populism_classifier_bsample_149

This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert_cased_v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5412
• Accuracy: 0.8720
• 1-f1: 0.3564
• 1-recall: 0.9
• 1-precision: 0.2222
• Balanced Acc: 0.8855

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
0.143	1.0	6	0.3808	0.8819	0.375	0.9	0.2368	0.8906
0.011	2.0	12	0.5273	0.8543	0.3509	1.0	0.2128	0.9242
0.0453	3.0	18	0.5412	0.8720	0.3564	0.9	0.2222	0.8855

Framework versions

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