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-yelp-k5-fixed-cosine")
# Run inference
sentences = [
    "Everytime I eat at this location I end up with a sick stomach.  I don't have that problem at other Arby's.  The dining area is clean and everything else seems ok but I always get a sick stomach.  Maybe they should relook at their food prep.",
    "Let me start by saying I have no idea about the food here, it could be amazing and knock my socks off, but I will not be back to find out.\\n\\nWe came here on a Saturday night and it was annoying.  The service was decent, the drinks pretty strong....that's all that I can say in the good arena here.  \\n\\nThe atmosphere is boring and uninspired, the decor blah and the clientele douchey. (if that's even a word)  Prime example: a 45 year old guy in an Affliction shirt with a sparkly peace sign on the back...what?!  There have to be better places to hang out in Scottsdale.",
    'WOW.... So I received a coupon in the mail for a buy one get one buffet, so me and the BF decided to go out and try it. Well, we walk in on a Sunday night and that might have been our first mistake. All of the food seemed like it had been sitting there since lunch time. It was old, and cold, and honestly, we were both worried about getting sick afterward. The place was empty, and our server still left our drinks empty and dirty plates on the table.\\n\\nPeople were PILING on the crab legs, and so I gave them a try... overcooked and watery. The \\"clarified butter\\" next to it was margarine, and honestly, I walked away thanking GOD that we didn\'t pay full price. I think McDonalds would have been a better choice.',
]
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, 0.9969, 0.9967],
#         [0.9969, 1.0000, 0.9983],
#         [0.9967, 0.9983, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 585,350 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: 6 tokensmean: 93.98 tokensmax: 128 tokens	min: 54 tokensmean: 117.81 tokensmax: 128 tokens	size: 2 elements

• Samples:

  text_a	text_b	label
  dr. goldberg offers everything i look for in a general practitioner. he's nice and easy to talk to without being patronizing; he's always on time in seeing his patients; he's affiliated with a top-notch hospital (nyu) which my parents have explained to me is very important in case something happens and you need surgery; and you can get referrals to see specialists without having to see him first. really, what more do you need? i'm sitting here trying to think of any complaints i have about him, but i'm really drawing a blank.	OMG, DELICIOUS!\nMy husband and I were in Vegas for a friend's graduation and I needed to come here. I'm pretty sure this place was on TV. We actually drove totally out of our way on the way to the actual graduation, and after a big brunch, just to have some custard. \nThey have a variety of custard flavors, which change daily, and a variety of toppings to put on. You can make up your own combo or pick from the board. They also do a standard size unless you tell them you want something else. \nWe ordered the Western Sundae and goggled it up in the car within five minutes. The custard is thick and creamy and the toppings were good. They did skimp on the hot fudge sauce, but I'm not even mad because everything else was so good.	[1.0, 0.0]
  Unfortunately, the frustration of being Dr. Goldberg's patient is a repeat of the experience I've had with so many other doctors in NYC -- good doctor, terrible staff. It seems that his staff simply never answers the phone. It usually takes 2 hours of repeated calling to get an answer. Who has time for that or wants to deal with it? I have run into this problem with many other doctors and I just don't get it. You have office workers, you have patients with medical needs, why isn't anyone answering the phone? It's incomprehensible and not work the aggravation. It's with regret that I feel that I have to give Dr. Goldberg 2 stars.	Let me start by saying I have no idea about the food here, it could be amazing and knock my socks off, but I will not be back to find out.\n\nWe came here on a Saturday night and it was annoying. The service was decent, the drinks pretty strong....that's all that I can say in the good arena here. \n\nThe atmosphere is boring and uninspired, the decor blah and the clientele douchey. (if that's even a word) Prime example: a 45 year old guy in an Affliction shirt with a sparkly peace sign on the back...what?! There have to be better places to hang out in Scottsdale.	[1.0, 0.0]
  Been going to Dr. Goldberg for over 10 years. I think I was one of his 1st patients when he started at MHMG. He's been great over the years and is really all about the big picture. It is because of him, not my now former gyn Dr. Markoff, that I found out I have fibroids. He explores all options with you and is very patient and understanding. He doesn't judge and asks all the right questions. Very thorough and wants to be kept in the loop on every aspect of your medical health and your life.	Yeah, this place is pretty good.\n\nWe live in Glendale (shut it, we know) and the food is definitely worth the drive to Tempe. While I am sure this spot was always popular due to the food and location in the heart of ASU, its cameo on Man vs. Food has done nothing if made Chompie's a must visit for out-of-towners. Have no fear, as the food does not disappoint, ESPECIALLY the sliders. I cannot say enough about how good those stupid mini-sandwiches are. They receive top billing and completely deserve it.\n\nThis is a deli and bakery in the truest sense of the word. There are several menu options, but sandwiches and baked goods are the stars here. Come hungry because Chompie's does not know the meaning of the phrase "manageable portion." Depending on the time, you may be forced to wait for seating, but that should reinforce the notion that you came to the right place. To give you perspective, we came in July and gladly sat outside just so we could eat sooner, desert sun be dam...	[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

• 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

• The bold row denotes the saved checkpoint.

Training Time

• Training: 12.5 minutes
• Evaluation: 4.3 minutes
• Total: 16.8 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",
}