populism_classifier_bsample_051

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

• Loss: 0.8707
• Accuracy: 0.8015
• 1-f1: 0.2697
• 1-recall: 0.6486
• 1-precision: 0.1702
• Balanced Acc: 0.7297

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
0.1637	1.0	9	0.8019	0.7954	0.2872	0.7297	0.1788	0.7645
0.0719	2.0	18	1.0117	0.6718	0.2456	0.9459	0.1411	0.8006
0.1512	3.0	27	0.8707	0.8015	0.2697	0.6486	0.1702	0.7297

Framework versions

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