populism_classifier_bsample_080

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7741
• Accuracy: 0.8164
• 1-f1: 0.2222
• 1-recall: 0.8889
• 1-precision: 0.1270
• Balanced Acc: 0.8515

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.0652	1.0	8	0.6031	0.8459	0.2295	0.7778	0.1346	0.8129
0.0156	2.0	16	1.9513	0.6164	0.1333	1.0	0.0714	0.8024
0.0343	3.0	24	0.7741	0.8164	0.2222	0.8889	0.1270	0.8515

Framework versions

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