populism_model338

This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert_uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4165
• Accuracy: 0.8868
• 1-f1: 0.8929
• 1-recall: 0.9615
• 1-precision: 0.8333
• Balanced Acc: 0.8882

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: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.569	1.0	2	0.5026	0.8302	0.8302	0.8462	0.8148	0.8305
0.4745	2.0	4	0.4608	0.8868	0.8929	0.9615	0.8333	0.8882
0.435	3.0	6	0.4388	0.8868	0.8929	0.9615	0.8333	0.8882
0.4108	4.0	8	0.4242	0.8868	0.8929	0.9615	0.8333	0.8882
0.3988	5.0	10	0.4165	0.8868	0.8929	0.9615	0.8333	0.8882

Framework versions

• Transformers 4.52.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1