populism_classifier_bsample_132

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: 1.0814
• Accuracy: 0.6426
• 1-f1: 0.128
• 1-recall: 0.8889
• 1-precision: 0.0690
• Balanced Acc: 0.7620

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
0.1746	1.0	4	1.6979	0.5279	0.1111	1.0	0.0588	0.7568
0.0554	2.0	8	0.7286	0.8033	0.0909	0.3333	0.0526	0.5755
0.2833	3.0	12	0.7481	0.7967	0.0882	0.3333	0.0508	0.5721
0.0565	4.0	16	1.0814	0.6426	0.128	0.8889	0.0690	0.7620

Framework versions

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