populism_model348

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: 0.3594
• Accuracy: 0.8475
• 1-f1: 0.8525
• 1-recall: 0.8966
• 1-precision: 0.8125
• Balanced Acc: 0.8483

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
0.3671	1.0	2	0.3591	0.8644	0.8710	0.9310	0.8182	0.8655
0.3393	2.0	4	0.3580	0.8644	0.875	0.9655	0.8	0.8661
0.2977	3.0	6	0.3531	0.8475	0.8525	0.8966	0.8125	0.8483
0.2733	4.0	8	0.3566	0.8475	0.8525	0.8966	0.8125	0.8483
0.2423	5.0	10	0.3594	0.8475	0.8525	0.8966	0.8125	0.8483

Framework versions

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