populism_classifier_306

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

• Loss: 0.5256
• Accuracy: 0.8889
• 1-f1: 0.6452
• 1-recall: 0.8
• 1-precision: 0.5405
• Balanced Acc: 0.8509

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: 128
• eval_batch_size: 128
• 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
0.4737	1.0	7	0.3745	0.8384	0.5789	0.88	0.4314	0.8562
0.1756	2.0	14	0.4435	0.8636	0.5970	0.8	0.4762	0.8364
0.2844	3.0	21	0.5256	0.8889	0.6452	0.8	0.5405	0.8509

Framework versions

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