metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
Title: 72'' Double Bathroom Vanity Set Base Finish: Black Description:
This 72'' double bathroom vanity set gives your bathroom a more
traditional look with its dentil molding, side columns, and Carrara marble
countertop. It features a solid and engineered wood base, with two
oval-shaped, porcelain sinks (faucets sold separately) on the countertop.
Two paneled cabinet doors beneath each sink open to reveal multiple
shelves, giving ample storage space for towels and cleaning supplies.
There are three additional functional drawers in the middle for toiletries
and other bathroom essentials, with a false drawer over each cabinet to
protect the under-mount sinks. Best of all, this vanity arrives fully
assembled. Features: {'list': array([{'element': 'Two sets of predrilled
three faucet holes; 8-inch spread; the faucet is not included'},
{'element': 'Designed with two false drawers and three functional drawers with soft closing glides'}],
dtype=object)}
- text: >-
Title: Felicity 60" Double Bathroom Vanity Set Base Finish: Natural Ash,
Top Finish: Pure White Matte Description: Bring mid-century style and
modern functionality to your bathroom with this striking vanity. Real ash
veneers add an airy warmth to the solid wood frame. The pure white quartz
top is both sleek and functional. Soft-closing doors and drawers provide
smooth access to ample storage space. Features: {'list':
array([{'element': 'The pulls are as follows:\nLarge: 0.04" x 0.98" x
12.52" - Space between holes 11,61"\nSmall: 0.59" x 0.98" x 7.52" - Space
between holes 6,69"'}],
dtype=object)}
- text: >-
Title: Babajide 42'' Wall-Mounted Single Bathroom Vanity Set Base Finish:
High Gloss White Description: This modern floating vanity gives your
bathroom an instant upgrade. This wall-mounted piece features a
rectangular, engineered wood base. Its two drawers feature soft-close
glides and plenty of space for toiletries and makeup. The integrated
acrylic sink is also rectangular and features ample room around its edge
for candles, a vase, or other decorative favorites. This vanity comes
fully assembled, so you can refresh your bathroom with ease. It completes
the look of any contemporary home. Features: {'list': array([],
dtype=object)}
- text: >-
Title: Binford 30" Single Bathroom Vanity Set Base Finish: Walnut
Description: This freestanding single vanity set brings a mix of rustic
and mid-century to your bathroom or powder room. It has a solid and
engineered wood base with flared legs and a two-door, soft-close cabinet,
the perfect spot to tuck away all your bathroom essentials. Measuring 30"
wide, it's ideal for tighter spaces and smaller bathrooms. Resting on top
is a white ceramic countertop with an integrated sink for a crisp,
streamlined design. Cabinet hardware is included, and a faucet sold
separately. Features: {'list': array([{'element': 'Space-saving yet
functional with hidden storage'},
{'element': 'The approximate distance from the edge/side of the vanity top to the sink opening: about 4"'},
{'element': 'Matte black hardware, 2 soft-close doors, and 1 false drawer'},
{'element': 'The handle\'s overall length is approx. 150 mm. (5.9")'},
{'element': 'The distance between the two screws is approx. 128 mm. (5")'},
{'element': 'Distance base of the vanity (where legs are attached) to the end of the legs (floor): 131.6 mm.'}],
dtype=object)}
- text: >-
Title: Aurilla 30" Wall-Mount Single Bathroom Vanity Set with Right Side
Shelf Base Color: White Description: Elevate your daily routine with this
wall-mounted single vanity set. The high-density ceramic countertop and
drop-in basin are both polished white, providing a sleek and clean look.
The base is handcrafted from hardwood and plywood. With two soft-close
drawers and open shelving, you'll have ample storage for your bathroom
essentials. The brushed nickel handles and knobs add a touch of elegance
to this vanity. In addition, an open back allows for convenient plumbing
access, while the fade-resistant and UV-resistant finish ensures lasting
beauty. Note that the faucet, mirror, and backsplash are not included.
