metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: cc_narratives_robertamodel2
results: []
widget:
- text: >-
I believe net zero target lacks legitimacy and without a referendum the
current climate change policy lacks the explicit consent of the people.
- text: >-
Solar panels installed within new homes would be far cheaper than retro
fitting after construction.This would help on home running costs and
assist in our climate policy pledge on carbon emission
- text: >-
It is environmentally irresponsible to allow garden space occupied by
grass and other plant life (which processes CO2 and supports wildlife) to
be replaced by plastic which does not biodegrade
base_model
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9156
- F1: 0.7112
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: 2e-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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 1.0269 | 1.0 | 22 | 0.9767 | 0.3192 |
| 0.9372 | 2.0 | 44 | 0.9233 | 0.4689 |
| 0.7988 | 3.0 | 66 | 0.8628 | 0.5678 |
| 0.6139 | 4.0 | 88 | 0.8515 | 0.6001 |
| 0.4226 | 5.0 | 110 | 0.9094 | 0.6003 |
| 0.2551 | 6.0 | 132 | 1.0029 | 0.6192 |
| 0.1439 | 7.0 | 154 | 1.0345 | 0.6581 |
| 0.0872 | 8.0 | 176 | 1.1825 | 0.6431 |
| 0.0702 | 9.0 | 198 | 1.2059 | 0.6468 |
| 0.0497 | 10.0 | 220 | 1.2089 | 0.6403 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3