metadata
license: apache-2.0
base_model: sentence-transformers/all-mpnet-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: IKT_classifier_conditional_best
results: []
widget:
- text: >-
Brick Kilns. Enforcement and Improved technology use. Residential and
Commercial. Enhanced use of energy- efficient appliances in household and
commercial buildings. F-Gases. Implement Montreal Protocol targets.
Industry. Achieve 10% Energy efficiency in the Industry sub-sector through
measures according to the Energy Efficiency and Conservation Master Plan
(EECMP). Agriculture. Implementation of 5925 Nos. solar irrigation pumps
(generating 176.38MW) for agriculture. Brick Kilns. 14% emission reduction
through Banning Fixed Chimney kiln (FCK), encourage advanced technology
and non-fired brick use. Residential and Commercial.
example_title: UNCONDITIONAL
- text: >-
Achieve 20% Energy efficiency in the Industry sub-sector through measures
according to the Energy Efficiency and Conservation Master Plan (EECMP).
Promote green Industry. Promote carbon financing. Agriculture. Enhanced
use of solar energy in Agriculture. Agriculture. Implementation of 4102
Nos. solar irrigation pumps (generating 164 MW) for agriculture. Brick
Kilns. Enforcement and Improved technology use. Brick Kilns. 47% emission
reduction through Banning Fixed Chimney kiln (FCK), encourage advanced
technology and non-fired brick use. Residential and Commercial.
example_title: CONDITIONAL
- text: >-
The GHG emission reductions from Cairo metro network includes the
rehabilitation of existing lines 1, 2, and 3. • The development of
Alexandria Metro (Abu Qir – Alexandria railway line) and rehabilitation of
the Raml tram line.
example_title: CONDITIONAL
IKT_classifier_conditional_best
This model is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 on the GIZ/policy_qa_v0_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9766
- Precision Macro: 0.8010
- Precision Weighted: 0.8078
- Recall Macro: 0.7928
- Recall Weighted: 0.8093
- F1-score: 0.7963
- Accuracy: 0.8093
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4.112924307850544e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 400.0
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision Macro | Precision Weighted | Recall Macro | Recall Weighted | F1-score | Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| 0.6562 | 1.0 | 696 | 0.5617 | 0.7283 | 0.7423 | 0.7283 | 0.7423 | 0.7283 | 0.7423 |
| 0.6091 | 2.0 | 1392 | 0.6492 | 0.7345 | 0.7443 | 0.7251 | 0.7474 | 0.7287 | 0.7474 |
| 0.3892 | 3.0 | 2088 | 0.7730 | 0.7848 | 0.7872 | 0.7612 | 0.7887 | 0.7687 | 0.7887 |
| 0.2509 | 4.0 | 2784 | 0.9735 | 0.7778 | 0.7937 | 0.7858 | 0.7887 | 0.7807 | 0.7887 |
| 0.1648 | 5.0 | 3480 | 0.9766 | 0.8010 | 0.8078 | 0.7928 | 0.8093 | 0.7963 | 0.8093 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3