metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
base_model: kinit/slovakbert-sentiment-twitter
metrics:
- accuracy
widget:
- text: >-
Pan Vilasek bol velmi mily, snaizl sa spestrit vyucbu zaujimavymi
aktivitami. a zaroven sa snazil nam vstiepit nieco z nemciny. skripta z
ktorych sa ucime by vsak mohli byt kusok zlozitejsie, slovna zasoba je
vecsinou trivialna...
- text: >-
Predmet na ktorom sa skvelo naucite zaklady html a css a celkovo
webdizajnu, dobre prednasky a cvicenia kde si to precvicite
- text: >-
Super zostavena prednaska, veci pre mna zaujimave, lebo viem ze sa celkom
pouzivaju, vyborne vysvetlovane, tempo na mna tak akurat - vela sa stihlo
(clovek sa nenudil) ale na druhej strane sa aj dalo stihat ak si to clovek
aspon raz za cas pozrel. Co som pocul tak niektori si stazovali na
narocnost vykladu, ale myslim ze to je skor tym, ze ked sa na to niekto
ani raz nepozrie nemoze cakat ze vsetko hned na prve pocutie pochopi. este
raz - super
- text: >-
potešili by ma praktické ukážky namiesto viacnásobných odvodení podobných
vecí
- text: Veľmi zaujímavé, zrozumiteľne podané a niekedy aj vtipné:)
pipeline_tag: text-classification
inference: true
model-index:
- name: SetFit with kinit/slovakbert-sentiment-twitter
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.6830314585319351
name: Accuracy
SetFit with kinit/slovakbert-sentiment-twitter
This is a SetFit model that can be used for Text Classification. This SetFit model uses kinit/slovakbert-sentiment-twitter 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: kinit/slovakbert-sentiment-twitter
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 514 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 |
---|---|
0 |
|
-1 |
|
1 |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.6830 |
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("pEpOo/setfit-model-24-3")
# Run inference
preds = model("Veľmi zaujímavé, zrozumiteľne podané a niekedy aj vtipné:)")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 1 | 41.9167 | 128 |
Label | Training Sample Count |
---|---|
-1 | 8 |
0 | 8 |
1 | 0 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (10, 10)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 10
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
---|---|---|---|
0.0333 | 1 | 0.3101 | - |
1.6667 | 50 | 0.0032 | - |
3.3333 | 100 | 0.0012 | - |
5.0 | 150 | 0.0004 | - |
6.6667 | 200 | 0.0002 | - |
8.3333 | 250 | 0.0003 | - |
10.0 | 300 | 0.0002 | - |
Framework Versions
- Python: 3.11.0
- SetFit: 1.0.3
- Sentence Transformers: 2.5.1
- Transformers: 4.38.2
- PyTorch: 2.2.1+cu121
- Datasets: 2.18.0
- Tokenizers: 0.15.2
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}
}