Hugging Face's logo

GIZ
/
SUBTARGET_multilabel_bge

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Model card Files Community
SUBTARGET_multilabel_bge / README.md
ppsingh's picture
ppsingh
Update README.md
82d6e43 verified
preview code
|
raw
history blame
10 kB
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      Unconditional Reduction The level of reduction planned unconditionally is
      expected to be up to 35% by 2030 as compared to the Business As Usual
      (BAU) scenario, taking 2005 as the reference year.  Conditional Reduction
      In a conditional mitigation scenario Angola plans to reduce further its
      emissions. Therefore, the mitigation options identified in this scenario
      are expected to reduce an additional 15% below BAU emission levels by
      2030.
  - text: >-
      Measure 300 MW total installed biomass power capacity in the country by
      Sector Energy GHG mitigation target 84 ktCO2e on average per year between
      2020 and 2030 Monitoring procedures Newly added biomass capacity will be
      monitored on an annual basis by the Department of Climate Change of the
      Ministry of Natural Resources and Environment using data from the Ministry
      of Energy and Mines  Comments - Installed capacity as of 2019 is around
      40MW  Measure 30% Electric Vehicles penetration for 2-wheelers and
      passengers  cars in national vehicles mix Sector Transport GHG mitigation
      target 30 ktCO2e on average per year between 2020 and 2030 Monitoring
      procedures Share of Electric Vehicles in national vehicle mix will be
      monitored on an annual basis by the Department of Climate Change of the
      Ministry of Natural Resources and Environment using data from the Ministry
      of Public Works and Transport.
  - text: "� Australia adopts a target of net zero emissions by 2050. This is an economy-wide target,\_covering all sectors and gases included in Australia’s national inventory. � In order to achieve net zero by 2050, Australia commits to seven low emissions technology stretch goals - ambitious but realistic goals to bring priority low emissions technologies to economic parity with existing mature technologies."
  - text: >-
      The GoP has taken a series of major initiatives as outlined in chapters 4
      and 5. Hence, Pakistan intends to set a cumulative ambitious conditional
      target of overall 50% reduction of its projected emissions by 2030, with
      15% from the country’s own resources and 35% subject to provision of
      international grant finance that would require USD 101 billion just for
      energy transition. 7.1  HIGH PRIORITY ACTIONS Addressing the Global
      Climate Summit at the United Nations in December 2020, the Prime Minister
      of Pakistan made an announcement to reduce future GHG emissions on a high
      priority basis if international financial and technical resources were made
      available: MITIGATION: 1.
  - text: >-
      This document enfolds Iceland’s first communication on its long-term
      strategy (LTS), to be updated when further analysis and policy documents
      are published on the matter. Iceland is committed to reducing its overall
      greenhouse gas emissions and reaching climate neutrality no later than
      2040 and become fossil fuel free in 2050, which should set Iceland on a
      path to net negative emissions.
pipeline_tag: text-classification
inference: false
co2_eq_emissions:
  emissions: 268.4261122496047
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: Intel(R) Xeon(R) CPU @ 2.20GHz
  ram_total_size: 12.674789428710938
  hours_used: 2.03
  hardware_used: 1 x Tesla V100-SXM2-16GB
base_model: BAAI/bge-base-en-v1.5
datasets:
  - GIZ/policy_classification

SetFit with BAAI/bge-base-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-base-en-v1.5 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:

  1. Fine-tuning a Sentence Transformer with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

The purpose of this model is to predict multiple labels simultaneously from a given input data. Specifically, the model will predict 3 labels - GHGLabel, NetzeroLabel, NonGHGLabel- that are relevant to a particular task or application

  • GHGLabel: GHG targets refer to contributions framed as targeted
    outcomes in GHG terms
  • NetzeroLabel: Identifies if it contains Netzero Target or not.
  • NonGHGLabel: Target not in terms of GHG, like energy efficiency, expansion of Solar Energy production etc.

Model Description

  • Model Type: SetFit
  • Sentence Transformer body: BAAI/bge-base-en-v1.5
  • Classification head: a SetFitHead instance
  • Maximum Sequence Length: 512 tokens
  • Number of Classes: 3 classes

Model Sources

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/SUBTARGET_multilabel_bge")
# Run inference
preds = model("This document enfolds Iceland’s first communication on its long-term strategy (LTS), to be updated when further analysis and policy documents are published on the matter. Iceland is committed to reducing its overall greenhouse gas emissions and reaching climate neutrality no later than 2040 and become fossil fuel free in 2050, which should set Iceland on a path to net negative emissions.")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 19 78.5467 173

  • Training Dataset: 728

    Class Positive Count of Class
    GHGLabel 440
    NetzeroLabel 120
    NonGHGLabel 259

  • Validation Dataset: 80

    Class Positive Count of Class
    GHGLabel 49
    NetzeroLabel 11
    NonGHGLabel 30

Training Hyperparameters

  • batch_size: (8, 2)
  • num_epochs: (1, 0)
  • max_steps: -1
  • sampling_strategy: undersampling
  • body_learning_rate: (6.86e-06, 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

Embedding Training Results

Epoch Step Training Loss Validation Loss
0.0000 1 0.2227 -
0.1519 5000 0.015 0.0831
0.3038 10000 0.0146 0.0924
0.4557 15000 0.0197 0.0827
0.6076 20000 0.0031 0.0883
0.7595 25000 0.0439 0.0865
0.9114 30000 0.0029 0.0914
label precision recall f1-score support
GHG 0.884 0.938 0.910 49.0
Netzero 0.846 1.000 0.916 11.0
NonGHG 0.903 0.933 0.918 30.0

Environmental Impact

Carbon emissions were measured using CodeCarbon.

  • Carbon Emitted: 0.268 kg of CO2
  • Hours Used: 2.03 hours

Training Hardware

  • On Cloud: No
  • GPU Model: 1 x Tesla V100-SXM2-16GB
  • CPU Model: Intel(R) Xeon(R) CPU @ 2.20GHz
  • 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: 2.17.0
  • 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}
}