populism_model351

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: 0.3870
• Accuracy: 0.8525
• 1-f1: 0.8696
• 1-recall: 1.0
• 1-precision: 0.7692
• Balanced Acc: 0.8548

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
0.4028	1.0	2	0.4842	0.7869	0.7451	0.6333	0.9048	0.7844
0.568	2.0	4	0.4842	0.7869	0.7451	0.6333	0.9048	0.7844
0.5091	3.0	6	0.3164	0.8689	0.875	0.9333	0.8235	0.8699
0.2573	4.0	8	0.4203	0.8525	0.8696	1.0	0.7692	0.8548
0.2775	5.0	10	0.3870	0.8525	0.8696	1.0	0.7692	0.8548

Framework versions

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