populism_classifier_bsample_308

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: 0.9016
• Accuracy: 0.6511
• 1-f1: 0.1341
• 1-recall: 0.6875
• 1-precision: 0.0743
• Balanced Acc: 0.6686

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
0.1745	1.0	4	1.2526	0.4324	0.1217	1.0	0.0648	0.7046
0.1847	2.0	8	0.8414	0.6290	0.1469	0.8125	0.0807	0.7170
0.1609	3.0	12	1.1042	0.5577	0.1429	0.9375	0.0773	0.7398
0.1047	4.0	16	0.9016	0.6511	0.1341	0.6875	0.0743	0.6686

Framework versions

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