populism_classifier_bsample_021

This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7006
• Accuracy: 0.6532
• 1-f1: 0.3645
• 1-recall: 0.9737
• 1-precision: 0.2242
• Balanced Acc: 0.7952

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
0.3713	1.0	6	0.6526	0.7473	0.4198	0.8947	0.2742	0.8126
0.1364	2.0	12	0.9083	0.5887	0.3319	1.0	0.1990	0.7710
0.1126	3.0	18	0.7006	0.6532	0.3645	0.9737	0.2242	0.7952

Framework versions

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