Update README.md

README.md

@@ -8,42 +8,46 @@ tags:
 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.
+- 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:
@@ -56,6 +60,8 @@ co2_eq_emissions:
   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
@@ -68,6 +74,13 @@ The model has been trained using an efficient few-shot learning technique that i
 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
+- **Target**: Targets are an intention to achieve a specific result, for example, to reduce GHG emissions to a specific level 
+            (a GHG target) or increase energy efficiency or renewable energy to a specific level (a non-GHG target), typically by  
+            a certain date.
+- **Action**: Actions are an intention to implement specific means of achieving GHG reductions, usually in forms of concrete projects.
+- **Policies**: Policies are domestic planning documents such as policies, regulations or guidlines.
 
 ### Model Description
 - **Model Type:** SetFit
@@ -101,7 +114,7 @@ Then you can load this model and run inference.
 from setfit import SetFitModel
 
 # Download from the 🤗 Hub
-model = SetFitModel.from_pretrained("ppsingh/SUBTARGET_multilabel_bge")
+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.")
 ```
@@ -137,6 +150,22 @@ preds = model("This document enfolds Iceland’s first communication on its long
 |:-------------|:----|:--------|:----|
 | 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)
@@ -154,7 +183,7 @@ preds = model("This document enfolds Iceland’s first communication on its long
 - eval_max_steps: -1
 - load_best_model_at_end: False
 
-### Training Results
+### Embedding Training Results
 | Epoch  | Step  | Training Loss | Validation Loss |
 |:------:|:-----:|:-------------:|:---------------:|
 | 0.0000 | 1     | 0.2227        | -               |
@@ -165,6 +194,13 @@ preds = model("This document enfolds Iceland’s first communication on its long
 | 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](https://github.com/mlco2/codecarbon).
 - **Carbon Emitted**: 0.268 kg of CO2