Yashodhar29/deberta-v3-base-cpp

deberta-v3-hybrid-detector_v2_universal

This model is a fine-tuned version of Yuvrajg2107/deberta-v3-hybrid-detector_12 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0389
• Accuracy: 0.9631

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: 5e-06
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0127	0.1455	1000	0.0275	0.9659
0.0083	0.2909	2000	0.0469	0.9541
0.0065	0.4364	3000	0.0439	0.9544
0.0063	0.5818	4000	0.0207	0.9785
0.007	0.7273	5000	0.0342	0.9647
0.0046	0.8727	6000	0.0389	0.9631

Framework versions

• Transformers 4.57.3
• Pytorch 2.6.0+cu124
• Datasets 4.4.2
• Tokenizers 0.22.1