populism_classifier_bsample_343

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

• Loss: 1.0271
• Accuracy: 0.6818
• 1-f1: 0.1635
• 1-recall: 0.8667
• 1-precision: 0.0903
• Balanced Acc: 0.7708

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
0.0885	1.0	7	0.6503	0.7775	0.2185	0.8667	0.125	0.8204
0.0591	2.0	14	1.0615	0.6435	0.1486	0.8667	0.0813	0.7510
0.0387	3.0	21	1.0271	0.6818	0.1635	0.8667	0.0903	0.7708

Framework versions

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