README.md

---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mpnet-multilabel-sector-classifier
  results: []
datasets:
- GIZ/sector_data
co2_eq_emissions: 0.276132
widget:
- text: >-
    Forestry, forestry and wildlife: Vulnerability will be globally high to very
    high in zones 4 and 5, high to medium in the rest of the country but with
    strong trends in woodlands (droughts, extreme events);. - Water, sanitation
    and health: Vulnerability will be globally strong to very strong in zones 4
    and 5, strong to medium in the rest of the country but with strong trends in
    the forested massifs (drought, floods and ground movement)
  example_title: Disaster Risk Management (DRM), Water, Environment
- text: >-
    Change fiscal policies on fossil fuel by 2025 to enable the transition to
    100% renewable energy generation in the transportation sector
  example_title: Transport, Energy
- text: >-
    Implementation of the electro-optical channel regulations for the
    distributed electricians, technicians in other regions and cities. 2- An
    integrated nationalization that complements the use of smart meter
    technology inside buildings. 3- Integrated solar photovoltaic in buildings.
    4- Support your company and use it from local women s clubs and local
    producers. Waste. 1- Setting up waste management laws, which encourages the
    transfer of waste into bottles and bottles, we will burn the waste streams
    and reduce waste. 1- We use the appropriate regulation in our time to remove
    electrical and electrical rations from waste. 2- An integrated application
    for waste management. 3- Investing fire methane on landfill sites. Farming.
    1- Nannnai to protect and increase the natural gaunanat
  example_title: Social Development, Waste, Urban, Buildings
- text: >-
    Distribution of GHG Emissions by Gas in 2018Determined Contribution at the
    National Level Directorate of the Environment Evolution of GHG Emissions by
    Gas between 1990 and 2018Determined Contribution at the National Level
    Directorate of the Environment 2.2 Objectives for the Reduction of
    Greenhouse Gas Emissions by 2030 The Principality of Monaco has set itself
    the objective, within the framework of this National Contribution, of
    reducing its greenhouse gas emissions by 55% by 2030.Determined Contribution
    at the National Level Directorate of the Environment 2.3 Main Policies and
    Measures In order to achieve its objectives by 2030, the Principality of
    Monaco has already implemented important policies and measures
  example_title: Economy-wide
library_name: transformers
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# mpnet-multilabel-sector-classifier

This model is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2273
- Precision Micro: 0.8075
- Precision Weighted: 0.8110
- Precision Samples: 0.8365
- Recall Micro: 0.8897
- Recall Weighted: 0.8897
- Recall Samples: 0.8922
- F1-score: 0.8464

## Model description

This model is trained for performing **Multi Label Sector Classification**. 


### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 6.9e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 8
- weight_decay: 0.001
- gradient_acumulation_steps: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Weighted | Precision Samples | Recall Micro | Recall Weighted | Recall Samples | F1-score |
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:------------------:|:-----------------:|:------------:|:---------------:|:--------------:|:--------:|
| 0.4478        | 1.0   | 897  | 0.2277          | 0.6731          | 0.7183             | 0.7460            | 0.8822       | 0.8822          | 0.8989         | 0.7871   |
| 0.2241        | 2.0   | 1794 | 0.1862          | 0.7088          | 0.7485             | 0.7754            | 0.8933       | 0.8933          | 0.9110         | 0.8108   |
| 0.1647        | 3.0   | 2691 | 0.2025          | 0.6785          | 0.7023             | 0.7634            | 0.9124       | 0.9124          | 0.9252         | 0.8077   |
| 0.1232        | 4.0   | 3588 | 0.1839          | 0.7274          | 0.7322             | 0.7976            | 0.9029       | 0.9029          | 0.9134         | 0.8286   |
| 0.0899        | 5.0   | 4485 | 0.1889          | 0.7919          | 0.8007             | 0.8350            | 0.8909       | 0.8909          | 0.9060         | 0.8483   |
| 0.0653        | 6.0   | 5382 | 0.2039          | 0.7478          | 0.7544             | 0.8098            | 0.8973       | 0.8973          | 0.9114         | 0.8346   |
| 0.0462        | 7.0   | 6279 | 0.2149          | 0.7447          | 0.7500             | 0.8060            | 0.8989       | 0.8989          | 0.9107         | 0.8323   |
| 0.0336        | 8.0   | 7176 | 0.2181          | 0.7733          | 0.7780             | 0.8221            | 0.8909       | 0.8909          | 0.9031         | 0.8400   |

## Environmental Impact

*Carbon emissions were estimated using the [codecarbon](https://github.com/mlco2/codecarbon). The carbon emission reported are incluidng the hyperparamter search performed on subset of training data*. 

- **Hardware Type:**  16GB T4
- **Hours used:** 3
- **Cloud Provider:** Google Colab
- **Carbon Emitted** : 0.276132
### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3