populism_classifier_bsample_295

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: 1.1222
• Accuracy: 0.5562
• 1-f1: 0.1811
• 1-recall: 0.8889
• 1-precision: 0.1008
• Balanced Acc: 0.7128

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
0.157	1.0	7	0.7070	0.7157	0.2567	0.8889	0.15	0.7973
0.131	2.0	14	0.9374	0.6217	0.2060	0.8889	0.1165	0.7475
0.1291	3.0	21	1.1222	0.5562	0.1811	0.8889	0.1008	0.7128

Framework versions

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