populism_classifier_bsample_244

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

• Loss: 0.9113
• Accuracy: 0.7635
• 1-f1: 0.1694
• 1-recall: 0.84
• 1-precision: 0.0942
• Balanced Acc: 0.8006

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
0.0772	1.0	9	0.5866	0.8450	0.2012	0.68	0.1181	0.7649
0.0646	2.0	18	0.9917	0.7313	0.1583	0.88	0.0870	0.8035
0.0924	3.0	27	0.9113	0.7635	0.1694	0.84	0.0942	0.8006

Framework versions

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