populism_classifier_bsample_258

This model is a fine-tuned version of AnonymousCS/populism_multilingual_roberta_base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5183
• Accuracy: 0.8992
• 1-f1: 0.4948
• 1-recall: 0.8571
• 1-precision: 0.3478
• Balanced Acc: 0.8794

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: 32
• eval_batch_size: 32
• 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
0.1862	1.0	7	0.5108	0.8765	0.4737	0.9643	0.3140	0.9177
0.0203	2.0	14	0.5728	0.8519	0.4286	0.9643	0.2755	0.9046
0.0154	3.0	21	0.5183	0.8992	0.4948	0.8571	0.3478	0.8794

Framework versions

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