metadata

base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      Dominica is striving for multi-sectoral and multi-level adaptation across
      all segments of society, giving particular consideration to vulnerable
      groups - the poor, disabled, elderly and Kalinago community; as well as
      gender disparities. Recognising the threats posed by climate change,
      Dominica has over the last two decades, undertaken a number of initiatives
      to respond to this threat. The adaptation component has been revised to
      incorporate updated information on regional climate change projections and
      impacts on Caribbean SIDS.
  - text: >-
      They live in geographical regions and ecosystems that are the most
      vulnerable to climate change. These include polar regions, humid tropical
      forests, high mountains, small islands, coastal regions, and arid and
      semi-arid lands, among others. The impacts of climate change in such
      regions have strong implications for the ecosystem-based livelihoods on
      which many indigenous peoples depend. Moreover, in some regions such as
      the Pacific, the very existence of many indigenous territories is under
      threat from rising sea levels that not only pose a grave threat to
      indigenous peoples’ livelihoods but also to their cultures and ways of
      life.
  - text: >-
      Enhancing climate change resilience in the Benguela current fisheries
      system (regional project: Angola, Namibia and South Africa). The project
      aims to build resilience and reduce vulnerability of the Benguela Current
      marine fisheries systems to climate change through strengthened adaptive
      capacity and implementation of participatory and integrated adaptive
      strategies in order to ensure food and livelihood security. Fisheries.
      Agriculture and food security. Total project cost (US $ million): 16.520.
      Implementing GEF agency: FAO.
  - text: >-
      As the average annual precipitation across the country is expected to
      decline 2.6-3.4% by 2025 and 5.9-6.3% by 2050 this will result direct
      yield response. As described by PACE experiment59 on the Pastures and
      Climate Extremes using a factorial combination of elevated temperature
      (ambient +3°C) and winter/spring extreme drought (60% rainfall reduction)
      resulted in productivity declines of up to 73%. Functional group identity
      was not an important predictor of yield response to drought.
  - text: >-
      Poor rural households in marginal territories that have a low productive
      potential and/or that are far from markets and infrastructure are highly
      vulnerable to climate-change impacts and could easily fall into
      poverty-environment traps 9. This means that communities that are already
      struggling economically and geographically isolated are at greater risk of
      experiencing the negative impacts of climate change on their agricultural
      livelihoods.
inference: false
co2_eq_emissions:
  emissions: 268.4261122496047
  source: codecarbon
  training_type: fine-tuning

SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-mpnet-base-v2 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: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
Classification head: a SetFitHead instance
Maximum Sequence Length: 128 tokens
Number of Classes: 18 classes

Model Sources

Repository: SetFit on GitHub
Paper: Efficient Few-Shot Learning Without Prompts
Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

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("GIZ/vulnerability_multilabel_v2")
# Run inference
preds = model("Poor rural households in marginal territories that have a low productive potential and/or that are far from markets and infrastructure are highly vulnerable to climate-change impacts and could easily fall into poverty-environment traps 9. This means that communities that are already struggling economically and geographically isolated are at greater risk of experiencing the negative impacts of climate change on their agricultural livelihoods.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	61.2897	164

Training Hyperparameters

batch_size: (16, 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
0.0002	1	0.2095	-
0.2084	1000	0.0307	0.1211
0.4168	2000	0.0165	0.1275
0.6251	3000	0.0085	0.131
0.8335	4000	0.0317	0.1171

Framework Versions

Python: 3.9.5
SetFit: 1.0.3
Sentence Transformers: 3.0.1
Transformers: 4.44.2
PyTorch: 2.4.0+cu121
Datasets: 2.3.0
Tokenizers: 0.19.1

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.155 kg of CO2
Hours Used: 1.08 hours

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}
}