populism_model344

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: 0.4234
• Accuracy: 0.8378
• 1-f1: 0.8421
• 1-recall: 0.8889
• 1-precision: 0.8
• Balanced Acc: 0.8392

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
0.3721	1.0	2	0.4823	0.7568	0.7429	0.7222	0.7647	0.7558
0.2987	2.0	4	0.4372	0.7838	0.7778	0.7778	0.7778	0.7836
0.3109	3.0	6	0.4250	0.8378	0.8421	0.8889	0.8	0.8392
0.2663	4.0	8	0.4238	0.8378	0.8421	0.8889	0.8	0.8392
0.2923	5.0	10	0.4234	0.8378	0.8421	0.8889	0.8	0.8392

Framework versions

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