Administration_RuRoberta_aug1

This model is a fine-tuned version of sberbank-ai/ruRoberta-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.9782
• Accuracy: 0.3559
• Top 2 Accuracy: 0.4949
• Top 3 Accuracy: 0.5995
• Roc Auc: 0.9207
• F1: 0.3141

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: 12
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Top 2 Accuracy	Top 3 Accuracy	Roc Auc	F1
4.1507	1.0	987	3.6147	0.2781	0.4082	0.4745	0.8956	0.2296
1.7773	2.0	1974	2.9782	0.3559	0.4949	0.5995	0.9207	0.3141

Framework versions

• Transformers 4.55.2
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4