populism_model350

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

• Loss: 0.5635
• Accuracy: 0.7083
• 1-f1: 0.7586
• 1-recall: 0.9167
• 1-precision: 0.6471
• Balanced Acc: 0.7083

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 OptimizerNames.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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
No log	1.0	1	0.6523	0.625	0.5263	0.4167	0.7143	0.625
0.7743	2.0	2	0.6523	0.625	0.5263	0.4167	0.7143	0.625
0.7743	3.0	3	0.6329	0.75	0.8	1.0	0.6667	0.75
0.6987	4.0	4	0.6122	0.75	0.8	1.0	0.6667	0.75
0.6987	5.0	5	0.5635	0.7083	0.7586	0.9167	0.6471	0.7083

Framework versions

• Transformers 4.52.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1