Features: {'list': array([{'element': '30 in. W x 18.5 in. D x 20.75 in. H
single-sink bathroom vanity offers generous storage solutions, making it
the perfect choice for rooms with limited space'},
{'element': 'Wall-mounted design is beneficial for space efficiency and convenient cleaning'},
{'element': 'The shelves on the right side of the cabinet provides space for storing frequently used items'},
{'element': 'Pre-drilled single faucet hole designed for easy installation '},
{'element': '2 functional drawer with 2 shelf offers generous storage capacity'},
{'element': 'The solid wood cabinet and hand-polished top offer superior quality and durability suitable for any bathroom setting'},
{'element': 'Soft-close glides guarantee quiet and effortless closing of drawers. Plus the stay-stop feature prevents accidental dropping and potential harm'},
{'element': 'Arriving fully assembled from the manufacture, swift and effortless, ready for installation'},
{'element': 'Dovetail drawer construction provide stronger joints'},
{'element': 'Sink overflow included, helps to prevent water from over spilling'},
{'element': 'Mirror and Faucet not included'}], dtype=object)}
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2
model-index:
- name: SetFit with sentence-transformers/all-MiniLM-L6-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.8837209302325582
name: Accuracy
SetFit with sentence-transformers/all-MiniLM-L6-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification.
The model has been trained using an efficient few-shot learning technique that involves:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: sentence-transformers/all-MiniLM-L6-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 256 tokens
- Number of Classes: 3 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
| Label | Examples |
|---|---|
| Other |
|
| Marble |
|
| Quartz |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.8837 |
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("setfit_model_id")
# Run inference
preds = model("Title: Felicity 60\" Double Bathroom Vanity Set Base Finish: Natural Ash, Top Finish: Pure White Matte Description: Bring mid-century style and modern functionality to your bathroom with this striking vanity. Real ash veneers add an airy warmth to the solid wood frame. The pure white quartz top is both sleek and functional. Soft-closing doors and drawers provide smooth access to ample storage space. Features: {'list': array([{'element': 'The pulls are as follows:\nLarge: 0.04\" x 0.98\" x 12.52\" - Space between holes 11,61\"\nSmall: 0.59\" x 0.98\" x 7.52\" - Space between holes 6,69\"'}],
dtype=object)}")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 55 | 164.9107 | 413 |
| Label | Training Sample Count |
|---|---|
| Marble | 49 |
| Quartz | 34 |
| Other | 85 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- evaluation_strategy: epoch
- eval_max_steps: -1
- load_best_model_at_end: True
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0009 | 1 | 0.1699 | - |
| 0.0458 | 50 | 0.2635 | - |
| 0.0917 | 100 | 0.1972 | - |
| 0.1375 | 150 | 0.0984 | - |
| 0.1833 | 200 | 0.0614 | - |
| 0.2291 | 250 | 0.048 | - |
| 0.2750 | 300 | 0.0155 | - |
| 0.3208 | 350 | 0.0094 | - |
| 0.3666 | 400 | 0.0065 | - |
| 0.4125 | 450 | 0.0059 | - |
| 0.4583 | 500 | 0.0029 | - |
| 0.5041 | 550 | 0.0033 | - |
| 0.5500 | 600 | 0.0031 | - |
| 0.5958 | 650 | 0.0022 | - |
| 0.6416 | 700 | 0.002 | - |
| 0.6874 | 750 | 0.0018 | - |
| 0.7333 | 800 | 0.0018 | - |
| 0.7791 | 850 | 0.0013 | - |
| 0.8249 | 900 | 0.0013 | - |
| 0.8708 | 950 | 0.0011 | - |
| 0.9166 | 1000 | 0.0012 | - |
| 0.9624 | 1050 | 0.0012 | - |
| 1.0 | 1091 | - | 0.1489 |
Framework Versions
- Python: 3.12.0
- SetFit: 1.1.3
- Sentence Transformers: 3.4.1
- Transformers: 4.57.6
- PyTorch: 2.10.0
- Datasets: 4.5.0
- Tokenizers: 0.22.2
Citation
BibTeX
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}