metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
Further research is needed to develop more effective methods for the
detection and inhibition of ESBLs in clinical settings.
- text: >-
Although the phosphomolybdenum method presents high accuracy and precision
for vitamin E quantitation, its applicability to other antioxidants may
require further investigation.
- text: >-
The persistent inflammation observed in Interleukin-10-deficient mice
provides insight into the role of this cytokine in maintaining intestinal
homeostasis and highlights the potential implications for human diseases,
such as inflammatory bowel syndrome.
- text: >-
The proposed algorithms in this paper utilize Hamilton-Jacobi formulations
to calculate the front propagation speed, which depends on the curvature
of the front.
- text: >-
The IC50 values obtained from the semiautomated microdilution assay
suggest that artesunate and dihydroartemisinin exhibit comparable
antimalarial activity against the Plasmodium falciparum strains tested.
pipeline_tag: text-classification
inference: true
base_model: kaisugi/scitoricsbert
model-index:
- name: SetFit with kaisugi/scitoricsbert
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.8833333333333333
name: Accuracy
SetFit with kaisugi/scitoricsbert
This is a SetFit model that can be used for Text Classification. This SetFit model uses kaisugi/scitoricsbert 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: kaisugi/scitoricsbert
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 12 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 |
|---|---|
| Aims |
|
| Background |
|
| Hypothesis |
|
| Implications |
|
| Importance |
|
| Limitations |
|
| Method |
|
| None |
|
| Purpose |
|
| Reccomendations |
|
| Result |
|
| Uncertainty |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.8833 |
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("Corran/SciGenSetfit2")
# Run inference
preds = model("Further research is needed to develop more effective methods for the detection and inhibition of ESBLs in clinical settings.")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 11 | 28.3767 | 60 |
| Label | Training Sample Count |
|---|---|
| Aims | 100 |
| Background | 100 |
| Hypothesis | 100 |
| Implications | 100 |
| Importance | 100 |
| Limitations | 100 |
| Method | 100 |
| None | 100 |
| Purpose | 100 |
| Reccomendations | 100 |
| Result | 100 |
| Uncertainty | 100 |
Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- 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
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0053 | 1 | 0.2248 | - |
| 0.2660 | 50 | 0.1239 | - |
| 0.5319 | 100 | 0.1105 | - |
| 0.7979 | 150 | 0.0665 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.2.2
- Transformers: 4.36.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.16.1
- Tokenizers: 0.15.0
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}
}