populism_model356

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: 0.5670
• Accuracy: 0.6984
• 1-f1: 0.7164
• 1-recall: 0.7742
• 1-precision: 0.6667
• Balanced Acc: 0.6996

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
0.8437	1.0	2	0.8034	0.6032	0.3902	0.2581	0.8	0.5978
0.7286	2.0	4	0.6622	0.6349	0.6849	0.8065	0.5952	0.6376
0.5573	3.0	6	0.5795	0.6984	0.6780	0.6452	0.7143	0.6976
0.4996	4.0	8	0.5647	0.6984	0.6984	0.7097	0.6875	0.6986
0.4434	5.0	10	0.5670	0.6984	0.7164	0.7742	0.6667	0.6996

Framework versions

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