populism_classifier_bsample_139

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: 0.6039
• Accuracy: 0.8303
• 1-f1: 0.3759
• 1-recall: 0.9259
• 1-precision: 0.2358
• Balanced Acc: 0.8753

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
0.0173	1.0	7	0.5255	0.8569	0.4068	0.8889	0.2637	0.8719
0.1835	2.0	14	0.6433	0.8037	0.3425	0.9259	0.2101	0.8612
0.0205	3.0	21	0.6039	0.8303	0.3759	0.9259	0.2358	0.8753

Framework versions

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