populism_classifier_bsample_042

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: 0.9459
• Accuracy: 0.7164
• 1-f1: 0.3968
• 1-recall: 1.0
• 1-precision: 0.2475
• Balanced Acc: 0.8436

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
0.2793	1.0	4	0.5943	0.8097	0.4742	0.92	0.3194	0.8592
0.1153	2.0	8	1.0210	0.6903	0.3759	1.0	0.2315	0.8292
0.1028	3.0	12	0.9459	0.7164	0.3968	1.0	0.2475	0.8436

Framework versions

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