metadata
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
metrics:
- accuracy
widget:
- text: >-
During 2021-2030, Thailand s LEDS will be implemented through the NDC
roadmap and sectoral action plans which provide detailed guidance on
measures and realistic actions to achieve the 1st NDC target by 2030, as
well as regular monitoring and evaluation of the progress and achievement.
The monitoring and evaluation of the mitigation measures relating to the
Thailand’s LEDS will be carried out to ensure its effectiveness and
efficiency in achieving its objectives and key performance indicators.
Because it is a long-term plan spanning many years during which many
changes can occur, it is envisaged that it will be subject to a
comprehensive review every five years. This is consistent with the
approach under the Paris Agreement that assigned Parties to submit their
NDCs to the UNFCCC every five year.
- text: >-
The NDC also benefited from the reviews and comments of these implementing
partners as well as local and international experts. Special thanks to The
Honourable Molwyn Joseph, Minister for Health, Wellness and the
Environment, for his unwavering commitment to advance this ambitious
climate change agenda, while Antigua and Barbuda faced an outbreak of the
COVID-19 pandemic. Significant contributions to the process were made by a
wide-cross section of stakeholders from the public and private sector,
civil society, trade and industry groups and training institutions, who
attended NDC-related workshops, consultations and participated in key
stakeholder interviews organized to inform the NDC update.
- text: >-
Antigua and Barbuda will mainstream gender in its energy planning through
an Inclusive Renewable Energy Strategy. This strategy will recognize and
acknowledge, among other things, the gender norms, and inequalities
prevalent in the energy sector, women and men’s differentiated access to
energy, their different energy needs and preferences, and different
impacts that energy access could have on their livelihoods. Antigua and
Barbuda’s plan for an inclusive renewable energy transition will ensure
continued affordable and reliable access to electricity and other energy
services for all.
- text: >-
Thailand’s climate actions are divided into short-term, medium-term and
long-term targets up to 2050. For the mitigation actions, short-term
targets include: (i) develop medium- and long-term GHG emission reduction
targets and prepare roadmaps for the implementation by sector, including
the GHG emission reduction target on a voluntary basis (pre-2020 target),
Nationally Appropriate Mitigation Actions (NAMAs) roadmaps, and
measurement, reporting, and verification mechanisms, (ii) establish
domestic incentive mechanisms to encourage low carbon development. The
medium-term targets include: (i) reduce GHG emissions from energy and
transport sectors by 7-20% against BAU level by 2020, subject to the level
of international support, (ii) supply at least 25% of energy consumption
from renewable energy sources by 2021 and (iii) increase the ratio of
municipalities with more than 10 m2 of green space per capita.
- text: >-
In the oil sector, the country has benefited from 372 million dollars for
the reduction of gas flaring at the initiative (GGFR - "Global Gas Flaring
Reduction") of the World Bank after having adopted in November 2015 a
national reduction plan flaring and associated gas upgrading. In the
electricity sector, the NDC highlights the development of hydroelectricity
which should make it possible to cover 80% of production in 2025, the
remaining 20% ​​being covered by gas and
other renewable energies.
pipeline_tag: text-classification
inference: true
co2_eq_emissions:
emissions: 5.901369050433577
source: codecarbon
training_type: fine-tuning
on_cloud: false
cpu_model: Intel(R) Xeon(R) CPU @ 2.00GHz
ram_total_size: 12.674789428710938
hours_used: 0.185
hardware_used: 1 x Tesla T4
base_model: ppsingh/TAPP-multilabel-mpnet
SetFit with ppsingh/TAPP-multilabel-mpnet
This is a SetFit model that can be used for Text Classification. This SetFit model uses ppsingh/TAPP-multilabel-mpnet as the Sentence Transformer embedding model. A SetFitHead 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: ppsingh/TAPP-multilabel-mpnet
- Classification head: a SetFitHead instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 2 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 |
|---|---|
| NEGATIVE |
|
| TARGET |
|
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("ppsingh/iki_target_setfit")
# Run inference
preds = model("In the oil sector, the country has benefited from 372 million dollars for the reduction of gas flaring at the initiative (GGFR - \"Global Gas Flaring Reduction\") of the World Bank after having adopted in November 2015 a national reduction plan flaring and associated gas upgrading. In the electricity sector, the NDC highlights the development of hydroelectricity which should make it possible to cover 80% of production in 2025, the remaining 20% ​​being covered by gas and other renewable energies.")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 58 | 116.6632 | 508 |
| Label | Training Sample Count |
|---|---|
| NEGATIVE | 51 |
| TARGET | 44 |
Training Hyperparameters
- batch_size: (8, 2)
- num_epochs: (1, 0)
- max_steps: -1
- sampling_strategy: undersampling
- 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: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0018 | 1 | 0.3343 | - |
| 0.1783 | 100 | 0.0026 | 0.1965 |
| 0.3565 | 200 | 0.0001 | 0.1995 |
| 0.5348 | 300 | 0.0001 | 0.2105 |
| 0.7130 | 400 | 0.0001 | 0.2153 |
| 0.8913 | 500 | 0.0 | 0.1927 |
Training Results Classifier
- Classes Representation in Test Data: Target: 9, Negative: 8
- F1-score: 87.8%
- Accuracy: 88.2%
Environmental Impact
Carbon emissions were measured using CodeCarbon.
- Carbon Emitted: 0.006 kg of CO2
- Hours Used: 0.185 hours
Training Hardware
- On Cloud: No
- GPU Model: 1 x Tesla T4
- CPU Model: Intel(R) Xeon(R) CPU @ 2.00GHz
- RAM Size: 12.67 GB
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.3.1
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.3.0
- Tokenizers: 0.15.1
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}
}