populism_model340

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: 0.4915
• Accuracy: 0.7551
• 1-f1: 0.76
• 1-recall: 0.7917
• 1-precision: 0.7308
• Balanced Acc: 0.7558

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
0.4345	1.0	2	0.4803	0.7755	0.8	0.9167	0.7097	0.7783
0.396	2.0	4	0.4746	0.7551	0.7778	0.875	0.7	0.7575
0.3556	3.0	6	0.4891	0.7551	0.76	0.7917	0.7308	0.7558
0.3484	4.0	8	0.4953	0.7551	0.76	0.7917	0.7308	0.7558
0.3412	5.0	10	0.4915	0.7551	0.76	0.7917	0.7308	0.7558

Framework versions

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