populism_classifier_bsample_049

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: 0.6892
• Accuracy: 0.7523
• 1-f1: 0.3622
• 1-recall: 0.92
• 1-precision: 0.2255
• Balanced Acc: 0.8292

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
1.7215	1.0	6	0.6419	0.8777	0.4872	0.76	0.3585	0.8237
0.0531	2.0	12	1.0382	0.6453	0.3012	1.0	0.1773	0.8079
0.078	3.0	18	0.6892	0.7523	0.3622	0.92	0.2255	0.8292

Framework versions

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