---
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_english_bert_large_cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_322
  results: []
---

<!-- 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. -->

# populism_classifier_322

This model is a fine-tuned version of [AnonymousCS/populism_english_bert_large_cased](https://huggingface.co/AnonymousCS/populism_english_bert_large_cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1391
- Accuracy: 0.9705
- 1-f1: 0.3243
- 1-recall: 0.2069
- 1-precision: 0.75
- Balanced Acc: 0.6022

## 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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
| 0.8312        | 1.0   | 53   | 0.3415          | 0.9741   | 0.5769 | 0.5172   | 0.6522      | 0.7537       |
| 0.2674        | 2.0   | 106  | 0.3158          | 0.9068   | 0.3680 | 0.7931   | 0.2396      | 0.8520       |
| 0.0309        | 3.0   | 159  | 0.3742          | 0.9469   | 0.4156 | 0.5517   | 0.3333      | 0.7563       |
| 0.0583        | 4.0   | 212  | 0.4696          | 0.9693   | 0.4583 | 0.3793   | 0.5789      | 0.6848       |
| 0.0358        | 5.0   | 265  | 1.1391          | 0.9705   | 0.3243 | 0.2069   | 0.75        | 0.6022       |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3