populism_classifier_bsample_321

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

• Loss: 0.8115
• Accuracy: 0.8998
• 1-f1: 0.4096
• 1-recall: 0.6296
• 1-precision: 0.3036
• Balanced Acc: 0.7726

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
0.134	1.0	7	0.7380	0.8916	0.3908	0.6296	0.2833	0.7683
0.0225	2.0	14	1.4923	0.6033	0.2049	0.9259	0.1152	0.7552
0.0118	3.0	21	0.8115	0.8998	0.4096	0.6296	0.3036	0.7726

Framework versions

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