swardiantara/bert-tiny-snli-k1-fixed-cosine

SentenceTransformer based on google/bert_uncased_L-2_H-128_A-2

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.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("swardiantara/bert-tiny-snli-k1-fixed-cosine")
# Run inference
sentences = [
    'A barber waiting for customers. [SEP] The barber is closing the shop at the end of the day.',
    'A young shirtless boy in kakhi pants is kneeling in a marsh while someone splashes nearby. [SEP] Two people are riding on a ferris wheel at the fair.',
    'A young shirtless boy in kakhi pants is kneeling in a marsh while someone splashes nearby. [SEP] Two people are riding on a ferris wheel at the fair.',
]
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, 0.9995, 0.9995],
#         [0.9995, 1.0000, 1.0000],
#         [0.9995, 1.0000, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 549,370 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: 33.8 tokens max: 67 tokens	min: 30 tokens mean: 33.69 tokens max: 36 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 young boy is posing for a picture at the beach next to a yellow watering can on a stick and a red folding chair. [SEP] The boy loves the beach.	[1.0, 0.0]
  A person on a horse jumps over a broken down airplane. [SEP] A person is at a diner, ordering an omelette.	A young shirtless boy in kakhi pants is kneeling in a marsh while someone splashes nearby. [SEP] Two people are riding on a ferris wheel at the fair.	[1.0, 0.0]
  A person on a horse jumps over a broken down airplane. [SEP] A person is outdoors, on a horse.	A girl in a white shirt is sitting on a park bench with a dog next to her. [SEP] The girl and the dog are outdoors.	[1.0, 0.0]

• Loss: main.OrdinalProxyContrastiveLoss

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 1024
• num_train_epochs: 10
• learning_rate: 2e-05
• load_best_model_at_end: True

All Hyperparameters

Click to expand

• per_device_train_batch_size: 1024
• num_train_epochs: 10
• max_steps: -1
• learning_rate: 2e-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
0.9311	500	0.0016
1.0	537	-
1.8622	1000	0.0001
2.0	1074	-
2.7933	1500	0.0000
3.0	1611	-
3.7244	2000	0.0000
4.0	2148	-
4.6555	2500	0.0000
5.0	2685	-
5.5866	3000	0.0000
6.0	3222	-
6.5177	3500	0.0000
7.0	3759	-
7.4488	4000	0.0000
8.0	4296	-
8.3799	4500	0.0000
9.0	4833	-
9.3110	5000	0.0000
10.0	5370	-

• The bold row denotes the saved checkpoint.

Training Time

• Training: 14.2 minutes
• Evaluation: 1.1 minutes
• Total: 15.3 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

@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",
}