5161	0.8107	-51.6070	-
0.672	2100	0.3714	-	-	-	-
0.704	2200	0.3690	-	-	-	-
0.736	2300	0.3663	-	-	-	-
0.768	2400	0.3612	-	-	-	-
0.8	2500	0.3574	0.5084	0.8150	-50.8375	-
0.832	2600	0.3548	-	-	-	-
0.864	2700	0.3539	-	-	-	-
0.896	2800	0.3519	-	-	-	-
0.928	2900	0.3518	-	-	-	-
0.96	3000	0.3516	0.5017	0.8157	-50.1695	-
0.992	3100	0.3487	-	-	-	-
1.0	3125	-	0.5014	0.8161	-50.1352	-
-1	-1	-	-	-	-	0.7450

• The bold row denotes the saved checkpoint.

Training Time

• Training: 2.5 minutes
• Evaluation: 1.1 minutes
• Total: 3.7 minutes

Framework Versions

• Python: 3.11.6
• Sentence Transformers: 5.5.0.dev0
• Transformers: 5.6.2
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0.dev0
• Datasets: 4.8.4
• Tokenizers: 0.22.2

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",
}

MSELoss

@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",
}